1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239#include "DenseTrack.h"
#include "Initialize.h"
#include "Descriptors.h"
#include "OpticalFlow.h"
#include <time.h>
using namespace cv;
int show_track = 0; // set show_track = 1, if you want to visualize the trajectories
int main(int argc, char** argv)
{
VideoCapture capture;
char* video = argv[1];
int flag = arg_parse(argc, argv);
capture.open(video);
if(!capture.isOpened()) {
fprintf(stderr, "Could not initialize capturing..\n");
return -1;
}
int frame_num = 0;
TrackInfo trackInfo;
DescInfo hogInfo, hofInfo, mbhInfo;
InitTrackInfo(&trackInfo, track_length, init_gap);
InitDescInfo(&hogInfo, 8, false, patch_size, nxy_cell, nt_cell);
InitDescInfo(&hofInfo, 9, true, patch_size, nxy_cell, nt_cell);
InitDescInfo(&mbhInfo, 8, false, patch_size, nxy_cell, nt_cell);
SeqInfo seqInfo;
InitSeqInfo(&seqInfo, video);
if(flag)
seqInfo.length = end_frame - start_frame + 1;
// fprintf(stderr, "video size, length: %d, width: %d, height: %d\n", seqInfo.length, seqInfo.width, seqInfo.height);
if(show_track == 1)
namedWindow("DenseTrack", 0);
Mat image, prev_grey, grey;
std::vector<float> fscales(0);
std::vector<Size> sizes(0);
std::vector<Mat> prev_grey_pyr(0), grey_pyr(0), flow_pyr(0);
std::vector<Mat> prev_poly_pyr(0), poly_pyr(0); // for optical flow
std::vector<std::list<Track> > xyScaleTracks;
int init_counter = 0; // indicate when to detect new feature points
while(true) {
Mat frame;
int i, j, c;
// get a new frame
capture >> frame;
if(frame.empty())
break;
if(frame_num < start_frame || frame_num > end_frame) {
frame_num++;
continue;
}
if(frame_num == start_frame) {
image.create(frame.size(), CV_8UC3);
grey.create(frame.size(), CV_8UC1);
prev_grey.create(frame.size(), CV_8UC1);
InitPry(frame, fscales, sizes);
BuildPry(sizes, CV_8UC1, prev_grey_pyr);
BuildPry(sizes, CV_8UC1, grey_pyr);
BuildPry(sizes, CV_32FC2, flow_pyr);
BuildPry(sizes, CV_32FC(5), prev_poly_pyr);
BuildPry(sizes, CV_32FC(5), poly_pyr);
xyScaleTracks.resize(scale_num);
frame.copyTo(image);
cvtColor(image, prev_grey, CV_BGR2GRAY);
for(int iScale = 0; iScale < scale_num; iScale++) {
if(iScale == 0)
prev_grey.copyTo(prev_grey_pyr[0]);
else
resize(prev_grey_pyr[iScale-1], prev_grey_pyr[iScale], prev_grey_pyr[iScale].size(), 0, 0, INTER_LINEAR);
// dense sampling feature points
std::vector<Point2f> points(0);
DenseSample(prev_grey_pyr[iScale], points, quality, min_distance);
// save the feature points
std::list<Track>& tracks = xyScaleTracks[iScale];
for(i = 0; i < points.size(); i++)
tracks.push_back(Track(points[i], trackInfo, hogInfo, hofInfo, mbhInfo));
}
// compute polynomial expansion
my::FarnebackPolyExpPyr(prev_grey, prev_poly_pyr, fscales, 7, 1.5);
frame_num++;
continue;
}
init_counter++;
frame.copyTo(image);
cvtColor(image, grey, CV_BGR2GRAY);
// compute optical flow for all scales once
my::FarnebackPolyExpPyr(grey, poly_pyr, fscales, 7, 1.5);
my::calcOpticalFlowFarneback(prev_poly_pyr, poly_pyr, flow_pyr, 10, 2);
for(int iScale = 0; iScale < scale_num; iScale++) {
if(iScale == 0)
grey.copyTo(grey_pyr[0]);
else
resize(grey_pyr[iScale-1], grey_pyr[iScale], grey_pyr[iScale].size(), 0, 0, INTER_LINEAR);
int width = grey_pyr[iScale].cols;
int height = grey_pyr[iScale].rows;
// compute the integral histograms
DescMat* hogMat = InitDescMat(height+1, width+1, hogInfo.nBins);
HogComp(prev_grey_pyr[iScale], hogMat->desc, hogInfo);
DescMat* hofMat = InitDescMat(height+1, width+1, hofInfo.nBins);
HofComp(flow_pyr[iScale], hofMat->desc, hofInfo);
DescMat* mbhMatX = InitDescMat(height+1, width+1, mbhInfo.nBins);
DescMat* mbhMatY = InitDescMat(height+1, width+1, mbhInfo.nBins);
MbhComp(flow_pyr[iScale], mbhMatX->desc, mbhMatY->desc, mbhInfo);
// track feature points in each scale separately
std::list<Track>& tracks = xyScaleTracks[iScale];
for (std::list<Track>::iterator iTrack = tracks.begin(); iTrack != tracks.end();) {
int index = iTrack->index;
Point2f prev_point = iTrack->point[index];
int x = std::min<int>(std::max<int>(cvRound(prev_point.x), 0), width-1);
int y = std::min<int>(std::max<int>(cvRound(prev_point.y), 0), height-1);
Point2f point;
point.x = prev_point.x + flow_pyr[iScale].ptr<float>(y)[2*x];
point.y = prev_point.y + flow_pyr[iScale].ptr<float>(y)[2*x+1];
if(point.x <= 0 || point.x >= width || point.y <= 0 || point.y >= height) {
iTrack = tracks.erase(iTrack);
continue;
}
// get the descriptors for the feature point
RectInfo rect;
GetRect(prev_point, rect, width, height, hogInfo);
GetDesc(hogMat, rect, hogInfo, iTrack->hog, index);
GetDesc(hofMat, rect, hofInfo, iTrack->hof, index);
GetDesc(mbhMatX, rect, mbhInfo, iTrack->mbhX, index);
GetDesc(mbhMatY, rect, mbhInfo, iTrack->mbhY, index);
iTrack->addPoint(point);
// draw the trajectories at the first scale
if(show_track == 1 && iScale == 0)
DrawTrack(iTrack->point, iTrack->index, fscales[iScale], image);
// if the trajectory achieves the maximal length
if(iTrack->index >= trackInfo.length) {
std::vector<Point2f> trajectory(trackInfo.length+1);
for(int i = 0; i <= trackInfo.length; ++i)
trajectory[i] = iTrack->point[i]*fscales[iScale];
float mean_x(0), mean_y(0), var_x(0), var_y(0), length(0);
if(IsValid(trajectory, mean_x, mean_y, var_x, var_y, length)) {
printf("%d\t%f\t%f\t%f\t%f\t%f\t%f\t", frame_num, mean_x, mean_y, var_x, var_y, length, fscales[iScale]);
// for spatio-temporal pyramid
printf("%f\t", std::min<float>(std::max<float>(mean_x/float(seqInfo.width), 0), 0.999));
printf("%f\t", std::min<float>(std::max<float>(mean_y/float(seqInfo.height), 0), 0.999));
printf("%f\t", std::min<float>(std::max<float>((frame_num - trackInfo.length/2.0 - start_frame)/float(seqInfo.length), 0), 0.999));
// output the trajectory
for (int i = 0; i < trackInfo.length; ++i)
printf("%f\t%f\t", trajectory[i].x,trajectory[i].y);
PrintDesc(iTrack->hog, hogInfo, trackInfo);
PrintDesc(iTrack->hof, hofInfo, trackInfo);
PrintDesc(iTrack->mbhX, mbhInfo, trackInfo);
PrintDesc(iTrack->mbhY, mbhInfo, trackInfo);
printf("\n");
}
iTrack = tracks.erase(iTrack);
continue;
}
++iTrack;
}
ReleDescMat(hogMat);
ReleDescMat(hofMat);
ReleDescMat(mbhMatX);
ReleDescMat(mbhMatY);
if(init_counter != trackInfo.gap)
continue;
// detect new feature points every initGap frames
std::vector<Point2f> points(0);
for(std::list<Track>::iterator iTrack = tracks.begin(); iTrack != tracks.end(); iTrack++)
points.push_back(iTrack->point[iTrack->index]);
DenseSample(grey_pyr[iScale], points, quality, min_distance);
// save the new feature points
for(i = 0; i < points.size(); i++)
tracks.push_back(Track(points[i], trackInfo, hogInfo, hofInfo, mbhInfo));
}
init_counter = 0;
grey.copyTo(prev_grey);
for(i = 0; i < scale_num; i++) {
grey_pyr[i].copyTo(prev_grey_pyr[i]);
poly_pyr[i].copyTo(prev_poly_pyr[i]);
}
frame_num++;
if( show_track == 1 ) {
imshow( "DenseTrack", image);
c = cvWaitKey(3);
if((char)c == 27) break;
}
}
if( show_track == 1 )
destroyWindow("DenseTrack");
return 0;
}