/
clip_object_tracker.py
262 lines (218 loc) · 10.7 KB
/
clip_object_tracker.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
import argparse
import time
from pathlib import Path
import clip
import cv2
import torch
import torch.backends.cudnn as cudnn
from numpy import random
import numpy as np
from models.experimental import attempt_load
from utils.datasets import LoadStreams, LoadImages
from utils.general import xyxy2xywh, \
strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box
from utils.torch_utils import select_device, time_synchronized
from utils.roboflow import predict_image
# deep sort imports
from deep_sort import preprocessing, nn_matching
from deep_sort.detection import Detection
from deep_sort.tracker import Tracker
from tools import generate_clip_detections as gdet
def update_tracks(tracker, frame_count, save_txt, txt_path, save_img, view_img, colors, im0, gn):
if len(tracker.tracks):
print("[Tracks]")
for track in tracker.tracks:
if not track.is_confirmed() or track.time_since_update > 1:
continue
xyxy = track.to_tlbr()
class_num = track.class_num
bbox = xyxy
if opt.info:
print("Tracker ID: {}, Class: {}, BBox Coords (xmin, ymin, xmax, ymax): {}".format(
str(track.track_id), class_num, (int(bbox[0]), int(bbox[1]), int(bbox[2]), int(bbox[3]))))
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)
) / gn).view(-1).tolist() # normalized xywh
with open(txt_path + '.txt', 'a') as f:
f.write('frame: {}; track: {}; class: {}; bbox: {};\n'.format(frame_count, track.track_id, class_num,
*xywh))
if save_img or view_img: # Add bbox to image
label = f'{class_num} {track.track_id}'
plot_one_box(xyxy, im0, label=label,
color=colors[len(class_num)], line_thickness=3)
def save_image(save_img, dataset, save_path, im0, vid_path, vid_writer, vid_cap):
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video'
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
fourcc = 'mp4v' # output video codec
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
vid_writer.write(im0)
def detect(save_img=False):
nms_max_overlap = opt.nms_max_overlap
max_cosine_distance = opt.max_cosine_distance
nn_budget = opt.nn_budget
# initialize deep sort
model_filename = "ViT-B/32"
device = "cuda" if torch.cuda.is_available() else "cpu"
model, transform = clip.load(model_filename, device=device)
encoder = gdet.create_box_encoder(model, transform, batch_size=1, device=device)
# calculate cosine distance metric
metric = nn_matching.NearestNeighborDistanceMetric(
"cosine", max_cosine_distance, nn_budget)
# initialize tracker
tracker = Tracker(metric)
source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://'))
# Directories
save_dir = Path(increment_path(Path(opt.project) / opt.name,
exist_ok=opt.exist_ok)) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True,
exist_ok=True) # make dir
# Initialize
set_logging()
device = select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
# colors
colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(80)]
frame_count = 0
for path, img, im0s, vid_cap in dataset:
# Roboflow Inference
t1 = time_synchronized()
pred, classes = predict_image(vid_cap, opt.api_key, opt.url, frame_count)
pred = [torch.tensor(pred)]
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
t2 = time_synchronized()
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(
), dataset.count
else:
p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + \
('' if dataset.mode == 'image' else f'_{frame}') # img.txt
# normalization gain whwh
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]
if len(det):
print("\n[Detections]")
# Print results
clss = np.array(classes)
for c in np.unique(clss):
n = (clss == c).sum() # detections per class
s += f'{n} {c}, ' # add to string
print(s)
trans_bboxes = det[:, :4].clone()
bboxes = trans_bboxes[:, :4].cpu()
confs = det[:, 4]
# encode yolo detections and feed to tracker
features = encoder(im0, bboxes)
detections = [Detection(bbox, conf, class_num, feature) for bbox, conf, class_num, feature in zip(
bboxes, confs, classes, features)]
# run non-maxima supression
boxs = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
class_nums = np.array([d.class_num for d in detections])
indices = preprocessing.non_max_suppression(
boxs, class_nums, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
# Call the tracker
tracker.predict()
tracker.update(detections)
# update tracks
update_tracks(tracker, frame_count, save_txt, txt_path, save_img, view_img, colors, im0, gn)
# Print time (inference + NMS)
print(f'Done. ({t2 - t1:.3f}s)')
# Stream results
if view_img:
cv2.imshow(str(p), im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
save_image(save_img, dataset, save_path, im0, vid_path, vid_writer, vid_cap)
frame_count = frame_count+1
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
print(f"Results saved to {save_dir}{s}")
print(f'Done. ({time.time() - t0:.3f}s)')
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', nargs='+', type=str,
default='yolov5s.pt', help='model.pt path(s)')
# file/folder, 0 for webcam
parser.add_argument('--source', type=str,
default='data/images', help='source')
parser.add_argument('--img-size', type=int, default=640,
help='inference size (pixels)')
parser.add_argument('--conf-thres', type=float,
default=0.25, help='object confidence threshold')
parser.add_argument('--iou-thres', type=float,
default=0.45, help='IOU threshold for NMS')
parser.add_argument('--device', default='',
help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--view-img', action='store_true',
help='display results')
parser.add_argument('--save-txt', action='store_true',
help='save results to *.txt')
parser.add_argument('--save-conf', action='store_true',
help='save confidences in --save-txt labels')
parser.add_argument('--classes', nargs='+', type=int,
help='filter by class: --class 0, or --class 0 2 3')
parser.add_argument('--agnostic-nms', action='store_true',
help='class-agnostic NMS')
parser.add_argument('--augment', action='store_true',
help='augmented inference')
parser.add_argument('--update', action='store_true',
help='update all models')
parser.add_argument('--project', default='runs/detect',
help='save results to project/name')
parser.add_argument('--name', default='exp',
help='save results to project/name')
parser.add_argument('--exist-ok', action='store_true',
help='existing project/name ok, do not increment')
parser.add_argument('--nms_max_overlap', type=float, default=1.0,
help='Non-maxima suppression threshold: Maximum detection overlap.')
parser.add_argument('--max_cosine_distance', type=float, default=0.4,
help='Gating threshold for cosine distance metric (object appearance).')
parser.add_argument('--nn_budget', type=int, default=None,
help='Maximum size of the appearance descriptors allery. If None, no budget is enforced.')
parser.add_argument('--api_key', default=None,
help='Roboflow API Key.')
parser.add_argument('--url', default=None,
help='Roboflow Model URL.')
parser.add_argument('--info', action='store_true',
help='Print debugging info.')
opt = parser.parse_args()
print(opt)
with torch.no_grad():
if opt.update: # update all models (to fix SourceChangeWarning)
for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
detect()
strip_optimizer(opt.weights)
else:
detect()