-
Notifications
You must be signed in to change notification settings - Fork 1
/
sort.py
362 lines (302 loc) · 13.6 KB
/
sort.py
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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
from __future__ import print_function
import os
import numpy as np
import matplotlib
matplotlib.use('TkAgg')
import matplotlib.pyplot as plt
import matplotlib.patches as patches
from skimage import io
from random import randint
import glob
import time
import argparse
from filterpy.kalman import KalmanFilter
def get_color():
# r = randint(0, 255)
# g = randint(0, 255)
# b = randint(0, 255)
color = (randint(0, 255), randint(0, 255), randint(0, 255))
return color
def linear_assignment(cost_matrix):
try:
import lap #linear assignment problem solver
_, x, y = lap.lapjv(cost_matrix, extend_cost = True)
return np.array([[y[i],i] for i in x if i>=0])
except ImportError:
from scipy.optimize import linear_sum_assignment
x,y = linear_sum_assignment(cost_matrix)
return np.array(list(zip(x,y)))
"""From SORT: Computes IOU between two boxes in the form [x1,y1,x2,y2]"""
def iou_batch(bb_test, bb_gt):
bb_gt = np.expand_dims(bb_gt, 0)
bb_test = np.expand_dims(bb_test, 1)
xx1 = np.maximum(bb_test[...,0], bb_gt[..., 0])
yy1 = np.maximum(bb_test[..., 1], bb_gt[..., 1])
xx2 = np.minimum(bb_test[..., 2], bb_gt[..., 2])
yy2 = np.minimum(bb_test[..., 3], bb_gt[..., 3])
w = np.maximum(0., xx2 - xx1)
h = np.maximum(0., yy2 - yy1)
wh = w * h
o = wh / ((bb_test[..., 2] - bb_test[..., 0]) * (bb_test[..., 3] - bb_test[..., 1])
+ (bb_gt[..., 2] - bb_gt[..., 0]) * (bb_gt[..., 3] - bb_gt[..., 1]) - wh)
return(o)
"""Takes a bounding box in the form [x1,y1,x2,y2] and returns z in the form [x,y,s,r] where x,y is the center of the box and s is the scale/area and r is the aspect ratio"""
def convert_bbox_to_z(bbox):
w = bbox[2] - bbox[0]
h = bbox[3] - bbox[1]
x = bbox[0] + w/2.
y = bbox[1] + h/2.
s = w * h
#scale is just area
r = w / float(h)
return np.array([x, y, s, r]).reshape((4, 1))
"""Takes a bounding box in the centre form [x,y,s,r] and returns it in the form
[x1,y1,x2,y2] where x1,y1 is the top left and x2,y2 is the bottom right"""
def convert_x_to_bbox(x, score=None):
w = np.sqrt(x[2] * x[3])
h = x[2] / w
if(score==None):
return np.array([x[0]-w/2.,x[1]-h/2.,x[0]+w/2.,x[1]+h/2.]).reshape((1,4))
else:
return np.array([x[0]-w/2.,x[1]-h/2.,x[0]+w/2.,x[1]+h/2.,score]).reshape((1,5))
"""This class represents the internal state of individual tracked objects observed as bbox."""
class KalmanBoxTracker(object):
count = 0
def __init__(self, bbox):
"""
Initialize a tracker using initial bounding box
Parameter 'bbox' must have 'detected class' int number at the -1 position.
"""
self.kf = KalmanFilter(dim_x=7, dim_z=4)
self.kf.F = np.array([[1,0,0,0,1,0,0],[0,1,0,0,0,1,0],[0,0,1,0,0,0,1],[0,0,0,1,0,0,0],[0,0,0,0,1,0,0],[0,0,0,0,0,1,0],[0,0,0,0,0,0,1]])
self.kf.H = np.array([[1,0,0,0,0,0,0],[0,1,0,0,0,0,0],[0,0,1,0,0,0,0],[0,0,0,1,0,0,0]])
self.kf.R[2:,2:] *= 10. # R: Covariance matrix of measurement noise (set to high for noisy inputs -> more 'inertia' of boxes')
self.kf.P[4:,4:] *= 1000. #give high uncertainty to the unobservable initial velocities
self.kf.P *= 10.
self.kf.Q[-1,-1] *= 0.5 # Q: Covariance matrix of process noise (set to high for erratically moving things)
self.kf.Q[4:,4:] *= 0.5
self.kf.x[:4] = convert_bbox_to_z(bbox) # STATE VECTOR
self.time_since_update = 0
self.id = KalmanBoxTracker.count
KalmanBoxTracker.count += 1
self.history = []
self.hits = 0
self.hit_streak = 0
self.age = 0
self.centroidarr = []
CX = (bbox[0]+bbox[2])//2
CY = (bbox[1]+bbox[3])//2
self.centroidarr.append((CX,CY))
#keep yolov5 detected class information
self.detclass = bbox[5]
def update(self, bbox):
"""
Updates the state vector with observed bbox
"""
self.time_since_update = 0
self.history = []
self.hits += 1
self.hit_streak += 1
self.kf.update(convert_bbox_to_z(bbox))
self.detclass = bbox[5]
CX = (bbox[0]+bbox[2])//2
CY = (bbox[1]+bbox[3])//2
self.centroidarr.append((CX,CY))
def predict(self):
"""
Advances the state vector and returns the predicted bounding box estimate
"""
if((self.kf.x[6]+self.kf.x[2])<=0):
self.kf.x[6] *= 0.0
self.kf.predict()
self.age += 1
if(self.time_since_update>0):
self.hit_streak = 0
self.time_since_update += 1
self.history.append(convert_x_to_bbox(self.kf.x))
# bbox=self.history[-1]
# CX = (bbox[0]+bbox[2])/2
# CY = (bbox[1]+bbox[3])/2
# self.centroidarr.append((CX,CY))
return self.history[-1]
def get_state(self):
"""
Returns the current bounding box estimate
# test
arr1 = np.array([[1,2,3,4]])
arr2 = np.array([0])
arr3 = np.expand_dims(arr2, 0)
np.concatenate((arr1,arr3), axis=1)
"""
arr_detclass = np.expand_dims(np.array([self.detclass]), 0)
arr_u_dot = np.expand_dims(self.kf.x[4],0)
arr_v_dot = np.expand_dims(self.kf.x[5],0)
arr_s_dot = np.expand_dims(self.kf.x[6],0)
return np.concatenate((convert_x_to_bbox(self.kf.x), arr_detclass, arr_u_dot, arr_v_dot, arr_s_dot), axis=1)
def associate_detections_to_trackers(detections, trackers, iou_threshold = 0.3):
"""
Assigns detections to tracked object (both represented as bounding boxes)
Returns 3 lists of
1. matches,
2. unmatched_detections
3. unmatched_trackers
"""
if(len(trackers)==0):
return np.empty((0,2),dtype=int), np.arange(len(detections)), np.empty((0,5),dtype=int)
iou_matrix = iou_batch(detections, trackers)
if min(iou_matrix.shape) > 0:
a = (iou_matrix > iou_threshold).astype(np.int32)
if a.sum(1).max() == 1 and a.sum(0).max() ==1:
matched_indices = np.stack(np.where(a), axis=1)
else:
matched_indices = linear_assignment(-iou_matrix)
else:
matched_indices = np.empty(shape=(0,2))
unmatched_detections = []
for d, det in enumerate(detections):
if(d not in matched_indices[:,0]):
unmatched_detections.append(d)
unmatched_trackers = []
for t, trk in enumerate(trackers):
if(t not in matched_indices[:,1]):
unmatched_trackers.append(t)
#filter out matched with low IOU
matches = []
for m in matched_indices:
if(iou_matrix[m[0], m[1]]<iou_threshold):
unmatched_detections.append(m[0])
unmatched_trackers.append(m[1])
else:
matches.append(m.reshape(1,2))
if(len(matches)==0):
matches = np.empty((0,2), dtype=int)
else:
matches = np.concatenate(matches, axis=0)
return matches, np.array(unmatched_detections), np.array(unmatched_trackers)
class Sort(object):
def __init__(self, max_age=1, min_hits=3, iou_threshold=0.3):
"""
Parameters for SORT
"""
self.max_age = max_age
self.min_hits = min_hits
self.iou_threshold = iou_threshold
self.trackers = []
self.frame_count = 0
self.color_list = []
def getTrackers(self,):
return self.trackers
def update(self, dets= np.empty((0,6)), unique_color = False):
"""
Parameters:
'dets' - a numpy array of detection in the format [[x1, y1, x2, y2, score], [x1,y1,x2,y2,score],...]
Ensure to call this method even frame has no detections. (pass np.empty((0,5)))
Returns a similar array, where the last column is object ID (replacing confidence score)
NOTE: The number of objects returned may differ from the number of objects provided.
"""
self.frame_count += 1
# Get predicted locations from existing trackers
trks = np.zeros((len(self.trackers), 6))
to_del = []
ret = []
for t, trk in enumerate(trks):
pos = self.trackers[t].predict()[0]
trk[:] = [pos[0], pos[1], pos[2], pos[3], 0, 0]
if np.any(np.isnan(pos)):
to_del.append(t)
trks = np.ma.compress_rows(np.ma.masked_invalid(trks))
for t in reversed(to_del):
self.trackers.pop(t)
if unique_color:
self.color_list.pop(t)
matched, unmatched_dets, unmatched_trks = associate_detections_to_trackers(dets, trks, self.iou_threshold)
# Update matched trackers with assigned detections
for m in matched:
self.trackers[m[1]].update(dets[m[0], :])
# Create and initialize new trackers for unmatched detections
for i in unmatched_dets:
trk = KalmanBoxTracker(np.hstack((dets[i,:], np.array([0]))))
self.trackers.append(trk)
if unique_color:
self.color_list.append(get_color())
i = len(self.trackers)
for trk in reversed(self.trackers):
d = trk.get_state()[0]
if (trk.time_since_update < 1) and (trk.hit_streak >= self.min_hits or self.frame_count <= self.min_hits):
ret.append(np.concatenate((d, [trk.id+1])).reshape(1,-1)) #+1'd because MOT benchmark requires positive value
i -= 1
#remove dead tracklet
if(trk.time_since_update >self.max_age):
self.trackers.pop(i)
if unique_color:
self.color_list.pop(i)
if(len(ret) > 0):
return np.concatenate(ret)
return np.empty((0,6))
def parse_args():
"""Parse input arguments."""
parser = argparse.ArgumentParser(description='SORT demo')
parser.add_argument('--display', dest='display', help='Display online tracker output (slow) [False]',action='store_true')
parser.add_argument("--seq_path", help="Path to detections.", type=str, default='data')
parser.add_argument("--phase", help="Subdirectory in seq_path.", type=str, default='train')
parser.add_argument("--max_age",
help="Maximum number of frames to keep alive a track without associated detections.",
type=int, default=1)
parser.add_argument("--min_hits",
help="Minimum number of associated detections before track is initialised.",
type=int, default=3)
parser.add_argument("--iou_threshold", help="Minimum IOU for match.", type=float, default=0.3)
args = parser.parse_args()
return args
if __name__ == '__main__':
# all train
args = parse_args()
display = args.display
phase = args.phase
total_time = 0.0
total_frames = 0
colours = np.random.rand(32, 3) #used only for display
if(display):
if not os.path.exists('mot_benchmark'):
print('\n\tERROR: mot_benchmark link not found!\n\n Create a symbolic link to the MOT benchmark\n (https://motchallenge.net/data/2D_MOT_2015/#download). E.g.:\n\n $ ln -s /path/to/MOT2015_challenge/2DMOT2015 mot_benchmark\n\n')
exit()
plt.ion()
fig = plt.figure()
ax1 = fig.add_subplot(111, aspect='equal')
if not os.path.exists('output'):
os.makedirs('output')
pattern = os.path.join(args.seq_path, phase, '*', 'det', 'det.txt')
for seq_dets_fn in glob.glob(pattern):
mot_tracker = Sort(max_age=args.max_age,
min_hits=args.min_hits,
iou_threshold=args.iou_threshold) #create instance of the SORT tracker
seq_dets = np.loadtxt(seq_dets_fn, delimiter=',')
seq = seq_dets_fn[pattern.find('*'):].split(os.path.sep)[0]
with open(os.path.join('output', '%s.txt'%(seq)),'w') as out_file:
print("Processing %s."%(seq))
for frame in range(int(seq_dets[:,0].max())):
frame += 1 #detection and frame numbers begin at 1
dets = seq_dets[seq_dets[:, 0]==frame, 2:7]
dets[:, 2:4] += dets[:, 0:2] #convert to [x1,y1,w,h] to [x1,y1,x2,y2]
total_frames += 1
if(display):
fn = os.path.join('mot_benchmark', phase, seq, 'img1', '%06d.jpg'%(frame))
im =io.imread(fn)
ax1.imshow(im)
plt.title(seq + ' Tracked Targets')
start_time = time.time()
trackers = mot_tracker.update(dets)
cycle_time = time.time() - start_time
total_time += cycle_time
for d in trackers:
print('%d,%d,%.2f,%.2f,%.2f,%.2f,1,-1,-1,-1'%(frame,d[4],d[0],d[1],d[2]-d[0],d[3]-d[1]),file=out_file)
if(display):
d = d.astype(np.int32)
ax1.add_patch(patches.Rectangle((d[0],d[1]),d[2]-d[0],d[3]-d[1],fill=False,lw=3,ec=colours[d[4]%32,:]))
if(display):
fig.canvas.flush_events()
plt.draw()
ax1.cla()
print("Total Tracking took: %.3f seconds for %d frames or %.1f FPS" % (total_time, total_frames, total_frames / total_time))
if(display):
print("Note: to get real runtime results run without the option: --display")