def run_tracker(tracker, img, gt, video_name, restart=True): frame_counter = 0 lost_number = 0 toc = 0 pred_bboxes = [] if restart: # VOT2016 and VOT 2018 for idx, (img, gt_bbox) in enumerate(video): if len(gt_bbox) == 4: gt_bbox = [ gt_bbox[0], gt_bbox[1], gt_bbox[0], gt_bbox[1] + gt_bbox[3] - 1, gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1] + gt_bbox[3] - 1, gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1] ] tic = cv2.getTickCount() if idx == frame_counter: cx, cy, w, h = get_min_max_bbox(np.array(gt_bbox)) gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h] tracker.init(img, gt_bbox_) pred_bbox = gt_bbox_ pred_bboxes.append(1) elif idx > frame_counter: outputs = tracker.track(img) pred_bbox = outputs['bbox'] overlap = vot_overlap(pred_bbox, gt_bbox, (img.shape[1], img.shape[0])) if overlap > 0: # not lost pred_bboxes.append(pred_bbox) else: # lost object pred_bboxes.append(2) frame_counter = idx + 5 # skip 5 frames lost_number += 1 else: pred_bboxes.append(0) toc += cv2.getTickCount() - tic toc /= cv2.getTickFrequency() print( 'Video: {:12s} Time: {:4.1f}s Speed: {:3.1f}fps Lost: {:d}'.format( video_name, toc, idx / toc, lost_number)) return pred_bboxes else: toc = 0 pred_bboxes = [] scores = [] track_times = [] for idx, (img, gt_bbox) in enumerate(video): tic = cv2.getTickCount() if idx == 0: cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox)) gt_bbox_ = [cx - w / 2, cy - h / 2, w, h] tracker.init(img, gt_bbox_) pred_bbox = gt_bbox_ scores.append(None) pred_bboxes.append(pred_bbox) else: outputs = tracker.track(img) pred_bbox = outputs['bbox'] pred_bboxes.append(pred_bbox) scores.append(outputs['best_score']) toc += cv2.getTickCount() - tic track_times.append( (cv2.getTickCount() - tic) / cv2.getTickFrequency()) toc /= cv2.getTickFrequency() print('Video: {:12s} Time: {:5.1f}s Speed: {:3.1f}fps'.format( video_name, toc, idx / toc)) return pred_bboxes, scores, track_times
def main(): os.environ['CUDA_VISIBLE_DEVICES'] = '0,' cur_dir = os.path.dirname(os.path.realpath(__file__)) dataset_root = os.path.join(cur_dir, '../../pysot/testing_dataset', args.dataset) # create model model = BsiModelBuilder(backbone=cfg.backbone_type).cuda() # load model model = load_pretrain(model, args.snapshot) torch.set_grad_enabled(False) # build tracker tracker = BaSiamIoUTracker(model) # create dataset dataset = DatasetFactory.create_dataset(name=args.dataset, dataset_root=dataset_root, load_img=False) model_name = args.snapshot.split('/')[-1].split('.')[0] total_lost = 0 if args.dataset in ['VOT2016', 'VOT2018']: # , 'VOT2019' # restart tracking for v_idx, video in enumerate(dataset): if args.video != '': # test one special video if video.name != args.video and args.video != '%d' % v_idx: continue frame_counter = 0 lost_number = 0 toc = 0 pred_bboxes = [] for idx, (img, gt_bbox) in enumerate(video): if len(gt_bbox) == 4: gt_bbox = [ gt_bbox[0], gt_bbox[1], gt_bbox[0], gt_bbox[1] + gt_bbox[3] - 1, gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1] + gt_bbox[3] - 1, gt_bbox[0] + gt_bbox[2] - 1, gt_bbox[1] ] tic = cv2.getTickCount() if idx == frame_counter: cx, cy, w, h = get_min_max_bbox( np.array(gt_bbox)) # get_axis_aligned_bbox gt_bbox_ = [cx - (w - 1) / 2, cy - (h - 1) / 2, w, h] tracker.init(img, gt_bbox_) pred_bbox = gt_bbox_ pred_bboxes.append(1) elif idx > frame_counter: outputs = tracker.track(img) pred_bbox = outputs['bbox'] overlap = vot_overlap(pred_bbox, gt_bbox, (img.shape[1], img.shape[0])) if overlap > 0: # not lost pred_bboxes.append(pred_bbox) else: # lost object pred_bboxes.append(2) frame_counter = idx + 5 # skip 5 frames lost_number += 1 else: pred_bboxes.append(0) toc += cv2.getTickCount() - tic if idx == 0: cv2.destroyAllWindows() if args.vis and idx > frame_counter: cv2.polylines( img, [np.array(gt_bbox, np.int).reshape( (-1, 1, 2))], True, (0, 255, 0), 3) bbox = list(map(int, pred_bbox)) cv2.rectangle(img, (bbox[0], bbox[1]), (bbox[0] + bbox[2], bbox[1] + bbox[3]), (0, 255, 255), 3) cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2) cv2.putText(img, str(lost_number), (40, 80), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 0, 255), 2) cv2.imshow(video.name, img) cv2.waitKey(1) toc /= cv2.getTickFrequency() # save results video_path = os.path.join('results', args.dataset, model_name, 'baseline', video.name) if not os.path.isdir(video_path): os.makedirs(video_path) result_path = os.path.join(video_path, '{}_001.txt'.format(video.name)) with open(result_path, 'w') as f: for x in pred_bboxes: if isinstance(x, int): f.write("{:d}\n".format(x)) else: f.write(','.join([vot_float2str("%.4f", i) for i in x]) + '\n') print( '({:3d}) Video: {:12s} Time: {:4.1f}s Speed: {:3.1f}fps Lost: {:d}' .format(v_idx + 1, video.name, toc, idx / toc, lost_number)) total_lost += lost_number print("{:s} total lost: {:d}".format(model_name, total_lost)) else: # OPE tracking for v_idx, video in enumerate(dataset): if args.video != '': # test one special video if video.name != args.video and args.video != '%d' % v_idx: continue toc = 0 pred_bboxes = [] scores = [] track_times = [] for idx, (img, gt_bbox) in enumerate(video): tic = cv2.getTickCount() if idx == 0: cx, cy, w, h = get_axis_aligned_bbox(np.array(gt_bbox)) gt_bbox_ = [cx - w / 2, cy - h / 2, w, h] tracker.init(img, gt_bbox_) pred_bbox = gt_bbox_ scores.append(None) if 'VOT2018-LT' == args.dataset: pred_bboxes.append([1]) else: pred_bboxes.append(pred_bbox) else: outputs = tracker.track(img) pred_bbox = outputs['bbox'] pred_bboxes.append(pred_bbox) scores.append(outputs['best_score']) toc += cv2.getTickCount() - tic track_times.append( (cv2.getTickCount() - tic) / cv2.getTickFrequency()) if idx == 0: cv2.destroyAllWindows() if args.vis and idx > 0: if not np.isnan(gt_bbox).any(): gt_bbox = list(map(int, gt_bbox)) cv2.rectangle( img, (gt_bbox[0], gt_bbox[1]), (gt_bbox[0] + gt_bbox[2], gt_bbox[1] + gt_bbox[3]), (0, 255, 0), 3) pred_bbox = list(map(int, pred_bbox)) cv2.rectangle(img, (pred_bbox[0], pred_bbox[1]), (pred_bbox[0] + pred_bbox[2], pred_bbox[1] + pred_bbox[3]), (0, 255, 255), 3) cv2.putText(img, str(idx), (40, 40), cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 255), 2) cv2.imshow(video.name, cv2.resize(img, (480, 360))) cv2.waitKey(1) toc /= cv2.getTickFrequency() # save results if 'VOT2018-LT' == args.dataset: video_path = os.path.join('results', args.dataset, model_name, 'longterm', video.name) if not os.path.isdir(video_path): os.makedirs(video_path) result_path = os.path.join(video_path, '{}_001.txt'.format(video.name)) with open(result_path, 'w') as f: for x in pred_bboxes: f.write(','.join([str(i) for i in x]) + '\n') result_path = os.path.join( video_path, '{}_001_confidence.value'.format(video.name)) with open(result_path, 'w') as f: for x in scores: f.write('\n') if x is None else f.write( "{:.6f}\n".format(x)) result_path = os.path.join(video_path, '{}_time.txt'.format(video.name)) with open(result_path, 'w') as f: for x in track_times: f.write("{:.6f}\n".format(x)) elif 'GOT-10k' == args.dataset: video_path = os.path.join('results', args.dataset, model_name, video.name) if not os.path.isdir(video_path): os.makedirs(video_path) result_path = os.path.join(video_path, '{}_001.txt'.format(video.name)) with open(result_path, 'w') as f: for x in pred_bboxes: f.write(','.join([str(i) for i in x]) + '\n') result_path = os.path.join(video_path, '{}_time.txt'.format(video.name)) with open(result_path, 'w') as f: for x in track_times: f.write("{:.6f}\n".format(x)) else: model_path = os.path.join( 'results', args.dataset, model_name) #, '{}'.format(video.name)) if not os.path.isdir(model_path): os.makedirs(model_path) result_path = os.path.join(model_path, '{}.txt'.format(video.name)) # result_path = os.path.join(model_path, '{}_001.txt'.format(video.name)) # model_path2 = os.path.join('results', args.dataset, model_name) # shutil.copyfile(result_path, result_path2) # if os.path.exists(result_path2): # print("success copy" + video.name) with open(result_path, 'w') as f: for x in pred_bboxes: f.write(','.join([str(i) for i in x]) + '\n') print('({:3d}) Video: {:12s} Time: {:5.1f}s Speed: {:3.1f}fps'. format(v_idx + 1, video.name, toc, idx / toc))