#include <iomanip>
#include <stdexcept>
#include <opencv2/core/utility.hpp>
-#include "opencv2/cuda.hpp"
+#include "opencv2/cudaobjdetect.hpp"
#include "opencv2/highgui.hpp"
#include "opencv2/objdetect.hpp"
#include "opencv2/imgproc.hpp"
static Args read(int argc, char** argv);
string src;
+ bool src_is_folder;
bool src_is_video;
bool src_is_camera;
int camera_id;
+ bool svm_load;
+ string svm;
+
bool write_video;
string dst_video;
double dst_video_fps;
int win_width;
int win_stride_width, win_stride_height;
+ int block_width;
+ int block_stride_width, block_stride_height;
+ int cell_width;
+ int nbins;
bool gamma_corr;
};
cout << "Histogram of Oriented Gradients descriptor and detector sample.\n"
<< "\nUsage: hog_gpu\n"
<< " (<image>|--video <vide>|--camera <camera_id>) # frames source\n"
+ << " or"
+ << " (--folder <folder_path>) # load images from folder\n"
+ << " [--svm <file> # load svm file"
<< " [--make_gray <true/false>] # convert image to gray one or not\n"
<< " [--resize_src <true/false>] # do resize of the source image or not\n"
<< " [--width <int>] # resized image width\n"
<< " [--hit_threshold <double>] # classifying plane distance threshold (0.0 usually)\n"
<< " [--scale <double>] # HOG window scale factor\n"
<< " [--nlevels <int>] # max number of HOG window scales\n"
- << " [--win_width <int>] # width of the window (48 or 64)\n"
+ << " [--win_width <int>] # width of the window\n"
<< " [--win_stride_width <int>] # distance by OX axis between neighbour wins\n"
<< " [--win_stride_height <int>] # distance by OY axis between neighbour wins\n"
+ << " [--block_width <int>] # width of the block\n"
+ << " [--block_stride_width <int>] # distance by 0X axis between neighbour blocks\n"
+ << " [--block_stride_height <int>] # distance by 0Y axis between neighbour blocks\n"
+ << " [--cell_width <int>] # width of the cell\n"
+ << " [--nbins <int>] # number of bins\n"
<< " [--gr_threshold <int>] # merging similar rects constant\n"
<< " [--gamma_correct <int>] # do gamma correction or not\n"
<< " [--write_video <bool>] # write video or not\n"
{
try
{
+ Args args;
if (argc < 2)
+ {
printHelp();
- Args args = Args::read(argc, argv);
- if (help_showed)
- return -1;
+ args.camera_id = 0;
+ args.src_is_camera = true;
+ }
+ else
+ {
+ args = Args::read(argc, argv);
+ if (help_showed)
+ return -1;
+ }
App app(args);
app.run();
}
{
src_is_video = false;
src_is_camera = false;
+ src_is_folder = false;
+ svm_load = false;
camera_id = 0;
write_video = false;
win_width = 48;
win_stride_width = 8;
win_stride_height = 8;
+ block_width = 16;
+ block_stride_width = 8;
+ block_stride_height = 8;
+ cell_width = 8;
+ nbins = 9;
gamma_corr = true;
}
else if (string(argv[i]) == "--win_width") args.win_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_width") args.win_stride_width = atoi(argv[++i]);
else if (string(argv[i]) == "--win_stride_height") args.win_stride_height = atoi(argv[++i]);
+ else if (string(argv[i]) == "--block_width") args.block_width = atoi(argv[++i]);
+ else if (string(argv[i]) == "--block_stride_width") args.block_stride_width = atoi(argv[++i]);
+ else if (string(argv[i]) == "--block_stride_height") args.block_stride_height = atoi(argv[++i]);
+ else if (string(argv[i]) == "--cell_width") args.cell_width = atoi(argv[++i]);
+ else if (string(argv[i]) == "--nbins") args.nbins = atoi(argv[++i]);
else if (string(argv[i]) == "--gr_threshold") args.gr_threshold = atoi(argv[++i]);
else if (string(argv[i]) == "--gamma_correct") args.gamma_corr = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--write_video") args.write_video = (string(argv[++i]) == "true");
else if (string(argv[i]) == "--help") printHelp();
else if (string(argv[i]) == "--video") { args.src = argv[++i]; args.src_is_video = true; }
else if (string(argv[i]) == "--camera") { args.camera_id = atoi(argv[++i]); args.src_is_camera = true; }
+ else if (string(argv[i]) == "--folder") { args.src = argv[++i]; args.src_is_folder = true;}
+ else if (string(argv[i]) == "--svm") { args.svm = argv[++i]; args.svm_load = true;}
else if (args.src.empty()) args.src = argv[i];
else throw runtime_error((string("unknown key: ") + argv[i]));
}
gamma_corr = args.gamma_corr;
- if (args.win_width != 64 && args.win_width != 48)
- args.win_width = 64;
-
cout << "Scale: " << scale << endl;
if (args.resize_src)
cout << "Resized source: (" << args.width << ", " << args.height << ")\n";
cout << "Group threshold: " << gr_threshold << endl;
cout << "Levels number: " << nlevels << endl;
- cout << "Win width: " << args.win_width << endl;
+ cout << "Win size: (" << args.win_width << ", " << args.win_width*2 << ")\n";
cout << "Win stride: (" << args.win_stride_width << ", " << args.win_stride_height << ")\n";
+ cout << "Block size: (" << args.block_width << ", " << args.block_width << ")\n";
+ cout << "Block stride: (" << args.block_stride_width << ", " << args.block_stride_height << ")\n";
+ cout << "Cell size: (" << args.cell_width << ", " << args.cell_width << ")\n";
+ cout << "Bins number: " << args.nbins << endl;
cout << "Hit threshold: " << hit_threshold << endl;
cout << "Gamma correction: " << gamma_corr << endl;
cout << endl;
running = true;
cv::VideoWriter video_writer;
- Size win_size(args.win_width, args.win_width * 2); //(64, 128) or (48, 96)
Size win_stride(args.win_stride_width, args.win_stride_height);
+ Size win_size(args.win_width, args.win_width * 2);
+ Size block_size(args.block_width, args.block_width);
+ Size block_stride(args.block_stride_width, args.block_stride_height);
+ Size cell_size(args.cell_width, args.cell_width);
+
+ cv::Ptr<cv::cuda::HOG> gpu_hog = cv::cuda::HOG::create(win_size, block_size, block_stride, cell_size, args.nbins);
+ cv::HOGDescriptor cpu_hog(win_size, block_size, block_stride, cell_size, args.nbins);
+
+ if(args.svm_load) {
+ std::vector<float> svm_model;
+ const std::string model_file_name = args.svm;
+ FileStorage ifs(model_file_name, FileStorage::READ);
+ if (ifs.isOpened()) {
+ ifs["svm_detector"] >> svm_model;
+ } else {
+ const std::string what =
+ "could not load model for hog classifier from file: "
+ + model_file_name;
+ throw std::runtime_error(what);
+ }
+
+ // check if the variables are initialized
+ if (svm_model.empty()) {
+ const std::string what =
+ "HoG classifier: svm model could not be loaded from file"
+ + model_file_name;
+ throw std::runtime_error(what);
+ }
+
+ gpu_hog->setSVMDetector(svm_model);
+ cpu_hog.setSVMDetector(svm_model);
+ } else {
+ // Create HOG descriptors and detectors here
+ Mat detector = gpu_hog->getDefaultPeopleDetector();
- // Create HOG descriptors and detectors here
- vector<float> detector;
- if (win_size == Size(64, 128))
- detector = cv::cuda::HOGDescriptor::getPeopleDetector64x128();
- else
- detector = cv::cuda::HOGDescriptor::getPeopleDetector48x96();
-
- cv::cuda::HOGDescriptor gpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9,
- cv::cuda::HOGDescriptor::DEFAULT_WIN_SIGMA, 0.2, gamma_corr,
- cv::cuda::HOGDescriptor::DEFAULT_NLEVELS);
- cv::HOGDescriptor cpu_hog(win_size, Size(16, 16), Size(8, 8), Size(8, 8), 9, 1, -1,
- HOGDescriptor::L2Hys, 0.2, gamma_corr, cv::HOGDescriptor::DEFAULT_NLEVELS);
- gpu_hog.setSVMDetector(detector);
- cpu_hog.setSVMDetector(detector);
+ gpu_hog->setSVMDetector(detector);
+ cpu_hog.setSVMDetector(detector);
+ }
+
+ cout << "gpusvmDescriptorSize : " << gpu_hog->getDescriptorSize()
+ << endl;
+ cout << "cpusvmDescriptorSize : " << cpu_hog.getDescriptorSize()
+ << endl;
while (running)
{
VideoCapture vc;
Mat frame;
+ vector<String> filenames;
+
+ unsigned int count = 1;
if (args.src_is_video)
{
throw runtime_error(string("can't open video file: " + args.src));
vc >> frame;
}
+ else if (args.src_is_folder) {
+ String folder = args.src;
+ cout << folder << endl;
+ glob(folder, filenames);
+ frame = imread(filenames[count]); // 0 --> .gitignore
+ if (!frame.data)
+ cerr << "Problem loading image from folder!!!" << endl;
+ }
else if (args.src_is_camera)
{
vc.open(args.camera_id);
else img = img_aux;
img_to_show = img;
- gpu_hog.nlevels = nlevels;
- cpu_hog.nlevels = nlevels;
-
vector<Rect> found;
// Perform HOG classification
if (use_gpu)
{
gpu_img.upload(img);
- gpu_hog.detectMultiScale(gpu_img, found, hit_threshold, win_stride,
+ gpu_hog->setNumLevels(nlevels);
+ gpu_hog->setHitThreshold(hit_threshold);
+ gpu_hog->setWinStride(win_stride);
+ gpu_hog->setScaleFactor(scale);
+ gpu_hog->setGroupThreshold(gr_threshold);
+ gpu_hog->detectMultiScale(gpu_img, found);
+ }
+ else
+ {
+ cpu_hog.nlevels = nlevels;
+ cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
Size(0, 0), scale, gr_threshold);
}
- else cpu_hog.detectMultiScale(img, found, hit_threshold, win_stride,
- Size(0, 0), scale, gr_threshold);
hogWorkEnd();
// Draw positive classified windows
putText(img_to_show, "Mode: GPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
else
putText(img_to_show, "Mode: CPU", Point(5, 25), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
- putText(img_to_show, "FPS (HOG only): " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
- putText(img_to_show, "FPS (total): " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+ putText(img_to_show, "FPS HOG: " + hogWorkFps(), Point(5, 65), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
+ putText(img_to_show, "FPS total: " + workFps(), Point(5, 105), FONT_HERSHEY_SIMPLEX, 1., Scalar(255, 100, 0), 2);
imshow("opencv_gpu_hog", img_to_show);
if (args.src_is_video || args.src_is_camera) vc >> frame;
+ if (args.src_is_folder) {
+ count++;
+ if (count < filenames.size()) {
+ frame = imread(filenames[count]);
+ } else {
+ Mat empty;
+ frame = empty;
+ }
+ }
workEnd();
projects / platform / upstream / opencv.git / blobdiff