File size: 20,272 Bytes
e215925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bcc8153
e215925
 
 
 
 
 
 
 
 
 
bcc8153
e215925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bcc8153
 
e215925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bcc8153
 
e215925
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bcc8153
 
 
e215925
 
 
 
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
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
import argparse
import cv2
import os
# limit the number of cpus used by high performance libraries
os.environ["OMP_NUM_THREADS"] = "1"
os.environ["OPENBLAS_NUM_THREADS"] = "1"
os.environ["MKL_NUM_THREADS"] = "1"
os.environ["VECLIB_MAXIMUM_THREADS"] = "1"
os.environ["NUMEXPR_NUM_THREADS"] = "1"

import sys
import platform
import numpy as np
from pathlib import Path
import torch
import torch.backends.cudnn as cudnn

FILE = Path(__file__).resolve()
ROOT = FILE.parents[0]  # yolov5 strongsort root directory
WEIGHTS = ROOT / 'weights'

if str(ROOT) not in sys.path:
    sys.path.append(str(ROOT))  # add ROOT to PATH
if str(ROOT / 'yolov8') not in sys.path:
    sys.path.append(str(ROOT / 'yolov8'))  # add yolov5 ROOT to PATH
if str(ROOT / 'trackers' / 'strongsort') not in sys.path:
    sys.path.append(str(ROOT / 'trackers' / 'strongsort'))  # add strong_sort ROOT to PATH

ROOT = Path(os.path.relpath(ROOT, Path.cwd()))  # relative

import logging

from ultralytics.nn.autobackend import AutoBackend
from ultralytics.yolo.data.dataloaders.stream_loaders import LoadImages, LoadStreams
from ultralytics.yolo.data.utils import IMG_FORMATS, VID_FORMATS
from ultralytics.yolo.utils import DEFAULT_CFG, LOGGER, SETTINGS, callbacks, colorstr, ops
from ultralytics.yolo.utils.checks import check_file, check_imgsz, check_imshow, print_args, check_requirements
from ultralytics.yolo.utils.files import increment_path
from ultralytics.yolo.utils.torch_utils import select_device
from ultralytics.yolo.utils.ops import Profile, non_max_suppression, scale_boxes, process_mask, process_mask_native
from ultralytics.yolo.utils.plotting import Annotator, colors, save_one_box


from trackers.multi_tracker_zoo import create_tracker


@torch.no_grad()
def run(
        source='0',
        yolo_weights=WEIGHTS / 'yolov5m.pt',  # model.pt path(s),
        reid_weights=WEIGHTS / 'osnet_x0_25_msmt17.pt',  # model.pt path,
        tracking_method='strongsort',
        tracking_config=None,
        imgsz=(640, 640),  # inference size (height, width)
        conf_thres=0.25,  # confidence threshold
        iou_thres=0.45,  # NMS IOU threshold
        max_det=1000,  # maximum detections per image
        device='',  # cuda device, i.e. 0 or 0,1,2,3 or cpu
        show_vid=False,  # show results
        save_txt=False,  # save results to *.txt
        save_conf=False,  # save confidences in --save-txt labels
        save_crop=False,  # save cropped prediction boxes
        save_trajectories=False,  # save trajectories for each track
        save_vid=True,  # save confidences in --save-txt labels
        nosave=False,  # do not save images/videos
        classes=None,  # filter by class: --class 0, or --class 0 2 3
        agnostic_nms=False,  # class-agnostic NMS
        augment=False,  # augmented inference
        visualize=False,  # visualize features
        update=False,  # update all models
        #project=ROOT / 'runs' / 'track',  # save results to project/name
        project=ROOT ,# save results to project/name
        name='exp',  # save results to project/name
        exist_ok=True,  # existing project/name ok, do not increment
        line_thickness=2,  # bounding box thickness (pixels)
        hide_labels=False,  # hide labels
        hide_conf=False,  # hide confidences
        hide_class=False,  # hide IDs
        half=False,  # use FP16 half-precision inference
        dnn=False,  # use OpenCV DNN for ONNX inference
        vid_stride=1,  # video frame-rate stride
        retina_masks=False,
):
    #print the inputs
    print(f"model used : {yolo_weights}, tracking method : {tracking_method}")

    source = str(source)
    save_img = not nosave and not source.endswith('.txt')  # save inference images
    is_file = Path(source).suffix[1:] in (VID_FORMATS)
    is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
    if is_url and is_file:
        source = check_file(source)  # download

    # Directories
    if not isinstance(yolo_weights, list):  # single yolo model
        exp_name = yolo_weights.stem
    elif type(yolo_weights) is list and len(yolo_weights) == 1:  # single models after --yolo_weights
        exp_name = Path(yolo_weights[0]).stem
    else:  # multiple models after --yolo_weights
        exp_name = 'ensemble'
    exp_name = name if name else exp_name + "_" + reid_weights.stem
    save_dir = increment_path(Path(project) / exp_name, exist_ok=exist_ok)  # increment run
    (save_dir / 'tracks' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

    # Load model
    device = select_device(device)
    is_seg = '-seg' in str(yolo_weights)

  
    model = AutoBackend(yolo_weights, device=device, dnn=dnn, fp16=half)
    stride, names, pt = model.stride, model.names, model.pt
    imgsz = check_imgsz(imgsz, stride=stride)  # check image size

    # Dataloader
    bs = 1
    if webcam:
        show_vid = check_imshow(warn=True)
        dataset = LoadStreams(
            source,
            imgsz=imgsz,
            stride=stride,
            auto=pt,
            transforms=getattr(model.model, 'transforms', None),
            vid_stride=vid_stride
        )
        bs = len(dataset)
    else:
        dataset = LoadImages(
            source,
            imgsz=imgsz,
            stride=stride,
            auto=pt,
            transforms=getattr(model.model, 'transforms', None),
            vid_stride=vid_stride
        )
    vid_path, vid_writer, txt_path = [None] * bs, [None] * bs, [None] * bs
    model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz))  # warmup

    # Create as many strong sort instances as there are video sources
    tracker_list = []
    for i in range(bs):
        tracker = create_tracker(tracking_method, tracking_config, reid_weights, device, half)
        tracker_list.append(tracker, )
        if hasattr(tracker_list[i], 'model'):
            if hasattr(tracker_list[i].model, 'warmup'):
                tracker_list[i].model.warmup()
    outputs = [None] * bs

    # Run tracking
    #model.warmup(imgsz=(1 if pt else bs, 3, *imgsz))  # warmup
    seen, windows, dt = 0, [], (Profile(), Profile(), Profile(), Profile())
    curr_frames, prev_frames = [None] * bs, [None] * bs
    for frame_idx, batch in enumerate(dataset):
        path, im, im0s, vid_cap, s = batch
        visualize = increment_path(save_dir / Path(path[0]).stem, mkdir=True) if visualize else False
        with dt[0]:
            im = torch.from_numpy(im).to(device)
            im = im.half() if half else im.float()  # uint8 to fp16/32
            im /= 255.0  # 0 - 255 to 0.0 - 1.0
            if len(im.shape) == 3:
                im = im[None]  # expand for batch dim

        # Inference
        with dt[1]:
            preds = model(im, augment=augment, visualize=visualize)

        # Apply NMS
        with dt[2]:
            if is_seg:
                masks = []
                p = non_max_suppression(preds[0], conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det, nm=32)
                proto = preds[1][-1]
            else:
                p = non_max_suppression(preds, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
            
        # Process detections
        filename = 'out.mp4'
        for i, det in enumerate(p):  # detections per image
            seen += 1
            if webcam:  # bs >= 1
                p, im0, _ = path[i], im0s[i].copy(), dataset.count
                p = Path(p)  # to Path
                s += f'{i}: '
                txt_file_name = p.name
                save_path = str(save_dir / filename)  # im.jpg, vid.mp4, ...
                
            else:
                p, im0, _ = path, im0s.copy(), getattr(dataset, 'frame', 0)
                p = Path(p)  # to Path
                # video file
                if source.endswith(VID_FORMATS):
                    txt_file_name = p.stem
                    save_path = str(save_dir / filename)  # im.jpg, vid.mp4, ...
                    LOGGER.info(f"p.name is {p.name}, save_path value is {save_path}")
                # folder with imgs
                else:
                    txt_file_name = p.parent.name  # get folder name containing current img
                    save_path = str(save_dir / p.parent.name)  # im.jpg, vid.mp4, ...
            curr_frames[i] = im0

            txt_path = str(save_dir / 'tracks' / txt_file_name)  # im.txt
            s += '%gx%g ' % im.shape[2:]  # print string
            imc = im0.copy() if save_crop else im0  # for save_crop

            annotator = Annotator(im0, line_width=line_thickness, example=str(names))
            
            if hasattr(tracker_list[i], 'tracker') and hasattr(tracker_list[i].tracker, 'camera_update'):
                if prev_frames[i] is not None and curr_frames[i] is not None:  # camera motion compensation
                    tracker_list[i].tracker.camera_update(prev_frames[i], curr_frames[i])

            if det is not None and len(det):
                if is_seg:
                    shape = im0.shape
                    # scale bbox first the crop masks
                    if retina_masks:
                        det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], shape).round()  # rescale boxes to im0 size
                        masks.append(process_mask_native(proto[i], det[:, 6:], det[:, :4], im0.shape[:2]))  # HWC
                    else:
                        masks.append(process_mask(proto[i], det[:, 6:], det[:, :4], im.shape[2:], upsample=True))  # HWC
                        det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], shape).round()  # rescale boxes to im0 size
                else:
                    det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()  # rescale boxes to im0 size

                # Print results
                for c in det[:, 5].unique():
                    n = (det[:, 5] == c).sum()  # detections per class
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

                # pass detections to strongsort
                with dt[3]:
                    outputs[i] = tracker_list[i].update(det.cpu(), im0)
                
                # draw boxes for visualization
                if len(outputs[i]) > 0:
                    
                    if is_seg:
                        # Mask plotting
                        annotator.masks(
                            masks[i],
                            colors=[colors(x, True) for x in det[:, 5]],
                            im_gpu=torch.as_tensor(im0, dtype=torch.float16).to(device).permute(2, 0, 1).flip(0).contiguous() /
                            255 if retina_masks else im[i]
                        )
                    
                    for j, (output) in enumerate(outputs[i]):
                        
                        bbox = output[0:4]
                        id = output[4]
                        cls = output[5]
                        conf = output[6]

                        if save_txt:
                            # to MOT format
                            bbox_left = output[0]
                            bbox_top = output[1]
                            bbox_w = output[2] - output[0]
                            bbox_h = output[3] - output[1]
                            # Write MOT compliant results to file
                            with open(txt_path + '.txt', 'a') as f:
                                f.write(('%g ' * 10 + '\n') % (frame_idx + 1, id, bbox_left,  # MOT format
                                                               bbox_top, bbox_w, bbox_h, -1, -1, -1, i))

                        if save_vid or save_crop or show_vid:  # Add bbox/seg to image
                            c = int(cls)  # integer class
                            id = int(id)  # integer id
                            label = None if hide_labels else (f'{id} {names[c]}' if hide_conf else \
                                (f'{id} {conf:.2f}' if hide_class else f'{id} {names[c]} {conf:.2f}'))
                            color = colors(c, True)
                            annotator.box_label(bbox, label, color=color)
                            
                            if save_trajectories and tracking_method == 'strongsort':
                                q = output[7]
                                tracker_list[i].trajectory(im0, q, color=color)
                            if save_crop:
                                txt_file_name = txt_file_name if (isinstance(path, list) and len(path) > 1) else ''
                                save_one_box(np.array(bbox, dtype=np.int16), imc, file=save_dir / 'crops' / txt_file_name / names[c] / f'{id}' / f'{p.stem}.jpg', BGR=True)
                            
            else:
                pass
                #tracker_list[i].tracker.pred_n_update_all_tracks()
                
            # Stream results
            im0 = annotator.result()
            if show_vid:
                if platform.system() == 'Linux' and p not in windows:
                    windows.append(p)
                    cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO)  # allow window resize (Linux)
                    cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0])
                cv2.imshow(str(p), im0)
                if cv2.waitKey(1) == ord('q'):  # 1 millisecond
                    exit()

            # Save results (image with detections)
            if save_vid:
                LOGGER.info(f"vid_path, save_path {vid_path[i]}{save_path}")
                if vid_path[i] != save_path:  # new video
                    vid_path[i] = save_path
                    if isinstance(vid_writer[i], cv2.VideoWriter):
                        vid_writer[i].release()  # release previous video writer
                    if vid_cap:  # video
                        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))
                    else:  # stream
                        fps, w, h = 30, im0.shape[1], im0.shape[0]
                    save_path = str(Path(save_path).with_suffix('.mp4'))  # force *.mp4 suffix on results videos
                    LOGGER.info(f"test Results saved to {colorstr('bold', save_path)}")
                    vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                vid_writer[i].write(im0)

            prev_frames[i] = curr_frames[i]
            
        # Print total time (preprocessing + inference + NMS + tracking)
        LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{sum([dt.dt for dt in dt if hasattr(dt, 'dt')]) * 1E3:.1f}ms")

    # Print results
    t = tuple(x.t / seen * 1E3 for x in dt)  # speeds per image
    LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS, %.1fms {tracking_method} update per image at shape {(1, 3, *imgsz)}' % t)
    if save_txt or save_vid:
        s = f"\n{len(list((save_dir / 'tracks').glob('*.txt')))} tracks saved to {save_dir / 'tracks'}" if save_txt else ''
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
    if update:
        strip_optimizer(yolo_weights)  # update model (to fix SourceChangeWarning)


def parse_opt():
    parser = argparse.ArgumentParser()
    #parser.add_argument('--yolo-weights', nargs='+', type=Path, default=WEIGHTS / 'yolov8s-seg.pt', help='model.pt path(s)')
    parser.add_argument('--reid-weights', type=Path, default=WEIGHTS / 'osnet_x0_25_msmt17.pt')
    #parser.add_argument('--tracking-method', type=str, default='bytetrack', help='strongsort, ocsort, bytetrack')
    parser.add_argument('--tracking-config', type=Path, default=None)
    #parser.add_argument('--source', type=str, default='0', help='file/dir/URL/glob, 0 for webcam')  
    parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
    parser.add_argument('--conf-thres', type=float, default=0.5, help='confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.5, help='NMS IoU threshold')
    parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--show-vid', action='store_true', help='display tracking video 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('--save-crop', action='store_true', help='save cropped prediction boxes')
    parser.add_argument('--save-trajectories', action='store_true', help='save trajectories for each track')
    parser.add_argument('--save-vid', action='store_true',default=True, help='save video tracking results')
    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
    # class 0 is person, 1 is bycicle, 2 is car... 79 is oven
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default=ROOT , help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to ROOT')
    parser.add_argument('--exist-ok', default='True', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--line-thickness', default=2, type=int, help='bounding box thickness (pixels)')
    parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
    parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
    parser.add_argument('--hide-class', default=False, action='store_true', help='hide IDs')
    parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
    parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference')
    parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
    parser.add_argument('--retina-masks', action='store_true', help='whether to plot masks in native resolution')
    #opt = parser.parse_args()
    #opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
    #opt.tracking_config = ROOT / 'trackers' / opt.tracking_method / 'configs' / (opt.tracking_method + '.yaml')
    #print_args(vars(opt))
    #return opt
    return parser


def main(opt):
    check_requirements(requirements=ROOT / 'requirements.txt', exclude=('tensorboard', 'thop'))
    run(**vars(opt))


#if __name__ == "__main__":
#    opt = parse_opt()
#    main(opt)

def MOT(yoloweights, trackingmethod, sourceVideo):
    parser = parse_opt()
    parser.add_argument('--yolo-weights', nargs='+', type=Path, default= yoloweights, help='model.pt path(s)')
    parser.add_argument('--tracking-method', type=str, default= trackingmethod, help='strongsort, ocsort, bytetrack')
    parser.add_argument('--source', type=str, default=sourceVideo, help='file/dir/URL/glob, 0 for webcam')  
    opt = parser.parse_args()
    opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1  # expand
    opt.tracking_config = ROOT / 'trackers' / opt.tracking_method / 'configs' / (opt.tracking_method + '.yaml')
    print_args(vars(opt))
    main(opt)
    save_dir = increment_path('exp', exist_ok=True) 
    input = os.path.join(save_dir,'out.mp4')
    outpath = 'output.mp4'  #'output/'+ 'output.mp4' 
    if os.path.exists(outpath):
        os.remove(outpath)
    
    command = f"ffmpeg -i {input} -vf fps=30 -vcodec libx264 {outpath}"
    print(command)
    os.system(command)
    return outpath