#include "MultiTracker.h"
#include "Metrics.h"
#include <algorithm>
+#include "hungarian.h"
+#include "Logger.h"
using namespace suanzi;
using namespace cv;
+using namespace std;
-MultiTracker::MultiTracker(MetricsPtr m) : metrics(m)
-{
-}
+static const std::string TAG = "MultiTracker";
+static const cv::Size PREFERRED_SIZE = Size(64, 128);
+#define MaxCost 100000
-MultiTracker::~MultiTracker()
+MultiTracker::MultiTracker()
{
- trackers.clear();
-}
+ LOG_DEBUG(TAG, "init - loading model.pkl");
+ predictor = PredictorWrapper::create("./python/model.pkl");
+ predictor->dump();
+ this->descriptor = {Size(64, 128), Size(16, 16), Size(8, 8), Size(8, 8), 9};
-TrackerPtr MultiTracker::createTracker(int id)
-{
- TrackerPtr t (new Tracker(id));
- addTracker(t);
- return t;
+ std::vector<double> ff (40, 1);
+ double prob = predictor->predict(4, ff);
}
-void MultiTracker::addTracker(TrackerPtr t)
+MultiTracker::~MultiTracker()
{
- trackers.insert(t);
+ predictor.reset();
+ trackers.clear();
}
-void MultiTracker::removeTracker(TrackerPtr t)
-{
- trackers.erase(t);
-}
-void MultiTracker::initNewTrackers(cv::Mat& iamge)
+static std::vector<double> similarity(const PatchPtr p1, const PatchPtr p2)
{
+ std::vector<double> feature;
+ cv::Mat im1(PREFERRED_SIZE, p1->image_crop.type());
+ cv::Mat im2(PREFERRED_SIZE, p2->image_crop.type());
+ cv::resize(p1->image_crop, im1, im1.size());
+ cv::resize(p2->image_crop, im2, im2.size());
+ cv::Mat result;
+ cv::matchTemplate(im1, im2, result, CV_TM_CCOEFF_NORMED);
+ feature.push_back(result.at<double>(0, 0));
+ cv::matchTemplate(im1, im2, result, CV_TM_CCORR_NORMED);
+ feature.push_back(result.at<double>(0, 0));
+
+
+ vector<double>& f1_hog = p1->features.first; Mat f1_hue = p1->features.second;
+ vector<double>& f2_hog = p1->features.first; Mat f2_hue = p1->features.second;
+ feature.push_back(distance_cosine(Eigen::Map<Eigen::VectorXd>(f1_hog.data(), f1_hog.size()),
+ Eigen::Map<Eigen::VectorXd>(f2_hog.data(), f2_hog.size())));
+ feature.push_back(distance_euclidean(Eigen::Map<Eigen::VectorXd>(f1_hog.data(), f1_hog.size()),
+ Eigen::Map<Eigen::VectorXd>(f2_hog.data(), f2_hog.size())));
+ feature.push_back(compareHist(f1_hue, f2_hue, HISTCMP_CORREL));
+ feature.push_back(compareHist(f1_hue, f2_hue, HISTCMP_HELLINGER));
+
+ Detection& d1 = p1->detection;
+ Detection& d2 = p2->detection;
+
+ double center_distance = sqrt(pow((d1.center_x - d2.center_x), 2) + pow((d1.center_y - d2.center_y), 2));
+ feature.push_back(center_distance / (d1.width + d1.height + d2.width + d2.height) * 4);
+
+ //TODO
+ double iou_ratio = 0.03;
+ feature.push_back(iou_ratio);
+
+ return feature;
}
-void MultiTracker::correctTrackers(MetricsPtr m, Mat& image)
+double MultiTracker::distance(TrackerPtr tracker, const cv::Mat& image, const Detection& d)
{
+ PatchPtr patch = createPatch(image, d);
+ std::vector<double> features;
+
+ std::vector<double> ss;
+ for (auto i : tracker->patches){
+ ss = similarity(i, patch);
+ features.insert(features.end(), ss.begin(), ss.end());
+ }
+ double prob = predictor->predict(4, features);
+ return prob;
}
-
-void MultiTracker::update(unsigned int total, const Detection* d, const Mat& image)
+void MultiTracker::update(unsigned int total, const Detection* detections, const Mat& image)
{
+ int row = trackers.size();
+ int col = total;
+ Eigen::MatrixXi cost_matrix = Eigen::MatrixXi::Zero(row, col);
+ for (int i = 0; i < row; i++){
+ for (int j = 0; j < col; j++){
+ // TODO
+ cost_matrix(i, j) = distance(trackers[i], image, detections[j]);
+ }
+ }
+
+ // assignment
+ Eigen::VectorXi tracker_inds, bb_inds;
+ linear_sum_assignment(cost_matrix, tracker_inds, bb_inds);
+
+ // handle unmatched trackers
+ vector<TrackerPtr> unmatched_trackers;
+ for (int i = 0; i < row; i++){
+ if (!(tracker_inds.array() == i).any()){
+ unmatched_trackers.push_back(trackers[i]);
+ }
+ }
+ for (auto t : unmatched_trackers){
+ t->updateState(image);
+ }
+
+ // handle unmatched detections
+ vector<int> unmatched_detection;
+ for(int j = 0; j < col; j++){
+ if (!(bb_inds.array() == j).any()){
+ unmatched_detection.push_back(j);
+ }
+ }
+ // create new trackers for new detections
+ for (auto i : unmatched_detection){
+ TrackerPtr t (new Tracker(image));
+ this->trackers.push_back(t);
+ }
- // correct_trackers
-
-
- //
-
-
-
-
-
-
+ Detection dd;
+ PatchPtr pp = createPatch(image, dd);
+}
- // Delete long lost trackers;
-// for (auto& t : trackers){
-// if (t->status == TrackerStatus::Delete)
-// trackers.erase(t);
-// }
-//
- // Update trackers using kalman filter
-// for(auto& t: trackers){
-// //t.bb_ltrb =
-// }
-//
- // associate trackers with detections
-// correctTrackers(this->metric, image);
+// Get image crop from input image within given bounding box - Detecinon
+static cv::Mat image_crop(const cv::Mat& image, const Detection& bb)
+{
+ // RECT
+ // TODO;
+ return image.clone();
+}
- // create new trackers for new detections
+PatchPtr MultiTracker::createPatch(const Mat& image, const Detection& detect)
+{
+ PatchPtr patch(new Patch());
+
+ // calculate hog descriptors, size is 3780
+ Mat im, im2;
+ im = image_crop(image, detect);
+ resize(im, im2, PREFERRED_SIZE);
+ vector<float> feature_hog;
+ this->descriptor.compute(im2, feature_hog);
+
+ // calculate histogram, size is (64 x 45)
+ Mat hsv, hist;
+ cvtColor(im, hsv, COLOR_BGR2HSV);
+ int channels[] = {0, 1};
+ int histSize[] = {45, 64};
+ float hranges[] = {0, 180};
+ float sranges[] = {0, 256};
+ const float* ranges[] = {hranges, sranges};
+ calcHist(&hsv, 1, channels, Mat(), hist, 2, histSize, ranges, true, false);
+ Size sm = hist.size();
+
+ patch->image_crop = im.clone();
+ patch->detection = detect;
+ std::vector<double> feature_hog_double (feature_hog.begin(), feature_hog.end()); // convert to double
+ patch->features = std::make_pair(feature_hog_double, hist);
+ return patch;
}
projects / trackerpp.git / blobdiff