1 /*M///////////////////////////////////////////////////////////////////////////////////////
\r
3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
\r
5 // By downloading, copying, installing or using the software you agree to this license.
\r
6 // If you do not agree to this license, do not download, install,
\r
7 // copy or use the software.
\r
10 // License Agreement
\r
11 // For Open Source Computer Vision Library
\r
13 // Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
\r
14 // Copyright (C) 2009, Willow Garage Inc., all rights reserved.
\r
15 // Third party copyrights are property of their respective owners.
\r
17 // Redistribution and use in source and binary forms, with or without modification,
\r
18 // are permitted provided that the following conditions are met:
\r
20 // * Redistribution's of source code must retain the above copyright notice,
\r
21 // this list of conditions and the following disclaimer.
\r
23 // * Redistribution's in binary form must reproduce the above copyright notice,
\r
24 // this list of conditions and the following disclaimer in the documentation
\r
25 // and/or other GpuMaterials provided with the distribution.
\r
27 // * The name of the copyright holders may not be used to endorse or promote products
\r
28 // derived from this software without specific prior written permission.
\r
30 // This software is provided by the copyright holders and contributors "as is" and
\r
31 // any express or implied warranties, including, but not limited to, the implied
\r
32 // warranties of merchantability and fitness for a particular purpose are disclaimed.
\r
33 // In no event shall the Intel Corporation or contributors be liable for any direct,
\r
34 // indirect, incidental, special, exemplary, or consequential damages
\r
35 // (including, but not limited to, procurement of substitute goods or services;
\r
36 // loss of use, data, or profits; or business interruption) however caused
\r
37 // and on any theory of liability, whether in contract, strict liability,
\r
38 // or tort (including negligence or otherwise) arising in any way out of
\r
39 // the use of this software, even if advised of the possibility of such damage.
\r
43 #ifndef __OPENCV_GPU_HPP__
\r
44 #define __OPENCV_GPU_HPP__
\r
47 #include "opencv2/core/core.hpp"
\r
48 #include "opencv2/imgproc/imgproc.hpp"
\r
49 #include "opencv2/objdetect/objdetect.hpp"
\r
50 #include "opencv2/gpu/devmem2d.hpp"
\r
51 #include "opencv2/features2d/features2d.hpp"
\r
57 //////////////////////////////// Initialization & Info ////////////////////////
\r
59 //! This is the only function that do not throw exceptions if the library is compiled without Cuda.
\r
60 CV_EXPORTS int getCudaEnabledDeviceCount();
\r
62 //! Functions below throw cv::Expception if the library is compiled without Cuda.
\r
64 CV_EXPORTS void setDevice(int device);
\r
65 CV_EXPORTS int getDevice();
\r
67 //! Explicitly destroys and cleans up all resources associated with the current device in the current process.
\r
68 //! Any subsequent API call to this device will reinitialize the device.
\r
69 CV_EXPORTS void resetDevice();
\r
73 FEATURE_SET_COMPUTE_10 = 10,
\r
74 FEATURE_SET_COMPUTE_11 = 11,
\r
75 FEATURE_SET_COMPUTE_12 = 12,
\r
76 FEATURE_SET_COMPUTE_13 = 13,
\r
77 FEATURE_SET_COMPUTE_20 = 20,
\r
78 FEATURE_SET_COMPUTE_21 = 21,
\r
79 GLOBAL_ATOMICS = FEATURE_SET_COMPUTE_11,
\r
80 NATIVE_DOUBLE = FEATURE_SET_COMPUTE_13
\r
83 // Gives information about what GPU archs this OpenCV GPU module was
\r
85 class CV_EXPORTS TargetArchs
\r
88 static bool builtWith(FeatureSet feature_set);
\r
89 static bool has(int major, int minor);
\r
90 static bool hasPtx(int major, int minor);
\r
91 static bool hasBin(int major, int minor);
\r
92 static bool hasEqualOrLessPtx(int major, int minor);
\r
93 static bool hasEqualOrGreater(int major, int minor);
\r
94 static bool hasEqualOrGreaterPtx(int major, int minor);
\r
95 static bool hasEqualOrGreaterBin(int major, int minor);
\r
100 // Gives information about the given GPU
\r
101 class CV_EXPORTS DeviceInfo
\r
104 // Creates DeviceInfo object for the current GPU
\r
105 DeviceInfo() : device_id_(getDevice()) { query(); }
\r
107 // Creates DeviceInfo object for the given GPU
\r
108 DeviceInfo(int device_id) : device_id_(device_id) { query(); }
\r
110 string name() const { return name_; }
\r
112 // Return compute capability versions
\r
113 int majorVersion() const { return majorVersion_; }
\r
114 int minorVersion() const { return minorVersion_; }
\r
116 int multiProcessorCount() const { return multi_processor_count_; }
\r
118 size_t freeMemory() const;
\r
119 size_t totalMemory() const;
\r
121 // Checks whether device supports the given feature
\r
122 bool supports(FeatureSet feature_set) const;
\r
124 // Checks whether the GPU module can be run on the given device
\r
125 bool isCompatible() const;
\r
127 int deviceID() const { return device_id_; }
\r
131 void queryMemory(size_t& free_memory, size_t& total_memory) const;
\r
136 int multi_processor_count_;
\r
141 //////////////////////////////// Error handling ////////////////////////
\r
143 CV_EXPORTS void error(const char *error_string, const char *file, const int line, const char *func);
\r
144 CV_EXPORTS void nppError( int err, const char *file, const int line, const char *func);
\r
146 //////////////////////////////// GpuMat ////////////////////////////////
\r
150 //! Smart pointer for GPU memory with reference counting. Its interface is mostly similar with cv::Mat.
\r
151 class CV_EXPORTS GpuMat
\r
154 //! default constructor
\r
156 //! constructs GpuMatrix of the specified size and type (_type is CV_8UC1, CV_64FC3, CV_32SC(12) etc.)
\r
157 GpuMat(int rows, int cols, int type);
\r
158 GpuMat(Size size, int type);
\r
159 //! constucts GpuMatrix and fills it with the specified value _s.
\r
160 GpuMat(int rows, int cols, int type, const Scalar& s);
\r
161 GpuMat(Size size, int type, const Scalar& s);
\r
162 //! copy constructor
\r
163 GpuMat(const GpuMat& m);
\r
165 //! constructor for GpuMatrix headers pointing to user-allocated data
\r
166 GpuMat(int rows, int cols, int type, void* data, size_t step = Mat::AUTO_STEP);
\r
167 GpuMat(Size size, int type, void* data, size_t step = Mat::AUTO_STEP);
\r
169 //! creates a matrix header for a part of the bigger matrix
\r
170 GpuMat(const GpuMat& m, const Range& rowRange, const Range& colRange);
\r
171 GpuMat(const GpuMat& m, const Rect& roi);
\r
173 //! builds GpuMat from Mat. Perfom blocking upload to device.
\r
174 explicit GpuMat (const Mat& m);
\r
176 //! destructor - calls release()
\r
179 //! assignment operators
\r
180 GpuMat& operator = (const GpuMat& m);
\r
181 //! assignment operator. Perfom blocking upload to device.
\r
182 GpuMat& operator = (const Mat& m);
\r
184 //! returns lightweight DevMem2D_ structure for passing to nvcc-compiled code.
\r
185 // Contains just image size, data ptr and step.
\r
186 template <class T> operator DevMem2D_<T>() const;
\r
187 template <class T> operator PtrStep_<T>() const;
\r
189 //! pefroms blocking upload data to GpuMat.
\r
190 void upload(const cv::Mat& m);
\r
193 void upload(const CudaMem& m, Stream& stream);
\r
195 //! downloads data from device to host memory. Blocking calls.
\r
196 operator Mat() const;
\r
197 void download(cv::Mat& m) const;
\r
200 void download(CudaMem& m, Stream& stream) const;
\r
202 //! returns a new GpuMatrix header for the specified row
\r
203 GpuMat row(int y) const;
\r
204 //! returns a new GpuMatrix header for the specified column
\r
205 GpuMat col(int x) const;
\r
206 //! ... for the specified row span
\r
207 GpuMat rowRange(int startrow, int endrow) const;
\r
208 GpuMat rowRange(const Range& r) const;
\r
209 //! ... for the specified column span
\r
210 GpuMat colRange(int startcol, int endcol) const;
\r
211 GpuMat colRange(const Range& r) const;
\r
213 //! returns deep copy of the GpuMatrix, i.e. the data is copied
\r
214 GpuMat clone() const;
\r
215 //! copies the GpuMatrix content to "m".
\r
216 // It calls m.create(this->size(), this->type()).
\r
217 void copyTo( GpuMat& m ) const;
\r
218 //! copies those GpuMatrix elements to "m" that are marked with non-zero mask elements.
\r
219 void copyTo( GpuMat& m, const GpuMat& mask ) const;
\r
220 //! converts GpuMatrix to another datatype with optional scalng. See cvConvertScale.
\r
221 void convertTo( GpuMat& m, int rtype, double alpha=1, double beta=0 ) const;
\r
223 void assignTo( GpuMat& m, int type=-1 ) const;
\r
225 //! sets every GpuMatrix element to s
\r
226 GpuMat& operator = (const Scalar& s);
\r
227 //! sets some of the GpuMatrix elements to s, according to the mask
\r
228 GpuMat& setTo(const Scalar& s, const GpuMat& mask = GpuMat());
\r
229 //! creates alternative GpuMatrix header for the same data, with different
\r
230 // number of channels and/or different number of rows. see cvReshape.
\r
231 GpuMat reshape(int cn, int rows = 0) const;
\r
233 //! allocates new GpuMatrix data unless the GpuMatrix already has specified size and type.
\r
234 // previous data is unreferenced if needed.
\r
235 void create(int rows, int cols, int type);
\r
236 void create(Size size, int type);
\r
237 //! decreases reference counter;
\r
238 // deallocate the data when reference counter reaches 0.
\r
241 //! swaps with other smart pointer
\r
242 void swap(GpuMat& mat);
\r
244 //! locates GpuMatrix header within a parent GpuMatrix. See below
\r
245 void locateROI( Size& wholeSize, Point& ofs ) const;
\r
246 //! moves/resizes the current GpuMatrix ROI inside the parent GpuMatrix.
\r
247 GpuMat& adjustROI( int dtop, int dbottom, int dleft, int dright );
\r
248 //! extracts a rectangular sub-GpuMatrix
\r
249 // (this is a generalized form of row, rowRange etc.)
\r
250 GpuMat operator()( Range rowRange, Range colRange ) const;
\r
251 GpuMat operator()( const Rect& roi ) const;
\r
253 //! returns true iff the GpuMatrix data is continuous
\r
254 // (i.e. when there are no gaps between successive rows).
\r
255 // similar to CV_IS_GpuMat_CONT(cvGpuMat->type)
\r
256 bool isContinuous() const;
\r
257 //! returns element size in bytes,
\r
258 // similar to CV_ELEM_SIZE(cvMat->type)
\r
259 size_t elemSize() const;
\r
260 //! returns the size of element channel in bytes.
\r
261 size_t elemSize1() const;
\r
262 //! returns element type, similar to CV_MAT_TYPE(cvMat->type)
\r
264 //! returns element type, similar to CV_MAT_DEPTH(cvMat->type)
\r
266 //! returns element type, similar to CV_MAT_CN(cvMat->type)
\r
267 int channels() const;
\r
268 //! returns step/elemSize1()
\r
269 size_t step1() const;
\r
270 //! returns GpuMatrix size:
\r
271 // width == number of columns, height == number of rows
\r
273 //! returns true if GpuMatrix data is NULL
\r
274 bool empty() const;
\r
276 //! returns pointer to y-th row
\r
277 uchar* ptr(int y = 0);
\r
278 const uchar* ptr(int y = 0) const;
\r
280 //! template version of the above method
\r
281 template<typename _Tp> _Tp* ptr(int y = 0);
\r
282 template<typename _Tp> const _Tp* ptr(int y = 0) const;
\r
284 //! matrix transposition
\r
287 /*! includes several bit-fields:
\r
288 - the magic signature
\r
291 - number of channels
\r
294 //! the number of rows and columns
\r
296 //! a distance between successive rows in bytes; includes the gap if any
\r
298 //! pointer to the data
\r
301 //! pointer to the reference counter;
\r
302 // when GpuMatrix points to user-allocated data, the pointer is NULL
\r
305 //! helper fields used in locateROI and adjustROI
\r
310 //#define TemplatedGpuMat // experimental now, deprecated to use
\r
311 #ifdef TemplatedGpuMat
\r
312 #include "GpuMat_BetaDeprecated.hpp"
\r
315 //! Creates continuous GPU matrix
\r
316 CV_EXPORTS void createContinuous(int rows, int cols, int type, GpuMat& m);
\r
318 //! Ensures that size of the given matrix is not less than (rows, cols) size
\r
319 //! and matrix type is match specified one too
\r
320 CV_EXPORTS void ensureSizeIsEnough(int rows, int cols, int type, GpuMat& m);
\r
322 //////////////////////////////// CudaMem ////////////////////////////////
\r
323 // CudaMem is limited cv::Mat with page locked memory allocation.
\r
324 // Page locked memory is only needed for async and faster coping to GPU.
\r
325 // It is convertable to cv::Mat header without reference counting
\r
326 // so you can use it with other opencv functions.
\r
328 class CV_EXPORTS CudaMem
\r
331 enum { ALLOC_PAGE_LOCKED = 1, ALLOC_ZEROCOPY = 2, ALLOC_WRITE_COMBINED = 4 };
\r
334 CudaMem(const CudaMem& m);
\r
336 CudaMem(int rows, int cols, int type, int _alloc_type = ALLOC_PAGE_LOCKED);
\r
337 CudaMem(Size size, int type, int alloc_type = ALLOC_PAGE_LOCKED);
\r
340 //! creates from cv::Mat with coping data
\r
341 explicit CudaMem(const Mat& m, int alloc_type = ALLOC_PAGE_LOCKED);
\r
345 CudaMem& operator = (const CudaMem& m);
\r
347 //! returns deep copy of the matrix, i.e. the data is copied
\r
348 CudaMem clone() const;
\r
350 //! allocates new matrix data unless the matrix already has specified size and type.
\r
351 void create(int rows, int cols, int type, int alloc_type = ALLOC_PAGE_LOCKED);
\r
352 void create(Size size, int type, int alloc_type = ALLOC_PAGE_LOCKED);
\r
354 //! decrements reference counter and released memory if needed.
\r
357 //! returns matrix header with disabled reference counting for CudaMem data.
\r
358 Mat createMatHeader() const;
\r
359 operator Mat() const;
\r
361 //! maps host memory into device address space and returns GpuMat header for it. Throws exception if not supported by hardware.
\r
362 GpuMat createGpuMatHeader() const;
\r
363 operator GpuMat() const;
\r
365 //returns if host memory can be mapperd to gpu address space;
\r
366 static bool canMapHostMemory();
\r
368 // Please see cv::Mat for descriptions
\r
369 bool isContinuous() const;
\r
370 size_t elemSize() const;
\r
371 size_t elemSize1() const;
\r
374 int channels() const;
\r
375 size_t step1() const;
\r
377 bool empty() const;
\r
380 // Please see cv::Mat for descriptions
\r
394 //////////////////////////////// CudaStream ////////////////////////////////
\r
395 // Encapculates Cuda Stream. Provides interface for async coping.
\r
396 // Passed to each function that supports async kernel execution.
\r
397 // Reference counting is enabled
\r
399 class CV_EXPORTS Stream
\r
405 Stream(const Stream&);
\r
406 Stream& operator=(const Stream&);
\r
408 bool queryIfComplete();
\r
409 void waitForCompletion();
\r
411 //! downloads asynchronously.
\r
412 // Warning! cv::Mat must point to page locked memory (i.e. to CudaMem data or to its subMat)
\r
413 void enqueueDownload(const GpuMat& src, CudaMem& dst);
\r
414 void enqueueDownload(const GpuMat& src, Mat& dst);
\r
416 //! uploads asynchronously.
\r
417 // Warning! cv::Mat must point to page locked memory (i.e. to CudaMem data or to its ROI)
\r
418 void enqueueUpload(const CudaMem& src, GpuMat& dst);
\r
419 void enqueueUpload(const Mat& src, GpuMat& dst);
\r
421 void enqueueCopy(const GpuMat& src, GpuMat& dst);
\r
423 void enqueueMemSet(GpuMat& src, Scalar val);
\r
424 void enqueueMemSet(GpuMat& src, Scalar val, const GpuMat& mask);
\r
426 // converts matrix type, ex from float to uchar depending on type
\r
427 void enqueueConvert(const GpuMat& src, GpuMat& dst, int type, double a = 1, double b = 0);
\r
429 static Stream& Null();
\r
431 operator bool() const;
\r
440 friend struct StreamAccessor;
\r
442 explicit Stream(Impl* impl);
\r
446 ////////////////////////////// Arithmetics ///////////////////////////////////
\r
448 //! transposes the matrix
\r
449 //! supports matrix with element size = 1, 4 and 8 bytes (CV_8UC1, CV_8UC4, CV_16UC2, CV_32FC1, etc)
\r
450 CV_EXPORTS void transpose(const GpuMat& src1, GpuMat& dst, Stream& stream = Stream::Null());
\r
452 //! reverses the order of the rows, columns or both in a matrix
\r
453 //! supports CV_8UC1, CV_8UC4 types
\r
454 CV_EXPORTS void flip(const GpuMat& a, GpuMat& b, int flipCode, Stream& stream = Stream::Null());
\r
456 //! transforms 8-bit unsigned integers using lookup table: dst(i)=lut(src(i))
\r
457 //! destination array will have the depth type as lut and the same channels number as source
\r
458 //! supports CV_8UC1, CV_8UC3 types
\r
459 CV_EXPORTS void LUT(const GpuMat& src, const Mat& lut, GpuMat& dst, Stream& stream = Stream::Null());
\r
461 //! makes multi-channel array out of several single-channel arrays
\r
462 CV_EXPORTS void merge(const GpuMat* src, size_t n, GpuMat& dst, Stream& stream = Stream::Null());
\r
464 //! makes multi-channel array out of several single-channel arrays
\r
465 CV_EXPORTS void merge(const vector<GpuMat>& src, GpuMat& dst, Stream& stream = Stream::Null());
\r
467 //! copies each plane of a multi-channel array to a dedicated array
\r
468 CV_EXPORTS void split(const GpuMat& src, GpuMat* dst, Stream& stream = Stream::Null());
\r
470 //! copies each plane of a multi-channel array to a dedicated array
\r
471 CV_EXPORTS void split(const GpuMat& src, vector<GpuMat>& dst, Stream& stream = Stream::Null());
\r
473 //! computes magnitude of complex (x(i).re, x(i).im) vector
\r
474 //! supports only CV_32FC2 type
\r
475 CV_EXPORTS void magnitude(const GpuMat& x, GpuMat& magnitude, Stream& stream = Stream::Null());
\r
477 //! computes squared magnitude of complex (x(i).re, x(i).im) vector
\r
478 //! supports only CV_32FC2 type
\r
479 CV_EXPORTS void magnitudeSqr(const GpuMat& x, GpuMat& magnitude, Stream& stream = Stream::Null());
\r
481 //! computes magnitude of each (x(i), y(i)) vector
\r
482 //! supports only floating-point source
\r
483 CV_EXPORTS void magnitude(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, Stream& stream = Stream::Null());
\r
485 //! computes squared magnitude of each (x(i), y(i)) vector
\r
486 //! supports only floating-point source
\r
487 CV_EXPORTS void magnitudeSqr(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, Stream& stream = Stream::Null());
\r
489 //! computes angle (angle(i)) of each (x(i), y(i)) vector
\r
490 //! supports only floating-point source
\r
491 CV_EXPORTS void phase(const GpuMat& x, const GpuMat& y, GpuMat& angle, bool angleInDegrees = false, Stream& stream = Stream::Null());
\r
493 //! converts Cartesian coordinates to polar
\r
494 //! supports only floating-point source
\r
495 CV_EXPORTS void cartToPolar(const GpuMat& x, const GpuMat& y, GpuMat& magnitude, GpuMat& angle, bool angleInDegrees = false, Stream& stream = Stream::Null());
\r
497 //! converts polar coordinates to Cartesian
\r
498 //! supports only floating-point source
\r
499 CV_EXPORTS void polarToCart(const GpuMat& magnitude, const GpuMat& angle, GpuMat& x, GpuMat& y, bool angleInDegrees = false, Stream& stream = Stream::Null());
\r
502 //////////////////////////// Per-element operations ////////////////////////////////////
\r
504 //! adds one matrix to another (c = a + b)
\r
505 //! supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32FC1 types
\r
506 CV_EXPORTS void add(const GpuMat& a, const GpuMat& b, GpuMat& c, Stream& stream = Stream::Null());
\r
507 //! adds scalar to a matrix (c = a + s)
\r
508 //! supports CV_32FC1 and CV_32FC2 type
\r
509 CV_EXPORTS void add(const GpuMat& a, const Scalar& sc, GpuMat& c, Stream& stream = Stream::Null());
\r
511 //! subtracts one matrix from another (c = a - b)
\r
512 //! supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32FC1 types
\r
513 CV_EXPORTS void subtract(const GpuMat& a, const GpuMat& b, GpuMat& c, Stream& stream = Stream::Null());
\r
514 //! subtracts scalar from a matrix (c = a - s)
\r
515 //! supports CV_32FC1 and CV_32FC2 type
\r
516 CV_EXPORTS void subtract(const GpuMat& a, const Scalar& sc, GpuMat& c, Stream& stream = Stream::Null());
\r
518 //! computes element-wise product of the two arrays (c = a * b)
\r
519 //! supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32FC1 types
\r
520 CV_EXPORTS void multiply(const GpuMat& a, const GpuMat& b, GpuMat& c, Stream& stream = Stream::Null());
\r
521 //! multiplies matrix to a scalar (c = a * s)
\r
522 //! supports CV_32FC1 type
\r
523 CV_EXPORTS void multiply(const GpuMat& a, const Scalar& sc, GpuMat& c, Stream& stream = Stream::Null());
\r
525 //! computes element-wise quotient of the two arrays (c = a / b)
\r
526 //! supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32FC1 types
\r
527 CV_EXPORTS void divide(const GpuMat& a, const GpuMat& b, GpuMat& c, Stream& stream = Stream::Null());
\r
528 //! computes element-wise quotient of matrix and scalar (c = a / s)
\r
529 //! supports CV_32FC1 type
\r
530 CV_EXPORTS void divide(const GpuMat& a, const Scalar& sc, GpuMat& c, Stream& stream = Stream::Null());
\r
532 //! computes exponent of each matrix element (b = e**a)
\r
533 //! supports only CV_32FC1 type
\r
534 CV_EXPORTS void exp(const GpuMat& a, GpuMat& b, Stream& stream = Stream::Null());
\r
536 //! computes natural logarithm of absolute value of each matrix element: b = log(abs(a))
\r
537 //! supports only CV_32FC1 type
\r
538 CV_EXPORTS void log(const GpuMat& a, GpuMat& b, Stream& stream = Stream::Null());
\r
540 //! computes element-wise absolute difference of two arrays (c = abs(a - b))
\r
541 //! supports CV_8UC1, CV_8UC4, CV_32SC1, CV_32FC1 types
\r
542 CV_EXPORTS void absdiff(const GpuMat& a, const GpuMat& b, GpuMat& c, Stream& stream = Stream::Null());
\r
543 //! computes element-wise absolute difference of array and scalar (c = abs(a - s))
\r
544 //! supports only CV_32FC1 type
\r
545 CV_EXPORTS void absdiff(const GpuMat& a, const Scalar& s, GpuMat& c, Stream& stream = Stream::Null());
\r
547 //! compares elements of two arrays (c = a <cmpop> b)
\r
548 //! supports CV_8UC4, CV_32FC1 types
\r
549 CV_EXPORTS void compare(const GpuMat& a, const GpuMat& b, GpuMat& c, int cmpop, Stream& stream = Stream::Null());
\r
551 //! performs per-elements bit-wise inversion
\r
552 CV_EXPORTS void bitwise_not(const GpuMat& src, GpuMat& dst, const GpuMat& mask=GpuMat(), Stream& stream = Stream::Null());
\r
554 //! calculates per-element bit-wise disjunction of two arrays
\r
555 CV_EXPORTS void bitwise_or(const GpuMat& src1, const GpuMat& src2, GpuMat& dst, const GpuMat& mask=GpuMat(), Stream& stream = Stream::Null());
\r
557 //! calculates per-element bit-wise conjunction of two arrays
\r
558 CV_EXPORTS void bitwise_and(const GpuMat& src1, const GpuMat& src2, GpuMat& dst, const GpuMat& mask=GpuMat(), Stream& stream = Stream::Null());
\r
560 //! calculates per-element bit-wise "exclusive or" operation
\r
561 CV_EXPORTS void bitwise_xor(const GpuMat& src1, const GpuMat& src2, GpuMat& dst, const GpuMat& mask=GpuMat(), Stream& stream = Stream::Null());
\r
563 //! computes per-element minimum of two arrays (dst = min(src1, src2))
\r
564 CV_EXPORTS void min(const GpuMat& src1, const GpuMat& src2, GpuMat& dst, Stream& stream = Stream::Null());
\r
566 //! computes per-element minimum of array and scalar (dst = min(src1, src2))
\r
567 CV_EXPORTS void min(const GpuMat& src1, double src2, GpuMat& dst, Stream& stream = Stream::Null());
\r
569 //! computes per-element maximum of two arrays (dst = max(src1, src2))
\r
570 CV_EXPORTS void max(const GpuMat& src1, const GpuMat& src2, GpuMat& dst, Stream& stream = Stream::Null());
\r
572 //! computes per-element maximum of array and scalar (dst = max(src1, src2))
\r
573 CV_EXPORTS void max(const GpuMat& src1, double src2, GpuMat& dst, Stream& stream = Stream::Null());
\r
576 ////////////////////////////// Image processing //////////////////////////////
\r
578 //! DST[x,y] = SRC[xmap[x,y],ymap[x,y]] with bilinear interpolation.
\r
579 //! supports CV_8UC1, CV_8UC3 source types and CV_32FC1 map type
\r
580 CV_EXPORTS void remap(const GpuMat& src, GpuMat& dst, const GpuMat& xmap, const GpuMat& ymap);
\r
582 //! Does mean shift filtering on GPU.
\r
583 CV_EXPORTS void meanShiftFiltering(const GpuMat& src, GpuMat& dst, int sp, int sr,
\r
584 TermCriteria criteria = TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 5, 1));
\r
586 //! Does mean shift procedure on GPU.
\r
587 CV_EXPORTS void meanShiftProc(const GpuMat& src, GpuMat& dstr, GpuMat& dstsp, int sp, int sr,
\r
588 TermCriteria criteria = TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 5, 1));
\r
590 //! Does mean shift segmentation with elimination of small regions.
\r
591 CV_EXPORTS void meanShiftSegmentation(const GpuMat& src, Mat& dst, int sp, int sr, int minsize,
\r
592 TermCriteria criteria = TermCriteria(TermCriteria::MAX_ITER + TermCriteria::EPS, 5, 1));
\r
594 //! Does coloring of disparity image: [0..ndisp) -> [0..240, 1, 1] in HSV.
\r
595 //! Supported types of input disparity: CV_8U, CV_16S.
\r
596 //! Output disparity has CV_8UC4 type in BGRA format (alpha = 255).
\r
597 CV_EXPORTS void drawColorDisp(const GpuMat& src_disp, GpuMat& dst_disp, int ndisp, Stream& stream = Stream::Null());
\r
599 //! Reprojects disparity image to 3D space.
\r
600 //! Supports CV_8U and CV_16S types of input disparity.
\r
601 //! The output is a 4-channel floating-point (CV_32FC4) matrix.
\r
602 //! Each element of this matrix will contain the 3D coordinates of the point (x,y,z,1), computed from the disparity map.
\r
603 //! Q is the 4x4 perspective transformation matrix that can be obtained with cvStereoRectify.
\r
604 CV_EXPORTS void reprojectImageTo3D(const GpuMat& disp, GpuMat& xyzw, const Mat& Q, Stream& stream = Stream::Null());
\r
606 //! converts image from one color space to another
\r
607 CV_EXPORTS void cvtColor(const GpuMat& src, GpuMat& dst, int code, int dcn = 0, Stream& stream = Stream::Null());
\r
609 //! applies fixed threshold to the image
\r
610 CV_EXPORTS double threshold(const GpuMat& src, GpuMat& dst, double thresh, double maxval, int type, Stream& stream = Stream::Null());
\r
612 //! resizes the image
\r
613 //! Supports INTER_NEAREST, INTER_LINEAR
\r
614 //! supports CV_8UC1, CV_8UC4 types
\r
615 CV_EXPORTS void resize(const GpuMat& src, GpuMat& dst, Size dsize, double fx=0, double fy=0, int interpolation = INTER_LINEAR, Stream& stream = Stream::Null());
\r
617 //! warps the image using affine transformation
\r
618 //! Supports INTER_NEAREST, INTER_LINEAR, INTER_CUBIC
\r
619 CV_EXPORTS void warpAffine(const GpuMat& src, GpuMat& dst, const Mat& M, Size dsize, int flags = INTER_LINEAR, Stream& stream = Stream::Null());
\r
621 //! warps the image using perspective transformation
\r
622 //! Supports INTER_NEAREST, INTER_LINEAR, INTER_CUBIC
\r
623 CV_EXPORTS void warpPerspective(const GpuMat& src, GpuMat& dst, const Mat& M, Size dsize, int flags = INTER_LINEAR, Stream& stream = Stream::Null());
\r
625 //! rotate 8bit single or four channel image
\r
626 //! Supports INTER_NEAREST, INTER_LINEAR, INTER_CUBIC
\r
627 //! supports CV_8UC1, CV_8UC4 types
\r
628 CV_EXPORTS void rotate(const GpuMat& src, GpuMat& dst, Size dsize, double angle, double xShift = 0, double yShift = 0, int interpolation = INTER_LINEAR, Stream& stream = Stream::Null());
\r
630 //! copies 2D array to a larger destination array and pads borders with user-specifiable constant
\r
631 //! supports CV_8UC1, CV_8UC4, CV_32SC1 and CV_32FC1 types
\r
632 CV_EXPORTS void copyMakeBorder(const GpuMat& src, GpuMat& dst, int top, int bottom, int left, int right, const Scalar& value = Scalar(), Stream& stream = Stream::Null());
\r
634 //! computes the integral image
\r
635 //! sum will have CV_32S type, but will contain unsigned int values
\r
636 //! supports only CV_8UC1 source type
\r
637 CV_EXPORTS void integral(const GpuMat& src, GpuMat& sum, Stream& stream = Stream::Null());
\r
639 //! buffered version
\r
640 CV_EXPORTS void integralBuffered(const GpuMat& src, GpuMat& sum, GpuMat& buffer, Stream& stream = Stream::Null());
\r
642 //! computes the integral image and integral for the squared image
\r
643 //! sum will have CV_32S type, sqsum - CV32F type
\r
644 //! supports only CV_8UC1 source type
\r
645 CV_EXPORTS void integral(const GpuMat& src, GpuMat& sum, GpuMat& sqsum, Stream& stream = Stream::Null());
\r
647 //! computes squared integral image
\r
648 //! result matrix will have 64F type, but will contain 64U values
\r
649 //! supports source images of 8UC1 type only
\r
650 CV_EXPORTS void sqrIntegral(const GpuMat& src, GpuMat& sqsum, Stream& stream = Stream::Null());
\r
652 //! computes vertical sum, supports only CV_32FC1 images
\r
653 CV_EXPORTS void columnSum(const GpuMat& src, GpuMat& sum);
\r
655 //! computes the standard deviation of integral images
\r
656 //! supports only CV_32SC1 source type and CV_32FC1 sqr type
\r
657 //! output will have CV_32FC1 type
\r
658 CV_EXPORTS void rectStdDev(const GpuMat& src, const GpuMat& sqr, GpuMat& dst, const Rect& rect, Stream& stream = Stream::Null());
\r
660 //! computes Harris cornerness criteria at each image pixel
\r
661 CV_EXPORTS void cornerHarris(const GpuMat& src, GpuMat& dst, int blockSize, int ksize, double k, int borderType=BORDER_REFLECT101);
\r
663 //! computes minimum eigen value of 2x2 derivative covariation matrix at each pixel - the cornerness criteria
\r
664 CV_EXPORTS void cornerMinEigenVal(const GpuMat& src, GpuMat& dst, int blockSize, int ksize, int borderType=BORDER_REFLECT101);
\r
666 //! performs per-element multiplication of two full (not packed) Fourier spectrums
\r
667 //! supports 32FC2 matrixes only (interleaved format)
\r
668 CV_EXPORTS void mulSpectrums(const GpuMat& a, const GpuMat& b, GpuMat& c, int flags, bool conjB=false);
\r
670 //! performs per-element multiplication of two full (not packed) Fourier spectrums
\r
671 //! supports 32FC2 matrixes only (interleaved format)
\r
672 CV_EXPORTS void mulAndScaleSpectrums(const GpuMat& a, const GpuMat& b, GpuMat& c, int flags,
\r
673 float scale, bool conjB=false);
\r
675 //! Performs a forward or inverse discrete Fourier transform (1D or 2D) of floating point matrix.
\r
676 //! Param dft_size is the size of DFT transform.
\r
678 //! If the source matrix is not continous, then additional copy will be done,
\r
679 //! so to avoid copying ensure the source matrix is continous one. If you want to use
\r
680 //! preallocated output ensure it is continuous too, otherwise it will be reallocated.
\r
682 //! Being implemented via CUFFT real-to-complex transform result contains only non-redundant values
\r
683 //! in CUFFT's format. Result as full complex matrix for such kind of transform cannot be retrieved.
\r
685 //! For complex-to-real transform it is assumed that the source matrix is packed in CUFFT's format.
\r
686 CV_EXPORTS void dft(const GpuMat& src, GpuMat& dst, Size dft_size, int flags=0);
\r
688 //! computes convolution (or cross-correlation) of two images using discrete Fourier transform
\r
689 //! supports source images of 32FC1 type only
\r
690 //! result matrix will have 32FC1 type
\r
691 CV_EXPORTS void convolve(const GpuMat& image, const GpuMat& templ, GpuMat& result,
\r
694 struct CV_EXPORTS ConvolveBuf;
\r
696 //! buffered version
\r
697 CV_EXPORTS void convolve(const GpuMat& image, const GpuMat& templ, GpuMat& result,
\r
698 bool ccorr, ConvolveBuf& buf);
\r
700 struct CV_EXPORTS ConvolveBuf
\r
703 ConvolveBuf(Size image_size, Size templ_size)
\r
704 { create(image_size, templ_size); }
\r
705 void create(Size image_size, Size templ_size);
\r
708 static Size estimateBlockSize(Size result_size, Size templ_size);
\r
709 friend void convolve(const GpuMat&, const GpuMat&, GpuMat&, bool, ConvolveBuf&);
\r
716 GpuMat image_spect, templ_spect, result_spect;
\r
717 GpuMat image_block, templ_block, result_data;
\r
720 //! computes the proximity map for the raster template and the image where the template is searched for
\r
721 CV_EXPORTS void matchTemplate(const GpuMat& image, const GpuMat& templ, GpuMat& result, int method);
\r
723 //! downsamples image
\r
724 CV_EXPORTS void downsample(const GpuMat& src, GpuMat& dst, int k=2);
\r
726 //! performs linear blending of two images
\r
727 //! to avoid accuracy errors sum of weigths shouldn't be very close to zero
\r
728 CV_EXPORTS void blendLinear(const GpuMat& img1, const GpuMat& img2, const GpuMat& weights1, const GpuMat& weights2,
\r
729 GpuMat& result, Stream& stream = Stream::Null());
\r
731 ////////////////////////////// Matrix reductions //////////////////////////////
\r
733 //! computes mean value and standard deviation of all or selected array elements
\r
734 //! supports only CV_8UC1 type
\r
735 CV_EXPORTS void meanStdDev(const GpuMat& mtx, Scalar& mean, Scalar& stddev);
\r
737 //! computes norm of array
\r
738 //! supports NORM_INF, NORM_L1, NORM_L2
\r
739 //! supports all matrices except 64F
\r
740 CV_EXPORTS double norm(const GpuMat& src1, int normType=NORM_L2);
\r
742 //! computes norm of array
\r
743 //! supports NORM_INF, NORM_L1, NORM_L2
\r
744 //! supports all matrices except 64F
\r
745 CV_EXPORTS double norm(const GpuMat& src1, int normType, GpuMat& buf);
\r
747 //! computes norm of the difference between two arrays
\r
748 //! supports NORM_INF, NORM_L1, NORM_L2
\r
749 //! supports only CV_8UC1 type
\r
750 CV_EXPORTS double norm(const GpuMat& src1, const GpuMat& src2, int normType=NORM_L2);
\r
752 //! computes sum of array elements
\r
753 //! supports only single channel images
\r
754 CV_EXPORTS Scalar sum(const GpuMat& src);
\r
756 //! computes sum of array elements
\r
757 //! supports only single channel images
\r
758 CV_EXPORTS Scalar sum(const GpuMat& src, GpuMat& buf);
\r
760 //! computes sum of array elements absolute values
\r
761 //! supports only single channel images
\r
762 CV_EXPORTS Scalar absSum(const GpuMat& src);
\r
764 //! computes sum of array elements absolute values
\r
765 //! supports only single channel images
\r
766 CV_EXPORTS Scalar absSum(const GpuMat& src, GpuMat& buf);
\r
768 //! computes squared sum of array elements
\r
769 //! supports only single channel images
\r
770 CV_EXPORTS Scalar sqrSum(const GpuMat& src);
\r
772 //! computes squared sum of array elements
\r
773 //! supports only single channel images
\r
774 CV_EXPORTS Scalar sqrSum(const GpuMat& src, GpuMat& buf);
\r
776 //! finds global minimum and maximum array elements and returns their values
\r
777 CV_EXPORTS void minMax(const GpuMat& src, double* minVal, double* maxVal=0, const GpuMat& mask=GpuMat());
\r
779 //! finds global minimum and maximum array elements and returns their values
\r
780 CV_EXPORTS void minMax(const GpuMat& src, double* minVal, double* maxVal, const GpuMat& mask, GpuMat& buf);
\r
782 //! finds global minimum and maximum array elements and returns their values with locations
\r
783 CV_EXPORTS void minMaxLoc(const GpuMat& src, double* minVal, double* maxVal=0, Point* minLoc=0, Point* maxLoc=0,
\r
784 const GpuMat& mask=GpuMat());
\r
786 //! finds global minimum and maximum array elements and returns their values with locations
\r
787 CV_EXPORTS void minMaxLoc(const GpuMat& src, double* minVal, double* maxVal, Point* minLoc, Point* maxLoc,
\r
788 const GpuMat& mask, GpuMat& valbuf, GpuMat& locbuf);
\r
790 //! counts non-zero array elements
\r
791 CV_EXPORTS int countNonZero(const GpuMat& src);
\r
793 //! counts non-zero array elements
\r
794 CV_EXPORTS int countNonZero(const GpuMat& src, GpuMat& buf);
\r
797 ///////////////////////////// Calibration 3D //////////////////////////////////
\r
799 CV_EXPORTS void transformPoints(const GpuMat& src, const Mat& rvec, const Mat& tvec,
\r
800 GpuMat& dst, Stream& stream = Stream::Null());
\r
802 CV_EXPORTS void projectPoints(const GpuMat& src, const Mat& rvec, const Mat& tvec,
\r
803 const Mat& camera_mat, const Mat& dist_coef, GpuMat& dst,
\r
804 Stream& stream = Stream::Null());
\r
806 CV_EXPORTS void solvePnPRansac(const Mat& object, const Mat& image, const Mat& camera_mat,
\r
807 const Mat& dist_coef, Mat& rvec, Mat& tvec, bool use_extrinsic_guess=false,
\r
808 int num_iters=100, float max_dist=8.0, int min_inlier_count=100,
\r
809 vector<int>* inliers=NULL);
\r
811 //////////////////////////////// Filter Engine ////////////////////////////////
\r
814 The Base Class for 1D or Row-wise Filters
\r
816 This is the base class for linear or non-linear filters that process 1D data.
\r
817 In particular, such filters are used for the "horizontal" filtering parts in separable filters.
\r
819 class CV_EXPORTS BaseRowFilter_GPU
\r
822 BaseRowFilter_GPU(int ksize_, int anchor_) : ksize(ksize_), anchor(anchor_) {}
\r
823 virtual ~BaseRowFilter_GPU() {}
\r
824 virtual void operator()(const GpuMat& src, GpuMat& dst, Stream& stream = Stream::Null()) = 0;
\r
829 The Base Class for Column-wise Filters
\r
831 This is the base class for linear or non-linear filters that process columns of 2D arrays.
\r
832 Such filters are used for the "vertical" filtering parts in separable filters.
\r
834 class CV_EXPORTS BaseColumnFilter_GPU
\r
837 BaseColumnFilter_GPU(int ksize_, int anchor_) : ksize(ksize_), anchor(anchor_) {}
\r
838 virtual ~BaseColumnFilter_GPU() {}
\r
839 virtual void operator()(const GpuMat& src, GpuMat& dst, Stream& stream = Stream::Null()) = 0;
\r
844 The Base Class for Non-Separable 2D Filters.
\r
846 This is the base class for linear or non-linear 2D filters.
\r
848 class CV_EXPORTS BaseFilter_GPU
\r
851 BaseFilter_GPU(const Size& ksize_, const Point& anchor_) : ksize(ksize_), anchor(anchor_) {}
\r
852 virtual ~BaseFilter_GPU() {}
\r
853 virtual void operator()(const GpuMat& src, GpuMat& dst, Stream& stream = Stream::Null()) = 0;
\r
859 The Base Class for Filter Engine.
\r
861 The class can be used to apply an arbitrary filtering operation to an image.
\r
862 It contains all the necessary intermediate buffers.
\r
864 class CV_EXPORTS FilterEngine_GPU
\r
867 virtual ~FilterEngine_GPU() {}
\r
869 virtual void apply(const GpuMat& src, GpuMat& dst, Rect roi = Rect(0,0,-1,-1), Stream& stream = Stream::Null()) = 0;
\r
872 //! returns the non-separable filter engine with the specified filter
\r
873 CV_EXPORTS Ptr<FilterEngine_GPU> createFilter2D_GPU(const Ptr<BaseFilter_GPU>& filter2D, int srcType, int dstType);
\r
875 //! returns the separable filter engine with the specified filters
\r
876 CV_EXPORTS Ptr<FilterEngine_GPU> createSeparableFilter_GPU(const Ptr<BaseRowFilter_GPU>& rowFilter,
\r
877 const Ptr<BaseColumnFilter_GPU>& columnFilter, int srcType, int bufType, int dstType);
\r
879 //! returns horizontal 1D box filter
\r
880 //! supports only CV_8UC1 source type and CV_32FC1 sum type
\r
881 CV_EXPORTS Ptr<BaseRowFilter_GPU> getRowSumFilter_GPU(int srcType, int sumType, int ksize, int anchor = -1);
\r
883 //! returns vertical 1D box filter
\r
884 //! supports only CV_8UC1 sum type and CV_32FC1 dst type
\r
885 CV_EXPORTS Ptr<BaseColumnFilter_GPU> getColumnSumFilter_GPU(int sumType, int dstType, int ksize, int anchor = -1);
\r
887 //! returns 2D box filter
\r
888 //! supports CV_8UC1 and CV_8UC4 source type, dst type must be the same as source type
\r
889 CV_EXPORTS Ptr<BaseFilter_GPU> getBoxFilter_GPU(int srcType, int dstType, const Size& ksize, Point anchor = Point(-1, -1));
\r
891 //! returns box filter engine
\r
892 CV_EXPORTS Ptr<FilterEngine_GPU> createBoxFilter_GPU(int srcType, int dstType, const Size& ksize,
\r
893 const Point& anchor = Point(-1,-1));
\r
895 //! returns 2D morphological filter
\r
896 //! only MORPH_ERODE and MORPH_DILATE are supported
\r
897 //! supports CV_8UC1 and CV_8UC4 types
\r
898 //! kernel must have CV_8UC1 type, one rows and cols == ksize.width * ksize.height
\r
899 CV_EXPORTS Ptr<BaseFilter_GPU> getMorphologyFilter_GPU(int op, int type, const Mat& kernel, const Size& ksize,
\r
900 Point anchor=Point(-1,-1));
\r
902 //! returns morphological filter engine. Only MORPH_ERODE and MORPH_DILATE are supported.
\r
903 CV_EXPORTS Ptr<FilterEngine_GPU> createMorphologyFilter_GPU(int op, int type, const Mat& kernel,
\r
904 const Point& anchor = Point(-1,-1), int iterations = 1);
\r
906 //! returns 2D filter with the specified kernel
\r
907 //! supports CV_8UC1 and CV_8UC4 types
\r
908 CV_EXPORTS Ptr<BaseFilter_GPU> getLinearFilter_GPU(int srcType, int dstType, const Mat& kernel, const Size& ksize,
\r
909 Point anchor = Point(-1, -1));
\r
911 //! returns the non-separable linear filter engine
\r
912 CV_EXPORTS Ptr<FilterEngine_GPU> createLinearFilter_GPU(int srcType, int dstType, const Mat& kernel,
\r
913 const Point& anchor = Point(-1,-1));
\r
915 //! returns the primitive row filter with the specified kernel.
\r
916 //! supports only CV_8UC1, CV_8UC4, CV_16SC1, CV_16SC2, CV_32SC1, CV_32FC1 source type.
\r
917 //! there are two version of algorithm: NPP and OpenCV.
\r
918 //! NPP calls when srcType == CV_8UC1 or srcType == CV_8UC4 and bufType == srcType,
\r
919 //! otherwise calls OpenCV version.
\r
920 //! NPP supports only BORDER_CONSTANT border type.
\r
921 //! OpenCV version supports only CV_32F as buffer depth and
\r
922 //! BORDER_REFLECT101, BORDER_REPLICATE and BORDER_CONSTANT border types.
\r
923 CV_EXPORTS Ptr<BaseRowFilter_GPU> getLinearRowFilter_GPU(int srcType, int bufType, const Mat& rowKernel,
\r
924 int anchor = -1, int borderType = BORDER_CONSTANT);
\r
926 //! returns the primitive column filter with the specified kernel.
\r
927 //! supports only CV_8UC1, CV_8UC4, CV_16SC1, CV_16SC2, CV_32SC1, CV_32FC1 dst type.
\r
928 //! there are two version of algorithm: NPP and OpenCV.
\r
929 //! NPP calls when dstType == CV_8UC1 or dstType == CV_8UC4 and bufType == dstType,
\r
930 //! otherwise calls OpenCV version.
\r
931 //! NPP supports only BORDER_CONSTANT border type.
\r
932 //! OpenCV version supports only CV_32F as buffer depth and
\r
933 //! BORDER_REFLECT101, BORDER_REPLICATE and BORDER_CONSTANT border types.
\r
934 CV_EXPORTS Ptr<BaseColumnFilter_GPU> getLinearColumnFilter_GPU(int bufType, int dstType, const Mat& columnKernel,
\r
935 int anchor = -1, int borderType = BORDER_CONSTANT);
\r
937 //! returns the separable linear filter engine
\r
938 CV_EXPORTS Ptr<FilterEngine_GPU> createSeparableLinearFilter_GPU(int srcType, int dstType, const Mat& rowKernel,
\r
939 const Mat& columnKernel, const Point& anchor = Point(-1,-1), int rowBorderType = BORDER_DEFAULT,
\r
940 int columnBorderType = -1);
\r
942 //! returns filter engine for the generalized Sobel operator
\r
943 CV_EXPORTS Ptr<FilterEngine_GPU> createDerivFilter_GPU(int srcType, int dstType, int dx, int dy, int ksize,
\r
944 int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1);
\r
946 //! returns the Gaussian filter engine
\r
947 CV_EXPORTS Ptr<FilterEngine_GPU> createGaussianFilter_GPU(int type, Size ksize, double sigma1, double sigma2 = 0,
\r
948 int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1);
\r
950 //! returns maximum filter
\r
951 CV_EXPORTS Ptr<BaseFilter_GPU> getMaxFilter_GPU(int srcType, int dstType, const Size& ksize, Point anchor = Point(-1,-1));
\r
953 //! returns minimum filter
\r
954 CV_EXPORTS Ptr<BaseFilter_GPU> getMinFilter_GPU(int srcType, int dstType, const Size& ksize, Point anchor = Point(-1,-1));
\r
956 //! smooths the image using the normalized box filter
\r
957 //! supports CV_8UC1, CV_8UC4 types
\r
958 CV_EXPORTS void boxFilter(const GpuMat& src, GpuMat& dst, int ddepth, Size ksize, Point anchor = Point(-1,-1), Stream& stream = Stream::Null());
\r
960 //! a synonym for normalized box filter
\r
961 static inline void blur(const GpuMat& src, GpuMat& dst, Size ksize, Point anchor = Point(-1,-1), Stream& stream = Stream::Null()) { boxFilter(src, dst, -1, ksize, anchor, stream); }
\r
963 //! erodes the image (applies the local minimum operator)
\r
964 CV_EXPORTS void erode( const GpuMat& src, GpuMat& dst, const Mat& kernel, Point anchor = Point(-1, -1), int iterations = 1, Stream& stream = Stream::Null());
\r
966 //! dilates the image (applies the local maximum operator)
\r
967 CV_EXPORTS void dilate( const GpuMat& src, GpuMat& dst, const Mat& kernel, Point anchor = Point(-1, -1), int iterations = 1, Stream& stream = Stream::Null());
\r
969 //! applies an advanced morphological operation to the image
\r
970 CV_EXPORTS void morphologyEx( const GpuMat& src, GpuMat& dst, int op, const Mat& kernel, Point anchor = Point(-1, -1), int iterations = 1, Stream& stream = Stream::Null());
\r
972 //! applies non-separable 2D linear filter to the image
\r
973 CV_EXPORTS void filter2D(const GpuMat& src, GpuMat& dst, int ddepth, const Mat& kernel, Point anchor=Point(-1,-1), Stream& stream = Stream::Null());
\r
975 //! applies separable 2D linear filter to the image
\r
976 CV_EXPORTS void sepFilter2D(const GpuMat& src, GpuMat& dst, int ddepth, const Mat& kernelX, const Mat& kernelY,
\r
977 Point anchor = Point(-1,-1), int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1, Stream& stream = Stream::Null());
\r
979 //! applies generalized Sobel operator to the image
\r
980 CV_EXPORTS void Sobel(const GpuMat& src, GpuMat& dst, int ddepth, int dx, int dy, int ksize = 3, double scale = 1,
\r
981 int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1, Stream& stream = Stream::Null());
\r
983 //! applies the vertical or horizontal Scharr operator to the image
\r
984 CV_EXPORTS void Scharr(const GpuMat& src, GpuMat& dst, int ddepth, int dx, int dy, double scale = 1,
\r
985 int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1, Stream& stream = Stream::Null());
\r
987 //! smooths the image using Gaussian filter.
\r
988 CV_EXPORTS void GaussianBlur(const GpuMat& src, GpuMat& dst, Size ksize, double sigma1, double sigma2 = 0,
\r
989 int rowBorderType = BORDER_DEFAULT, int columnBorderType = -1, Stream& stream = Stream::Null());
\r
991 //! applies Laplacian operator to the image
\r
992 //! supports only ksize = 1 and ksize = 3
\r
993 CV_EXPORTS void Laplacian(const GpuMat& src, GpuMat& dst, int ddepth, int ksize = 1, double scale = 1, Stream& stream = Stream::Null());
\r
995 //////////////////////////////// Image Labeling ////////////////////////////////
\r
997 //!performs labeling via graph cuts
\r
998 CV_EXPORTS void graphcut(GpuMat& terminals, GpuMat& leftTransp, GpuMat& rightTransp, GpuMat& top, GpuMat& bottom, GpuMat& labels, GpuMat& buf, Stream& stream = Stream::Null());
\r
1000 ////////////////////////////////// Histograms //////////////////////////////////
\r
1002 //! Compute levels with even distribution. levels will have 1 row and nLevels cols and CV_32SC1 type.
\r
1003 CV_EXPORTS void evenLevels(GpuMat& levels, int nLevels, int lowerLevel, int upperLevel);
\r
1004 //! Calculates histogram with evenly distributed bins for signle channel source.
\r
1005 //! Supports CV_8UC1, CV_16UC1 and CV_16SC1 source types.
\r
1006 //! Output hist will have one row and histSize cols and CV_32SC1 type.
\r
1007 CV_EXPORTS void histEven(const GpuMat& src, GpuMat& hist, int histSize, int lowerLevel, int upperLevel, Stream& stream = Stream::Null());
\r
1008 //! Calculates histogram with evenly distributed bins for four-channel source.
\r
1009 //! All channels of source are processed separately.
\r
1010 //! Supports CV_8UC4, CV_16UC4 and CV_16SC4 source types.
\r
1011 //! Output hist[i] will have one row and histSize[i] cols and CV_32SC1 type.
\r
1012 CV_EXPORTS void histEven(const GpuMat& src, GpuMat hist[4], int histSize[4], int lowerLevel[4], int upperLevel[4], Stream& stream = Stream::Null());
\r
1013 //! Calculates histogram with bins determined by levels array.
\r
1014 //! levels must have one row and CV_32SC1 type if source has integer type or CV_32FC1 otherwise.
\r
1015 //! Supports CV_8UC1, CV_16UC1, CV_16SC1 and CV_32FC1 source types.
\r
1016 //! Output hist will have one row and (levels.cols-1) cols and CV_32SC1 type.
\r
1017 CV_EXPORTS void histRange(const GpuMat& src, GpuMat& hist, const GpuMat& levels, Stream& stream = Stream::Null());
\r
1018 //! Calculates histogram with bins determined by levels array.
\r
1019 //! All levels must have one row and CV_32SC1 type if source has integer type or CV_32FC1 otherwise.
\r
1020 //! All channels of source are processed separately.
\r
1021 //! Supports CV_8UC4, CV_16UC4, CV_16SC4 and CV_32FC4 source types.
\r
1022 //! Output hist[i] will have one row and (levels[i].cols-1) cols and CV_32SC1 type.
\r
1023 CV_EXPORTS void histRange(const GpuMat& src, GpuMat hist[4], const GpuMat levels[4], Stream& stream = Stream::Null());
\r
1025 //////////////////////////////// StereoBM_GPU ////////////////////////////////
\r
1027 class CV_EXPORTS StereoBM_GPU
\r
1030 enum { BASIC_PRESET = 0, PREFILTER_XSOBEL = 1 };
\r
1032 enum { DEFAULT_NDISP = 64, DEFAULT_WINSZ = 19 };
\r
1034 //! the default constructor
\r
1036 //! the full constructor taking the camera-specific preset, number of disparities and the SAD window size. ndisparities must be multiple of 8.
\r
1037 StereoBM_GPU(int preset, int ndisparities = DEFAULT_NDISP, int winSize = DEFAULT_WINSZ);
\r
1039 //! the stereo correspondence operator. Finds the disparity for the specified rectified stereo pair
\r
1040 //! Output disparity has CV_8U type.
\r
1041 void operator() ( const GpuMat& left, const GpuMat& right, GpuMat& disparity, Stream& stream = Stream::Null());
\r
1043 //! Some heuristics that tries to estmate
\r
1044 // if current GPU will be faster than CPU in this algorithm.
\r
1045 // It queries current active device.
\r
1046 static bool checkIfGpuCallReasonable();
\r
1052 // If avergeTexThreshold == 0 => post procesing is disabled
\r
1053 // If avergeTexThreshold != 0 then disparity is set 0 in each point (x,y) where for left image
\r
1054 // SumOfHorizontalGradiensInWindow(x, y, winSize) < (winSize * winSize) * avergeTexThreshold
\r
1055 // i.e. input left image is low textured.
\r
1056 float avergeTexThreshold;
\r
1058 GpuMat minSSD, leBuf, riBuf;
\r
1061 ////////////////////////// StereoBeliefPropagation ///////////////////////////
\r
1062 // "Efficient Belief Propagation for Early Vision"
\r
1065 class CV_EXPORTS StereoBeliefPropagation
\r
1068 enum { DEFAULT_NDISP = 64 };
\r
1069 enum { DEFAULT_ITERS = 5 };
\r
1070 enum { DEFAULT_LEVELS = 5 };
\r
1072 static void estimateRecommendedParams(int width, int height, int& ndisp, int& iters, int& levels);
\r
1074 //! the default constructor
\r
1075 explicit StereoBeliefPropagation(int ndisp = DEFAULT_NDISP,
\r
1076 int iters = DEFAULT_ITERS,
\r
1077 int levels = DEFAULT_LEVELS,
\r
1078 int msg_type = CV_32F);
\r
1080 //! the full constructor taking the number of disparities, number of BP iterations on each level,
\r
1081 //! number of levels, truncation of data cost, data weight,
\r
1082 //! truncation of discontinuity cost and discontinuity single jump
\r
1083 //! DataTerm = data_weight * min(fabs(I2-I1), max_data_term)
\r
1084 //! DiscTerm = min(disc_single_jump * fabs(f1-f2), max_disc_term)
\r
1085 //! please see paper for more details
\r
1086 StereoBeliefPropagation(int ndisp, int iters, int levels,
\r
1087 float max_data_term, float data_weight,
\r
1088 float max_disc_term, float disc_single_jump,
\r
1089 int msg_type = CV_32F);
\r
1091 //! the stereo correspondence operator. Finds the disparity for the specified rectified stereo pair,
\r
1092 //! if disparity is empty output type will be CV_16S else output type will be disparity.type().
\r
1093 void operator()(const GpuMat& left, const GpuMat& right, GpuMat& disparity, Stream& stream = Stream::Null());
\r
1096 //! version for user specified data term
\r
1097 void operator()(const GpuMat& data, GpuMat& disparity, Stream& stream = Stream::Null());
\r
1104 float max_data_term;
\r
1105 float data_weight;
\r
1106 float max_disc_term;
\r
1107 float disc_single_jump;
\r
1111 GpuMat u, d, l, r, u2, d2, l2, r2;
\r
1112 std::vector<GpuMat> datas;
\r
1116 /////////////////////////// StereoConstantSpaceBP ///////////////////////////
\r
1117 // "A Constant-Space Belief Propagation Algorithm for Stereo Matching"
\r
1118 // Qingxiong Yang, Liang Wang, Narendra Ahuja
\r
1119 // http://vision.ai.uiuc.edu/~qyang6/
\r
1121 class CV_EXPORTS StereoConstantSpaceBP
\r
1124 enum { DEFAULT_NDISP = 128 };
\r
1125 enum { DEFAULT_ITERS = 8 };
\r
1126 enum { DEFAULT_LEVELS = 4 };
\r
1127 enum { DEFAULT_NR_PLANE = 4 };
\r
1129 static void estimateRecommendedParams(int width, int height, int& ndisp, int& iters, int& levels, int& nr_plane);
\r
1131 //! the default constructor
\r
1132 explicit StereoConstantSpaceBP(int ndisp = DEFAULT_NDISP,
\r
1133 int iters = DEFAULT_ITERS,
\r
1134 int levels = DEFAULT_LEVELS,
\r
1135 int nr_plane = DEFAULT_NR_PLANE,
\r
1136 int msg_type = CV_32F);
\r
1138 //! the full constructor taking the number of disparities, number of BP iterations on each level,
\r
1139 //! number of levels, number of active disparity on the first level, truncation of data cost, data weight,
\r
1140 //! truncation of discontinuity cost, discontinuity single jump and minimum disparity threshold
\r
1141 StereoConstantSpaceBP(int ndisp, int iters, int levels, int nr_plane,
\r
1142 float max_data_term, float data_weight, float max_disc_term, float disc_single_jump,
\r
1143 int min_disp_th = 0,
\r
1144 int msg_type = CV_32F);
\r
1146 //! the stereo correspondence operator. Finds the disparity for the specified rectified stereo pair,
\r
1147 //! if disparity is empty output type will be CV_16S else output type will be disparity.type().
\r
1148 void operator()(const GpuMat& left, const GpuMat& right, GpuMat& disparity, Stream& stream = Stream::Null());
\r
1157 float max_data_term;
\r
1158 float data_weight;
\r
1159 float max_disc_term;
\r
1160 float disc_single_jump;
\r
1166 bool use_local_init_data_cost;
\r
1168 GpuMat u[2], d[2], l[2], r[2];
\r
1169 GpuMat disp_selected_pyr[2];
\r
1172 GpuMat data_cost_selected;
\r
1179 /////////////////////////// DisparityBilateralFilter ///////////////////////////
\r
1180 // Disparity map refinement using joint bilateral filtering given a single color image.
\r
1181 // Qingxiong Yang, Liang Wang, Narendra Ahuja
\r
1182 // http://vision.ai.uiuc.edu/~qyang6/
\r
1184 class CV_EXPORTS DisparityBilateralFilter
\r
1187 enum { DEFAULT_NDISP = 64 };
\r
1188 enum { DEFAULT_RADIUS = 3 };
\r
1189 enum { DEFAULT_ITERS = 1 };
\r
1191 //! the default constructor
\r
1192 explicit DisparityBilateralFilter(int ndisp = DEFAULT_NDISP, int radius = DEFAULT_RADIUS, int iters = DEFAULT_ITERS);
\r
1194 //! the full constructor taking the number of disparities, filter radius,
\r
1195 //! number of iterations, truncation of data continuity, truncation of disparity continuity
\r
1196 //! and filter range sigma
\r
1197 DisparityBilateralFilter(int ndisp, int radius, int iters, float edge_threshold, float max_disc_threshold, float sigma_range);
\r
1199 //! the disparity map refinement operator. Refine disparity map using joint bilateral filtering given a single color image.
\r
1200 //! disparity must have CV_8U or CV_16S type, image must have CV_8UC1 or CV_8UC3 type.
\r
1201 void operator()(const GpuMat& disparity, const GpuMat& image, GpuMat& dst, Stream& stream = Stream::Null());
\r
1208 float edge_threshold;
\r
1209 float max_disc_threshold;
\r
1210 float sigma_range;
\r
1212 GpuMat table_color;
\r
1213 GpuMat table_space;
\r
1217 //////////////// HOG (Histogram-of-Oriented-Gradients) Descriptor and Object Detector //////////////
\r
1219 struct CV_EXPORTS HOGDescriptor
\r
1221 enum { DEFAULT_WIN_SIGMA = -1 };
\r
1222 enum { DEFAULT_NLEVELS = 64 };
\r
1223 enum { DESCR_FORMAT_ROW_BY_ROW, DESCR_FORMAT_COL_BY_COL };
\r
1225 HOGDescriptor(Size win_size=Size(64, 128), Size block_size=Size(16, 16),
\r
1226 Size block_stride=Size(8, 8), Size cell_size=Size(8, 8),
\r
1227 int nbins=9, double win_sigma=DEFAULT_WIN_SIGMA,
\r
1228 double threshold_L2hys=0.2, bool gamma_correction=true,
\r
1229 int nlevels=DEFAULT_NLEVELS);
\r
1231 size_t getDescriptorSize() const;
\r
1232 size_t getBlockHistogramSize() const;
\r
1234 void setSVMDetector(const vector<float>& detector);
\r
1236 static vector<float> getDefaultPeopleDetector();
\r
1237 static vector<float> getPeopleDetector48x96();
\r
1238 static vector<float> getPeopleDetector64x128();
\r
1240 void detect(const GpuMat& img, vector<Point>& found_locations,
\r
1241 double hit_threshold=0, Size win_stride=Size(),
\r
1242 Size padding=Size());
\r
1244 void detectMultiScale(const GpuMat& img, vector<Rect>& found_locations,
\r
1245 double hit_threshold=0, Size win_stride=Size(),
\r
1246 Size padding=Size(), double scale0=1.05,
\r
1247 int group_threshold=2);
\r
1249 void getDescriptors(const GpuMat& img, Size win_stride,
\r
1250 GpuMat& descriptors,
\r
1251 int descr_format=DESCR_FORMAT_COL_BY_COL);
\r
1255 Size block_stride;
\r
1259 double threshold_L2hys;
\r
1260 bool gamma_correction;
\r
1264 void computeBlockHistograms(const GpuMat& img);
\r
1265 void computeGradient(const GpuMat& img, GpuMat& grad, GpuMat& qangle);
\r
1267 double getWinSigma() const;
\r
1268 bool checkDetectorSize() const;
\r
1270 static int numPartsWithin(int size, int part_size, int stride);
\r
1271 static Size numPartsWithin(Size size, Size part_size, Size stride);
\r
1273 // Coefficients of the separating plane
\r
1277 // Results of the last classification step
\r
1278 GpuMat labels, labels_buf;
\r
1281 // Results of the last histogram evaluation step
\r
1282 GpuMat block_hists, block_hists_buf;
\r
1284 // Gradients conputation results
\r
1285 GpuMat grad, qangle, grad_buf, qangle_buf;
\r
1287 // returns subbuffer with required size, reallocates buffer if nessesary.
\r
1288 static GpuMat getBuffer(const Size& sz, int type, GpuMat& buf);
\r
1289 static GpuMat getBuffer(int rows, int cols, int type, GpuMat& buf);
\r
1291 std::vector<GpuMat> image_scales;
\r
1295 ////////////////////////////////// BruteForceMatcher //////////////////////////////////
\r
1297 class CV_EXPORTS BruteForceMatcher_GPU_base
\r
1300 enum DistType {L1Dist = 0, L2Dist, HammingDist};
\r
1302 explicit BruteForceMatcher_GPU_base(DistType distType = L2Dist);
\r
1304 // Add descriptors to train descriptor collection.
\r
1305 void add(const std::vector<GpuMat>& descCollection);
\r
1307 // Get train descriptors collection.
\r
1308 const std::vector<GpuMat>& getTrainDescriptors() const;
\r
1310 // Clear train descriptors collection.
\r
1313 // Return true if there are not train descriptors in collection.
\r
1314 bool empty() const;
\r
1316 // Return true if the matcher supports mask in match methods.
\r
1317 bool isMaskSupported() const;
\r
1319 // Find one best match for each query descriptor.
\r
1320 // trainIdx.at<int>(0, queryIdx) will contain best train index for queryIdx
\r
1321 // distance.at<float>(0, queryIdx) will contain distance
\r
1322 void matchSingle(const GpuMat& queryDescs, const GpuMat& trainDescs,
\r
1323 GpuMat& trainIdx, GpuMat& distance,
\r
1324 const GpuMat& mask = GpuMat(), Stream& stream = Stream::Null());
\r
1326 // Download trainIdx and distance to CPU vector with DMatch
\r
1327 static void matchDownload(const GpuMat& trainIdx, const GpuMat& distance, std::vector<DMatch>& matches);
\r
1329 // Find one best match for each query descriptor.
\r
1330 void match(const GpuMat& queryDescs, const GpuMat& trainDescs, std::vector<DMatch>& matches,
\r
1331 const GpuMat& mask = GpuMat());
\r
1333 // Make gpu collection of trains and masks in suitable format for matchCollection function
\r
1334 void makeGpuCollection(GpuMat& trainCollection, GpuMat& maskCollection,
\r
1335 const vector<GpuMat>& masks = std::vector<GpuMat>());
\r
1337 // Find one best match from train collection for each query descriptor.
\r
1338 // trainIdx.at<int>(0, queryIdx) will contain best train index for queryIdx
\r
1339 // imgIdx.at<int>(0, queryIdx) will contain best image index for queryIdx
\r
1340 // distance.at<float>(0, queryIdx) will contain distance
\r
1341 void matchCollection(const GpuMat& queryDescs, const GpuMat& trainCollection,
\r
1342 GpuMat& trainIdx, GpuMat& imgIdx, GpuMat& distance,
\r
1343 const GpuMat& maskCollection, Stream& stream = Stream::Null());
\r
1345 // Download trainIdx, imgIdx and distance to CPU vector with DMatch
\r
1346 static void matchDownload(const GpuMat& trainIdx, const GpuMat& imgIdx, const GpuMat& distance,
\r
1347 std::vector<DMatch>& matches);
\r
1349 // Find one best match from train collection for each query descriptor.
\r
1350 void match(const GpuMat& queryDescs, std::vector<DMatch>& matches,
\r
1351 const std::vector<GpuMat>& masks = std::vector<GpuMat>());
\r
1353 // Find k best matches for each query descriptor (in increasing order of distances).
\r
1354 // trainIdx.at<int>(queryIdx, i) will contain index of i'th best trains (i < k).
\r
1355 // distance.at<float>(queryIdx, i) will contain distance.
\r
1356 // allDist is a buffer to store all distance between query descriptors and train descriptors
\r
1357 // it have size (nQuery,nTrain) and CV_32F type
\r
1358 // allDist.at<float>(queryIdx, trainIdx) will contain FLT_MAX, if trainIdx is one from k best,
\r
1359 // otherwise it will contain distance between queryIdx and trainIdx descriptors
\r
1360 void knnMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
\r
1361 GpuMat& trainIdx, GpuMat& distance, GpuMat& allDist, int k, const GpuMat& mask = GpuMat(), Stream& stream = Stream::Null());
\r
1363 // Download trainIdx and distance to CPU vector with DMatch
\r
1364 // compactResult is used when mask is not empty. If compactResult is false matches
\r
1365 // vector will have the same size as queryDescriptors rows. If compactResult is true
\r
1366 // matches vector will not contain matches for fully masked out query descriptors.
\r
1367 static void knnMatchDownload(const GpuMat& trainIdx, const GpuMat& distance,
\r
1368 std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
\r
1370 // Find k best matches for each query descriptor (in increasing order of distances).
\r
1371 // compactResult is used when mask is not empty. If compactResult is false matches
\r
1372 // vector will have the same size as queryDescriptors rows. If compactResult is true
\r
1373 // matches vector will not contain matches for fully masked out query descriptors.
\r
1374 void knnMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
\r
1375 std::vector< std::vector<DMatch> >& matches, int k, const GpuMat& mask = GpuMat(),
\r
1376 bool compactResult = false);
\r
1378 // Find k best matches for each query descriptor (in increasing order of distances).
\r
1379 // compactResult is used when mask is not empty. If compactResult is false matches
\r
1380 // vector will have the same size as queryDescriptors rows. If compactResult is true
\r
1381 // matches vector will not contain matches for fully masked out query descriptors.
\r
1382 void knnMatch(const GpuMat& queryDescs, std::vector< std::vector<DMatch> >& matches, int knn,
\r
1383 const std::vector<GpuMat>& masks = std::vector<GpuMat>(), bool compactResult = false );
\r
1385 // Find best matches for each query descriptor which have distance less than maxDistance.
\r
1386 // nMatches.at<unsigned int>(0, queruIdx) will contain matches count for queryIdx.
\r
1387 // carefully nMatches can be greater than trainIdx.cols - it means that matcher didn't find all matches,
\r
1388 // because it didn't have enough memory.
\r
1389 // trainIdx.at<int>(queruIdx, i) will contain ith train index (i < min(nMatches.at<unsigned int>(0, queruIdx), trainIdx.cols))
\r
1390 // distance.at<int>(queruIdx, i) will contain ith distance (i < min(nMatches.at<unsigned int>(0, queruIdx), trainIdx.cols))
\r
1391 // If trainIdx is empty, then trainIdx and distance will be created with size nQuery x nTrain,
\r
1392 // otherwize user can pass own allocated trainIdx and distance with size nQuery x nMaxMatches
\r
1393 // Matches doesn't sorted.
\r
1394 void radiusMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
\r
1395 GpuMat& trainIdx, GpuMat& nMatches, GpuMat& distance, float maxDistance,
\r
1396 const GpuMat& mask = GpuMat(), Stream& stream = Stream::Null());
\r
1398 // Download trainIdx, nMatches and distance to CPU vector with DMatch.
\r
1399 // matches will be sorted in increasing order of distances.
\r
1400 // compactResult is used when mask is not empty. If compactResult is false matches
\r
1401 // vector will have the same size as queryDescriptors rows. If compactResult is true
\r
1402 // matches vector will not contain matches for fully masked out query descriptors.
\r
1403 static void radiusMatchDownload(const GpuMat& trainIdx, const GpuMat& nMatches, const GpuMat& distance,
\r
1404 std::vector< std::vector<DMatch> >& matches, bool compactResult = false);
\r
1406 // Find best matches for each query descriptor which have distance less than maxDistance
\r
1407 // in increasing order of distances).
\r
1408 void radiusMatch(const GpuMat& queryDescs, const GpuMat& trainDescs,
\r
1409 std::vector< std::vector<DMatch> >& matches, float maxDistance,
\r
1410 const GpuMat& mask = GpuMat(), bool compactResult = false);
\r
1412 // Find best matches from train collection for each query descriptor which have distance less than
\r
1413 // maxDistance (in increasing order of distances).
\r
1414 void radiusMatch(const GpuMat& queryDescs, std::vector< std::vector<DMatch> >& matches, float maxDistance,
\r
1415 const std::vector<GpuMat>& masks = std::vector<GpuMat>(), bool compactResult = false);
\r
1417 DistType distType;
\r
1420 std::vector<GpuMat> trainDescCollection;
\r
1423 template <class Distance>
\r
1424 class CV_EXPORTS BruteForceMatcher_GPU;
\r
1426 template <typename T>
\r
1427 class CV_EXPORTS BruteForceMatcher_GPU< L1<T> > : public BruteForceMatcher_GPU_base
\r
1430 explicit BruteForceMatcher_GPU() : BruteForceMatcher_GPU_base(L1Dist) {}
\r
1431 explicit BruteForceMatcher_GPU(L1<T> /*d*/) : BruteForceMatcher_GPU_base(L1Dist) {}
\r
1433 template <typename T>
\r
1434 class CV_EXPORTS BruteForceMatcher_GPU< L2<T> > : public BruteForceMatcher_GPU_base
\r
1437 explicit BruteForceMatcher_GPU() : BruteForceMatcher_GPU_base(L2Dist) {}
\r
1438 explicit BruteForceMatcher_GPU(L2<T> /*d*/) : BruteForceMatcher_GPU_base(L2Dist) {}
\r
1440 template <> class CV_EXPORTS BruteForceMatcher_GPU< HammingLUT > : public BruteForceMatcher_GPU_base
\r
1443 explicit BruteForceMatcher_GPU() : BruteForceMatcher_GPU_base(HammingDist) {}
\r
1444 explicit BruteForceMatcher_GPU(HammingLUT /*d*/) : BruteForceMatcher_GPU_base(HammingDist) {}
\r
1446 template <> class CV_EXPORTS BruteForceMatcher_GPU< Hamming > : public BruteForceMatcher_GPU_base
\r
1449 explicit BruteForceMatcher_GPU() : BruteForceMatcher_GPU_base(HammingDist) {}
\r
1450 explicit BruteForceMatcher_GPU(Hamming /*d*/) : BruteForceMatcher_GPU_base(HammingDist) {}
\r
1453 ////////////////////////////////// CascadeClassifier_GPU //////////////////////////////////////////
\r
1454 // The cascade classifier class for object detection.
\r
1455 class CV_EXPORTS CascadeClassifier_GPU
\r
1458 CascadeClassifier_GPU();
\r
1459 CascadeClassifier_GPU(const string& filename);
\r
1460 ~CascadeClassifier_GPU();
\r
1462 bool empty() const;
\r
1463 bool load(const string& filename);
\r
1466 /* returns number of detected objects */
\r
1467 int detectMultiScale( const GpuMat& image, GpuMat& objectsBuf, double scaleFactor=1.2, int minNeighbors=4, Size minSize=Size());
\r
1469 bool findLargestObject;
\r
1470 bool visualizeInPlace;
\r
1472 Size getClassifierSize() const;
\r
1475 struct CascadeClassifierImpl;
\r
1476 CascadeClassifierImpl* impl;
\r
1479 ////////////////////////////////// SURF //////////////////////////////////////////
\r
1481 class CV_EXPORTS SURF_GPU : public CvSURFParams
\r
1484 enum KeypointLayout
\r
1495 //! the default constructor
\r
1497 //! the full constructor taking all the necessary parameters
\r
1498 explicit SURF_GPU(double _hessianThreshold, int _nOctaves=4,
\r
1499 int _nOctaveLayers=2, bool _extended=false, float _keypointsRatio=0.01f, bool _upright = false);
\r
1501 //! returns the descriptor size in float's (64 or 128)
\r
1502 int descriptorSize() const;
\r
1504 //! upload host keypoints to device memory
\r
1505 void uploadKeypoints(const vector<KeyPoint>& keypoints, GpuMat& keypointsGPU);
\r
1506 //! download keypoints from device to host memory
\r
1507 void downloadKeypoints(const GpuMat& keypointsGPU, vector<KeyPoint>& keypoints);
\r
1509 //! download descriptors from device to host memory
\r
1510 void downloadDescriptors(const GpuMat& descriptorsGPU, vector<float>& descriptors);
\r
1512 //! finds the keypoints using fast hessian detector used in SURF
\r
1513 //! supports CV_8UC1 images
\r
1514 //! keypoints will have nFeature cols and 6 rows
\r
1515 //! keypoints.ptr<float>(SF_X)[i] will contain x coordinate of i'th feature
\r
1516 //! keypoints.ptr<float>(SF_Y)[i] will contain y coordinate of i'th feature
\r
1517 //! keypoints.ptr<float>(SF_LAPLACIAN)[i] will contain laplacian sign of i'th feature
\r
1518 //! keypoints.ptr<float>(SF_SIZE)[i] will contain size of i'th feature
\r
1519 //! keypoints.ptr<float>(SF_DIR)[i] will contain orientation of i'th feature
\r
1520 //! keypoints.ptr<float>(SF_HESSIAN)[i] will contain response of i'th feature
\r
1521 void operator()(const GpuMat& img, const GpuMat& mask, GpuMat& keypoints);
\r
1522 //! finds the keypoints and computes their descriptors.
\r
1523 //! Optionally it can compute descriptors for the user-provided keypoints and recompute keypoints direction
\r
1524 void operator()(const GpuMat& img, const GpuMat& mask, GpuMat& keypoints, GpuMat& descriptors,
\r
1525 bool useProvidedKeypoints = false);
\r
1527 void operator()(const GpuMat& img, const GpuMat& mask, std::vector<KeyPoint>& keypoints);
\r
1528 void operator()(const GpuMat& img, const GpuMat& mask, std::vector<KeyPoint>& keypoints, GpuMat& descriptors,
\r
1529 bool useProvidedKeypoints = false);
\r
1531 void operator()(const GpuMat& img, const GpuMat& mask, std::vector<KeyPoint>& keypoints, std::vector<float>& descriptors,
\r
1532 bool useProvidedKeypoints = false);
\r
1534 //! max keypoints = min(keypointsRatio * img.size().area(), 65535)
\r
1535 float keypointsRatio;
\r
1537 GpuMat sum, mask1, maskSum, intBuffer;
\r
1539 GpuMat det, trace;
\r
1541 GpuMat maxPosBuffer;
\r
1546 //! Speckle filtering - filters small connected components on diparity image.
\r
1547 //! It sets pixel (x,y) to newVal if it coresponds to small CC with size < maxSpeckleSize.
\r
1548 //! Threshold for border between CC is diffThreshold;
\r
1549 CV_EXPORTS void filterSpeckles( Mat& img, uchar newVal, int maxSpeckleSize, uchar diffThreshold, Mat& buf);
\r
1552 #include "opencv2/gpu/matrix_operations.hpp"
\r
1554 #endif /* __OPENCV_GPU_HPP__ */
\r