TRACE("");
// obtain a sub-window for training
- // TODO: Move Mats outside from here
- MatScaleFeats patch_feats(1, p_num_of_feats, feature_size);
- DEBUG_PRINT(patch_feats);
- MatScaleFeats temp(1, p_num_of_feats, feature_size);
- get_features(input_rgb, input_gray, p_current_center.x, p_current_center.y,
+ get_features(input_rgb, input_gray, nullptr, p_current_center.x, p_current_center.y,
p_windows_size.width, p_windows_size.height,
- p_current_scale).copyTo(patch_feats.scale(0));
- DEBUG_PRINT(patch_feats);
- fft.forward_window(patch_feats, p_xf, temp);
- DEBUG_PRINTM(p_xf);
- p_model_xf = p_model_xf * (1. - interp_factor) + p_xf * interp_factor;
- DEBUG_PRINTM(p_model_xf);
-
- ComplexMat alphaf_num, alphaf_den;
+ p_current_scale).copyTo(model->patch_feats.scale(0));
+ DEBUG_PRINT(model->patch_feats);
+ fft.forward_window(model->patch_feats, model->xf, model->temp);
+ DEBUG_PRINTM(model->xf);
+ model->model_xf = model->model_xf * (1. - interp_factor) + model->xf * interp_factor;
+ DEBUG_PRINTM(model->model_xf);
if (m_use_linearkernel) {
- ComplexMat xfconj = p_xf.conj();
- alphaf_num = xfconj.mul(p_yf);
- alphaf_den = (p_xf * xfconj);
+ ComplexMat xfconj = model->xf.conj();
+ model->model_alphaf_num = xfconj.mul(model->yf);
+ model->model_alphaf_den = (model->xf * xfconj);
} else {
// Kernel Ridge Regression, calculate alphas (in Fourier domain)
cv::Size sz(Fft::freq_size(feature_size));
ComplexMat kf(sz.height, sz.width, 1);
- (*gaussian_correlation)(kf, p_model_xf, p_model_xf, p_kernel_sigma, true, *this);
+ (*gaussian_correlation)(kf, model->model_xf, model->model_xf, p_kernel_sigma, true, *this);
DEBUG_PRINTM(kf);
- p_model_alphaf_num = p_yf * kf;
- p_model_alphaf_den = kf * (kf + p_lambda);
+ model->model_alphaf_num = model->yf * kf;
+ model->model_alphaf_den = kf * (kf + p_lambda);
}
- p_model_alphaf = p_model_alphaf_num / p_model_alphaf_den;
- DEBUG_PRINTM(p_model_alphaf);
+ model->model_alphaf = model->model_alphaf_num / model->model_alphaf_den;
+ DEBUG_PRINTM(model->model_alphaf);
// p_model_alphaf = p_yf / (kf + p_lambda); //equation for fast training
}
feature_size = fit_size / p_cell_size;
p_scales.clear();
- for (int i = -int(p_num_scales) / 2; i <= int(p_num_scales) / 2; ++i)
+ for (int i = -int(p_num_scales - 1) / 2; i <= int(p_num_scales) / 2; ++i)
p_scales.push_back(std::pow(p_scale_step, i));
-#ifdef CUFFT
- if (Fft::freq_size(feature_size).area() > 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: " << fit_size
- << " which is " << fit_size.area() << " pixels. " << std::endl;
- std::exit(EXIT_FAILURE);
- }
+ p_angles.clear();
+ for (int i = -int(p_num_angles - 1) / 2; i <= int(p_num_angles) / 2; ++i)
+ p_angles.push_back(i * p_angle_step);
+#ifdef CUFFT
if (m_use_linearkernel) {
std::cerr << "cuFFT supports only Gaussian kernel." << std::endl;
std::exit(EXIT_FAILURE);
}
#endif
- cv::Size csz = Fft::freq_size(feature_size);
- p_model_xf.create(csz.height, csz.width, p_num_of_feats);
- p_yf.create(csz.height, csz.width, 1);
- p_xf.create(csz.height, csz.width, p_num_of_feats);
+ model.reset(new Model(feature_size, p_num_of_feats));
#ifndef BIG_BATCH
for (auto scale: p_scales)
d.threadctxs.emplace_back(feature_size, p_num_of_feats, p_num_scales);
#endif
- gaussian_correlation.reset(new GaussianCorrelation(1, feature_size));
+ gaussian_correlation.reset(new GaussianCorrelation(1, p_num_of_feats, feature_size));
p_current_center = p_init_pose.center();
p_current_scale = 1.;
// window weights, i.e. labels
MatScales gsl(1, feature_size);
gaussian_shaped_labels(p_output_sigma, feature_size.width, feature_size.height).copyTo(gsl.plane(0));
- fft.forward(gsl, p_yf);
- DEBUG_PRINTM(p_yf);
+ fft.forward(gsl, model->yf);
+ DEBUG_PRINTM(model->yf);
// train initial model
train(input_rgb, input_gray, 1.0);
tmp.cy = p_current_center.y;
tmp.w = p_init_pose.w * p_current_scale;
tmp.h = p_init_pose.h * p_current_scale;
+ tmp.a = 0;
if (p_resize_image)
tmp.scale(1 / p_downscale_factor);
assert(max_idx < IF_BIG_BATCH(p_scales.size(), d.threadctxs.size()));
if (m_visual_debug) {
- int w = 100; //feature_size.width;
- int h = 100; //feature_size.height;
- cv::Mat all_responses(h * p_num_scales, w * p_num_angles,
- d.threadctxs[0].response.type(), cv::Scalar::all(0));
+ const bool rgb = true;
+ int type = rgb ? d.threadctxs[0].dbg_patch[0].type() : d.threadctxs[0].response.type();
+ int w = true ? 100 : (rgb ? fit_size.width : feature_size.width);
+ int h = true ? 100 : (rgb ? fit_size.height : feature_size.height);
+ cv::Mat all_responses((h + 1) * p_num_scales - 1,
+ (w + 1) * p_num_angles - 1, 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 tmp = d.threadctxs[IF_BIG_BATCH(0, p_num_angles * i + j)].response.plane(IF_BIG_BATCH(p_num_angles * i + j, 0));
- tmp = circshift(tmp, -tmp.cols/2, -tmp.rows/2);
+ cv::Mat tmp;
+ if (rgb) {
+ tmp = d.threadctxs[IF_BIG_BATCH(0, p_num_angles * i + j)].dbg_patch[IF_BIG_BATCH(p_num_angles * i + j, 0)];
+ } else {
+ tmp = d.threadctxs[IF_BIG_BATCH(0, p_num_angles * i + j)].response.plane(IF_BIG_BATCH(p_num_angles * i + j, 0));
+ tmp = circshift(tmp, -tmp.cols/2, -tmp.rows/2);
+ }
cv::resize(tmp, tmp, cv::Size(w, h));
- cv::Mat resp_roi(all_responses, cv::Rect(j * w, i * h, w, h));
+ cv::Mat resp_roi(all_responses, cv::Rect(j * (w+1), i * (h+1), w, h));
tmp.copyTo(resp_roi);
}
}
- cv::namedWindow("All responses", CV_WINDOW_AUTOSIZE);
- cv::imshow("All responses", all_responses);
+ cv::namedWindow("KCF visual debug", CV_WINDOW_AUTOSIZE);
+ cv::imshow("KCF visual debug", all_responses);
}
cv::Point2i &max_response_pt = IF_BIG_BATCH(d.threadctxs[0].max[max_idx].loc, d.threadctxs[max_idx].max.loc);
BIG_BATCH_OMP_PARALLEL_FOR
for (uint i = 0; i < IF_BIG_BATCH(kcf.p_num_scales, 1); ++i)
{
- kcf.get_features(input_rgb, input_gray, kcf.p_current_center.x, kcf.p_current_center.y,
+ kcf.get_features(input_rgb, input_gray, &dbg_patch[i],
+ kcf.p_current_center.x, kcf.p_current_center.y,
kcf.p_windows_size.width, kcf.p_windows_size.height,
kcf.p_current_scale * IF_BIG_BATCH(kcf.p_scales[i], scale))
.copyTo(patch_feats.scale(i));
DEBUG_PRINTM(zf);
if (kcf.m_use_linearkernel) {
- kzf = zf.mul(kcf.p_model_alphaf).sum_over_channels();
+ kzf = zf.mul(kcf.model->model_alphaf).sum_over_channels();
} else {
- gaussian_correlation(kzf, zf, kcf.p_model_xf, kcf.p_kernel_sigma, false, kcf);
+ gaussian_correlation(kzf, zf, kcf.model->model_xf, kcf.p_kernel_sigma, false, kcf);
DEBUG_PRINTM(kzf);
- kzf = kzf.mul(kcf.p_model_alphaf);
+ kzf = kzf.mul(kcf.model->model_alphaf);
}
kcf.fft.inverse(kzf, response);
// ****************************************************************************
-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) const
+cv::Mat KCF_Tracker::get_features(cv::Mat &input_rgb, cv::Mat &input_gray, cv::Mat *dbg_patch,
+ int cx, int cy, int size_x, int size_y, double scale) const
{
cv::Size scaled = cv::Size(floor(size_x * scale), floor(size_y * scale));
cv::Mat patch_gray = get_subwindow(input_gray, cx, cy, scaled.width, scaled.height);
cv::Mat patch_rgb = get_subwindow(input_rgb, cx, cy, scaled.width, scaled.height);
+ if (dbg_patch)
+ patch_rgb.copyTo(*dbg_patch);
+
// resize to default size
if (scaled.area() > fit_size.area()) {
// if we downsample use INTER_AREA interpolation
double sigma, bool auto_correlation, const KCF_Tracker &kcf)
{
TRACE("");
+ DEBUG_PRINTM(xf);
+ DEBUG_PRINT(xf_sqr_norm.num_elem);
xf.sqr_norm(xf_sqr_norm);
+ for (uint s = 0; s < xf.n_scales; ++s)
+ DEBUG_PRINT(xf_sqr_norm[s]);
if (auto_correlation) {
yf_sqr_norm = xf_sqr_norm;
} else {
+ DEBUG_PRINTM(yf);
yf.sqr_norm(yf_sqr_norm);
}
+ for (uint s = 0; s < yf.n_scales; ++s)
+ DEBUG_PRINTM(yf_sqr_norm[s]);
xyf = auto_correlation ? xf.sqr_mag() : xf * yf.conj(); // xf.muln(yf.conj());
DEBUG_PRINTM(xyf);
DEBUG_PRINTM(xyf_sum);
kcf.fft.inverse(xyf_sum, ifft_res);
DEBUG_PRINTM(ifft_res);
-#ifdef CUFFT
- // FIXME
- cuda_gaussian_correlation(ifft_res.deviceMem(), k.deviceMem(), xf_sqr_norm.deviceMem(),
- auto_correlation ? xf_sqr_norm.deviceMem() : yf_sqr_norm.deviceMem(), sigma,
- xf.n_channels, xf.n_scales, kcf.feature_size.height, kcf.feature_size.width);
-#else
float numel_xf_inv = 1.f / (xf.cols * xf.rows * (xf.channels() / xf.n_scales));
for (uint i = 0; i < xf.n_scales; ++i) {
* numel_xf_inv, 0), plane);
DEBUG_PRINTM(plane);
}
-#endif
+
kcf.fft.forward(ifft_res, result);
}
projects / hercules2020 / kcf.git / blobdiff