#endif // OPENMP
#define DEBUG_PRINT(obj) \
- if (m_debug) { \
+ if (m_debug || m_visual_debug) { \
std::cout << #obj << " @" << __LINE__ << std::endl << (obj) << std::endl; \
}
#define DEBUG_PRINTM(obj) \
p_roi.width = p_windows_size.width / p_cell_size;
p_roi.height = p_windows_size.height / p_cell_size;
- p_num_of_feats = 31;
- if (m_use_color) p_num_of_feats += 3;
- if (m_use_cnfeat) p_num_of_feats += 10;
-
p_scales.clear();
- if (m_use_scale)
+ if (m_use_scale) {
for (int i = -int(p_num_scales) / 2; i <= int(p_num_scales) / 2; ++i)
p_scales.push_back(std::pow(p_scale_step, i));
- else
+ } else {
p_scales.push_back(1.);
+ p_num_scales = 1;
+ }
+
+ if (m_use_angle) {
+ for (int i = p_angle_min; i <= p_angle_max; i += p_angle_step)
+ p_angles.push_back(i);
+ } else {
+ p_angles.push_back(0);
+ p_num_angles = 1;
+ }
#ifdef CUFFT
if (p_roi.height * (p_roi.width / 2 + 1) > 1024) {
std::cerr << "Window after forward FFT is too big for CUDA kernels. Plese use -f to set "
"the window dimensions so its size is less or equal to "
<< 1024 * p_cell_size * p_cell_size * 2 + 1
- << " pixels . Currently the size of the window is: " << p_windows_size.width << "x" << p_windows_size.height
- << " which is " << p_windows_size.width * p_windows_size.height << " pixels. " << std::endl;
+ << " pixels . Currently the size of the window is: " << p_windows_size.width << "x"
+ << p_windows_size.height << " which is " << p_windows_size.width * p_windows_size.height
+ << " pixels. " << std::endl;
std::exit(EXIT_FAILURE);
}
std::cerr << "cuFFT supports only Gaussian kernel." << std::endl;
std::exit(EXIT_FAILURE);
}
+
CudaSafeCall(cudaSetDeviceFlags(cudaDeviceMapHost));
+
p_rot_labels_data = DynMem(p_roi.width * p_roi.height * sizeof(float));
p_rot_labels = cv::Mat(p_roi, CV_32FC1, p_rot_labels_data.hostMem());
-#else
- p_xf.create(p_roi.height, p_roi.height / 2 + 1, p_num_of_feats);
#endif
#if defined(CUFFT) || defined(FFTW)
p_yf.create(p_roi.height, width, 1);
p_xf.create(p_roi.height, width, p_num_of_feats);
- int max = BIG_BATCH_MODE ? 2 : p_num_scales;
- for (int i = 0; i < max; ++i) {
- if (BIG_BATCH_MODE && i == 1)
- p_threadctxs.emplace_back(p_roi, p_num_of_feats * p_num_scales, 1, p_num_scales);
- else
- p_threadctxs.emplace_back(p_roi, p_num_of_feats, p_scales[i], 1);
+ int max1 = BIG_BATCH_MODE ? 2 : p_num_scales;
+ int max2 = BIG_BATCH_MODE ? 1 : p_num_angles;
+ for (int i = 0; i < max1; ++i) {
+ for (int j = 0; j < max2; ++j) {
+ if (BIG_BATCH_MODE && i == 1)
+ p_threadctxs.emplace_back(p_roi, p_num_of_feats * p_num_scales * p_num_angles, 1, 0, p_num_scales,
+ p_num_angles);
+ else
+ p_threadctxs.emplace_back(p_roi, p_num_of_feats, p_scales[i], p_angles[j]);
+ }
}
p_current_scale = 1.;
fft.set_window(cosine_window_function(p_roi.width, p_roi.height));
// window weights, i.e. labels
- fft.forward(
- gaussian_shaped_labels(p_output_sigma, p_roi.width, p_roi.height), p_yf,
- m_use_cuda ? p_rot_labels_data.deviceMem() : nullptr, p_threadctxs.front().stream);
+ fft.forward(gaussian_shaped_labels(p_output_sigma, p_roi.width, p_roi.height), p_yf,
+ m_use_cuda ? p_rot_labels_data.deviceMem() : nullptr, p_threadctxs.front().stream);
DEBUG_PRINTM(p_yf);
// obtain a sub-window for training initial model
- std::vector<cv::Mat> patch_feats = get_features(input_rgb, input_gray, p_pose.cx, p_pose.cy,
- p_windows_size.width, p_windows_size.height);
+ int size_x_scaled = floor(p_windows_size.width);
+ int size_y_scaled = floor(p_windows_size.height);
+
+ cv::Mat patch_gray = get_subwindow(input_gray, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_gray, p_windows_size.width, p_windows_size.height, 0, false);
+
+ cv::Mat patch_rgb;
+ if ((m_use_color || m_use_cnfeat) && input_rgb.channels() == 3) {
+ patch_rgb = get_subwindow(input_rgb, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_rgb, p_windows_size.width, p_windows_size.height, 0, false);
+ }
+
+ std::vector<cv::Mat> patch_feats = get_features(patch_rgb, patch_gray);
fft.forward_window(patch_feats, p_model_xf, p_threadctxs.front().fw_all,
m_use_cuda ? p_threadctxs.front().data_features.deviceMem() : nullptr,
p_threadctxs.front().stream);
DEBUG_PRINTM(p_model_xf);
+
#if !defined(BIG_BATCH) && defined(CUFFT) && (defined(ASYNC) || defined(OPENMP))
p_threadctxs.front().model_xf = p_model_xf;
p_threadctxs.front().model_xf.set_stream(p_threadctxs.front().stream);
BBox_c tmp = p_pose;
tmp.w *= p_current_scale;
tmp.h *= p_current_scale;
+ tmp.a = p_current_angle;
if (p_resize_image) tmp.scale(1 / p_downscale_factor);
if (p_fit_to_pw2) {
void KCF_Tracker::track(cv::Mat &img)
{
- if (m_debug) std::cout << "NEW FRAME" << '\n';
+ if (m_debug || m_visual_debug) std::cout << "\nNEW FRAME" << std::endl;
cv::Mat input_gray, input_rgb = img.clone();
if (img.channels() == 3) {
cv::cvtColor(img, input_gray, CV_BGR2GRAY);
cv::resize(input_rgb, input_rgb, cv::Size(0, 0), p_scale_factor_x, p_scale_factor_y, cv::INTER_LINEAR);
}
}
-
max_response = -1.;
ThreadCtx *max = nullptr;
cv::Point2i *max_response_pt = nullptr;
});
for (auto const &it : p_threadctxs)
it.async_res.wait();
-
#else // !ASYNC
- // FIXME: Iterate correctly in big batch mode - perhaps have only one element in the list
NORMAL_OMP_PARALLEL_FOR
- for (uint i = 0; i < p_threadctxs.size(); ++i)
+ for (uint i = BIG_BATCH_MODE ? 1 : 0; i < p_threadctxs.size(); ++i)
scale_track(p_threadctxs[i], input_rgb, input_gray);
#endif
}
}
#else
- // FIXME: Iterate correctly in big batch mode - perhaps have only one element in the list
- for (uint j = 0; j < p_scales.size(); ++j) {
- if (p_threadctxs[0].max_responses[j] > max_response) {
- max_response = p_threadctxs[0].max_responses[j];
- max_response_pt = &p_threadctxs[0].max_locs[j];
- max_response_map = &p_threadctxs[0].response_maps[j];
- max = &p_threadctxs[0];
+ for (uint j = 0; j < p_num_scales; ++j) {
+ for (uint k = 0; k < p_num_angles; ++k) {
+ if (p_threadctxs.back().max_responses[j + k] > max_response) {
+ max_response = p_threadctxs.back().max_responses[j + k];
+ max_response_pt = &p_threadctxs.back().max_locs[j + k];
+ max_response_map = &p_threadctxs.back().response_maps[j + k];
+ }
}
}
+ max = &p_threadctxs.back();
#endif
+ if (m_visual_debug) {
+ cv::Mat all_responses(cv::Size(p_num_angles* p_debug_image_size, p_num_scales * p_debug_image_size),
+ p_debug_scale_responses[0].type(), cv::Scalar::all(0));
+ cv::Mat all_subwindows(cv::Size(p_num_angles* p_debug_image_size, p_num_scales* p_debug_image_size),
+ p_debug_subwindows[0].type(), cv::Scalar::all(0));
+ for (size_t i = 0; i < p_num_scales; ++i) {
+ for (size_t j = 0; j < p_num_angles; ++j) {
+ cv::Mat in_roi(all_responses, cv::Rect(j * p_debug_image_size, i * p_debug_image_size,
+ p_debug_image_size, p_debug_image_size));
+ p_debug_scale_responses[5 * i + j].copyTo(in_roi);
+ in_roi = all_subwindows(
+ cv::Rect(j * p_debug_image_size, i * p_debug_image_size, p_debug_image_size, p_debug_image_size));
+ p_debug_subwindows[5 * i + j].copyTo(in_roi);
+ }
+ }
+ cv::namedWindow("All subwindows", CV_WINDOW_AUTOSIZE);
+ cv::imshow("All subwindows", all_subwindows);
+ cv::namedWindow("All responses", CV_WINDOW_AUTOSIZE);
+ cv::imshow("All responses", all_responses);
+ cv::waitKey();
+ p_debug_scale_responses.clear();
+ p_debug_subwindows.clear();
+ }
DEBUG_PRINTM(*max_response_map);
DEBUG_PRINT(*max_response_pt);
new_location = sub_pixel_peak(*max_response_pt, *max_response_map);
DEBUG_PRINT(new_location);
+ if (m_visual_debug) std::cout << "Old p_pose, cx: " << p_pose.cx << " cy: " << p_pose.cy << std::endl;
+
p_pose.cx += p_current_scale * p_cell_size * double(new_location.x);
p_pose.cy += p_current_scale * p_cell_size * double(new_location.y);
+
+ if (m_visual_debug) std::cout << "New p_pose, cx: " << p_pose.cx << " cy: " << p_pose.cy << std::endl;
+
if (p_fit_to_pw2) {
clamp2(p_pose.cx, 0.0, (img.cols * p_scale_factor_x) - 1);
clamp2(p_pose.cy, 0.0, (img.rows * p_scale_factor_y) - 1);
clamp2(p_current_scale, p_min_max_scale[0], p_min_max_scale[1]);
- ThreadCtx &ctx = p_threadctxs.front();
+ if (p_current_scale < p_min_max_scale[0]) p_current_scale = p_min_max_scale[0];
+ if (p_current_scale > p_min_max_scale[1]) p_current_scale = p_min_max_scale[1];
+
+ p_current_angle = (p_current_angle + max->angle) < 0
+ ? -std::abs(p_current_angle + max->angle) % 360
+ : (p_current_angle + max->angle) % 360;
+
// obtain a subwindow for training at newly estimated target position
- std::vector<cv::Mat> patch_feats = get_features(input_rgb, input_gray, p_pose.cx, p_pose.cy,
- p_windows_size.width, p_windows_size.height,
- p_current_scale);
- fft.forward_window(patch_feats, p_xf, ctx.fw_all,
- m_use_cuda ? ctx.data_features.deviceMem() : nullptr, ctx.stream);
+ int size_x_scaled = floor(p_windows_size.width * p_current_scale);
+ int size_y_scaled = floor(p_windows_size.height * p_current_scale);
+
+ cv::Mat patch_gray = get_subwindow(input_gray, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_gray, p_windows_size.width, p_windows_size.height, p_current_angle, false);
+
+ cv::Mat patch_rgb = cv::Mat::zeros(size_y_scaled, size_x_scaled, CV_32F);
+ if ((m_use_color || m_use_cnfeat) && input_rgb.channels() == 3) {
+ patch_rgb = get_subwindow(input_rgb, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_rgb, p_windows_size.width, p_windows_size.height, p_current_angle, false);
+ }
+
+ ThreadCtx &ctx = p_threadctxs.front();
+ std::vector<cv::Mat> patch_feats = get_features(patch_rgb, patch_gray);
+ fft.forward_window(patch_feats, p_xf, ctx.fw_all, m_use_cuda ? ctx.data_features.deviceMem() : nullptr, ctx.stream);
// subsequent frames, interpolate model
p_model_xf = p_model_xf * float((1. - p_interp_factor)) + p_xf * float(p_interp_factor);
std::vector<cv::Mat> patch_feats;
if (BIG_BATCH_MODE) {
BIG_BATCH_OMP_PARALLEL_FOR
- for (uint i = 0; i < p_num_scales; ++i) {
- patch_feats = get_features(input_rgb, input_gray, this->p_pose.cx, this->p_pose.cy,
- this->p_windows_size.width, this->p_windows_size.height,
- this->p_current_scale * this->p_scales[i]);
+ for (uint i = 0; i < this->p_scales.size(); ++i) {
+ for (uint j = 0; j < this->p_angles.size(); ++j) {
+ int size_x_scaled = floor(this->p_windows_size.width * this->p_current_scale * this->p_scales[i]);
+ int size_y_scaled = floor(this->p_windows_size.height * this->p_current_scale * this->p_scales[i]);
+
+ cv::Mat patch_gray =
+ get_subwindow(input_gray, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_gray, p_windows_size.width, p_windows_size.height,
+ p_current_scale * this->p_scales[i], p_current_angle + this->p_angles[j]);
+
+ cv::Mat patch_rgb;
+ if ((m_use_color || m_use_cnfeat) && input_rgb.channels() == 3) {
+ patch_rgb =
+ get_subwindow(input_rgb, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_rgb, p_windows_size.width, p_windows_size.height,
+ p_current_scale * this->p_scales[i], p_current_angle + this->p_angles[j]);
+ }
+ std::vector<cv::Mat> tmp = get_features(patch_rgb, patch_gray);
+ BIG_BATCH_OMP_ORDERED
+ patch_feats.insert(patch_feats.end(), tmp.begin(), tmp.end());
+ }
}
} else {
- patch_feats = get_features(input_rgb, input_gray, this->p_pose.cx, this->p_pose.cy,
- this->p_windows_size.width, this->p_windows_size.height,
- this->p_current_scale * vars.scale);
+ int size_x_scaled = floor(this->p_windows_size.width * this->p_current_scale * vars.scale);
+ int size_y_scaled = floor(this->p_windows_size.height * this->p_current_scale * vars.scale);
+
+ cv::Mat patch_gray = get_subwindow(input_gray, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_gray, p_windows_size.width, p_windows_size.height, p_current_scale * vars.scale);
+
+ cv::Mat patch_rgb;
+ if ((m_use_color || m_use_cnfeat) && input_rgb.channels() == 3) {
+ patch_rgb = get_subwindow(input_rgb, this->p_pose.cx, this->p_pose.cy, size_x_scaled, size_y_scaled);
+ geometric_transformations(patch_rgb, p_windows_size.width, p_windows_size.height, p_current_scale * vars.scale,
+ p_current_angle + vars.angle);
+ }
+ patch_feats = get_features(patch_rgb, patch_gray);
}
fft.forward_window(patch_feats, vars.zf, vars.fw_all, m_use_cuda ? vars.data_features.deviceMem() : nullptr,
// ****************************************************************************
-std::vector<cv::Mat> KCF_Tracker::get_features(cv::Mat & input_rgb, cv::Mat & input_gray, int cx, int cy, int size_x, int size_y, double scale)
+std::vector<cv::Mat> KCF_Tracker::get_features(cv::Mat &patch_rgb, cv::Mat &patch_gray)
{
- int size_x_scaled = floor(size_x * scale);
- int size_y_scaled = floor(size_y * scale);
-
- cv::Mat patch_gray = get_subwindow(input_gray, cx, cy, size_x_scaled, size_y_scaled);
- cv::Mat patch_rgb = get_subwindow(input_rgb, cx, cy, size_x_scaled, size_y_scaled);
-
- // resize to default size
- if (scale > 1.) {
- // if we downsample use INTER_AREA interpolation
- cv::resize(patch_gray, patch_gray, cv::Size(size_x, size_y), 0., 0., cv::INTER_AREA);
- } else {
- cv::resize(patch_gray, patch_gray, cv::Size(size_x, size_y), 0., 0., cv::INTER_LINEAR);
- }
-
// get hog(Histogram of Oriented Gradients) features
std::vector<cv::Mat> hog_feat = FHoG::extract(patch_gray, 2, p_cell_size, 9);
// get color rgb features (simple r,g,b channels)
std::vector<cv::Mat> color_feat;
- if ((m_use_color || m_use_cnfeat) && input_rgb.channels() == 3) {
- // resize to default size
- if (scale > 1.) {
- // if we downsample use INTER_AREA interpolation
- cv::resize(patch_rgb, patch_rgb, cv::Size(size_x / p_cell_size, size_y / p_cell_size), 0., 0., cv::INTER_AREA);
- } else {
- cv::resize(patch_rgb, patch_rgb, cv::Size(size_x / p_cell_size, size_y / p_cell_size), 0., 0., cv::INTER_LINEAR);
- }
- }
- if (m_use_color && input_rgb.channels() == 3) {
+ if (m_use_color && patch_rgb.channels() == 3) {
// use rgb color space
cv::Mat patch_rgb_norm;
patch_rgb.convertTo(patch_rgb_norm, CV_32F, 1. / 255., -0.5);
color_feat.insert(color_feat.end(), rgb.begin(), rgb.end());
}
- if (m_use_cnfeat && input_rgb.channels() == 3) {
+ if (m_use_cnfeat && patch_rgb.channels() == 3) {
std::vector<cv::Mat> cn_feat = CNFeat::extract(patch_rgb);
color_feat.insert(color_feat.end(), cn_feat.begin(), cn_feat.end());
}
if (x2 - x1 == 0 || y2 - y1 == 0)
patch = cv::Mat::zeros(height, width, CV_32FC1);
- else {
+ else
cv::copyMakeBorder(input(cv::Range(y1, y2), cv::Range(x1, x2)), patch, top, bottom, left, right,
cv::BORDER_REPLICATE);
- // imshow( "copyMakeBorder", patch);
- // cv::waitKey();
- }
// sanity check
assert(patch.cols == width && patch.rows == height);
return patch;
}
-void KCF_Tracker::gaussian_correlation(struct ThreadCtx &vars, const ComplexMat &xf, const ComplexMat &yf,
- double sigma, bool auto_correlation)
+void KCF_Tracker::geometric_transformations(cv::Mat &patch, int size_x, int size_y, int angle, bool allow_debug)
+{
+ if (m_use_angle) {
+ cv::Point2f center((patch.cols - 1) / 2., (patch.rows - 1) / 2.);
+ cv::Mat r = cv::getRotationMatrix2D(center, angle, 1.0);
+
+ cv::warpAffine(patch, patch, r, cv::Size(patch.cols, patch.rows), cv::INTER_LINEAR, cv::BORDER_REPLICATE);
+ }
+
+ // resize to default size
+ if (patch.channels() != 3) {
+ if (patch.cols / size_x > 1.) {
+ // if we downsample use INTER_AREA interpolation
+ cv::resize(patch, patch, cv::Size(size_x, size_y), 0., 0., cv::INTER_AREA);
+ } else {
+ cv::resize(patch, patch, cv::Size(size_x, size_y), 0., 0., cv::INTER_LINEAR);
+ }
+ } else {
+ if (patch.cols / size_x > 1.) {
+ // if we downsample use INTER_AREA interpolation
+ cv::resize(patch, patch, cv::Size(size_x / p_cell_size, size_y / p_cell_size), 0., 0., cv::INTER_AREA);
+ } else {
+ cv::resize(patch, patch, cv::Size(size_x / p_cell_size, size_y / p_cell_size), 0., 0., cv::INTER_LINEAR);
+ }
+ if (m_visual_debug && allow_debug) {
+ cv::Mat input_clone = patch.clone();
+ cv::resize(input_clone, input_clone, cv::Size(p_debug_image_size, p_debug_image_size), 0., 0.,
+ cv::INTER_LINEAR);
+
+ std::string angle_string = std::to_string(p_current_angle + angle);
+
+ cv::putText(input_clone, angle_string, cv::Point(1, input_clone.rows - 5), cv::FONT_HERSHEY_COMPLEX_SMALL,
+ 0.5, cv::Scalar(0, 255, 0), 1);
+
+ p_debug_subwindows.push_back(input_clone);
+ }
+ }
+}
+
+void KCF_Tracker::gaussian_correlation(struct ThreadCtx &vars, const ComplexMat &xf, const ComplexMat &yf, double sigma,
+ bool auto_correlation)
{
xf.sqr_norm(vars.xf_sqr_norm);
if (auto_correlation) {