def task1_1(paths, show, noise_params):
gt = read_annotations(paths['gt'], grouped=False, use_parked=True)
det = read_detections(paths['det'], grouped=True)
grouped_gt = group_by_frame(gt)
# if we want to replicate results
# np.random.seed(10)
cap = cv2.VideoCapture(paths['video'])
# cap.set(cv2.CAP_PROP_POS_FRAMES, frame_id) # to start from frame #frame_id
num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
if noise_params['add']:
noisy_gt = add_noise(gt, noise_params, num_frames)
grouped_noisy_gt = group_by_frame(noisy_gt)
for frame_id in range(num_frames):
_, frame = cap.read()
if show['gt']:
frame = draw_boxes(frame, grouped_gt[frame_id], color='g')
if show['det']:
frame = draw_boxes(frame, det[frame_id], color='b', det=True)
if show['noisy']:
frame = draw_boxes(frame, grouped_noisy_gt[frame_id], color='r')
cv2.imshow('frame', frame)
if cv2.waitKey() == 113: # press q to quit
break
frame_id += 1
cv2.destroyAllWindows()
return
def eval_sota(vidcap,
test_len,
backSub,
params,
init_frame=535,
return_detections=False):
print("Evaluating SOTA")
# gt = read_annotations(params["gt_path"], grouped=True, use_parked=False)
gt = read_detections(params['gt_path'], grouped=True)
frame_id = int(vidcap.get(cv2.CAP_PROP_POS_FRAMES))
detections = []
annotations = {}
for t in tqdm(range(test_len)):
_, frame = vidcap.read()
segmentation = backSub.apply(frame)
roi = cv2.imread(params['roi_path'], cv2.IMREAD_GRAYSCALE) / 255
segmentation = segmentation * roi
segmentation = postprocess_fg(segmentation)
det_bboxes = fg_bboxes(segmentation, frame_id, params)
detections += det_bboxes
segmentation = cv2.cvtColor(segmentation.astype(np.uint8),
cv2.COLOR_GRAY2RGB)
gt_bboxes = []
if frame_id in gt:
gt_bboxes = gt[frame_id]
annotations[frame_id] = gt_bboxes
text_bboxes = "nbb" #no bouning boxes
if params['show_boxes']:
segmentation = draw_boxes(image=segmentation,
boxes=gt_bboxes,
color='g',
linewidth=3)
cv2.rectangle(frame, (10, 2), (120, 20), (255, 255, 255), -1)
cv2.putText(
frame, params["sota_method"] + " - " +
str(vidcap.get(cv2.CAP_PROP_POS_FRAMES)), (15, 15),
cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))
segmentation = draw_boxes(image=segmentation,
boxes=det_bboxes,
color='r',
linewidth=3)
cv2.imshow("Segmentation mask with detected boxes and gt",
segmentation)
cv2.imshow('Frame', frame)
text_bboxes = ""
if params[
'save_results'] and frame_id >= 1169 and frame_id < 1229: # if frame_id >= 535 and frame_id < 550
cv2.imwrite(
params['results_path'] +
f"seg_{str(frame_id)}_pp_{params['sota_method']}_{text_bboxes}.bmp",
segmentation.astype(int))
if cv2.waitKey() == 113: # press q to quit
break
if params['save_results'] and frame_id >= 1169 and frame_id < 1229:
segmentation = draw_boxes(image=segmentation,
boxes=gt_bboxes,
color='g',
linewidth=3)
segmentation = draw_boxes(image=segmentation,
boxes=det_bboxes,
color='r',
linewidth=3)
cv2.imwrite(f"seg/{str(frame_id)}.png", segmentation.astype(int))
frame_id += 1
detections = temporal_filter(group_by_frame(detections),
init=init_frame,
end=frame_id)
rec, prec, ap = voc_evaluation.voc_eval(detections,
annotations,
ovthresh=0.5,
use_confidence=False)
if return_detections:
return ap, group_by_frame(detections)
else:
return ap
def eval(vidcap, frame_size, mean, std, params):
gt = read_annotations(params['gt_path'], grouped=True, use_parked=False)
init_frame = int(vidcap.get(cv2.CAP_PROP_POS_FRAMES))
frame_id = init_frame
detections = []
annotations = {}
for t in tqdm(range(params['num_frames_eval'])):
_, frame = vidcap.read()
frame = cv2.cvtColor(frame, color_space[params['color_space']][0])
if params['color_space'] == 'H':
H, S, V = np.split(frame, 3, axis=2)
frame = np.squeeze(H)
if params['color_space'] == 'L':
L, A, B = np.split(frame, 3, axis=2)
frame = np.squeeze(L)
if params['color_space'] == 'CbCr':
Y, Cb, Cr = np.split(frame, 3, axis=2)
frame = np.dstack((Cb, Cr))
segmentation, mean, std = bg_est_method[params['bg_est']](frame,
frame_size,
mean, std,
params)
roi = cv2.imread(params['roi_path'], cv2.IMREAD_GRAYSCALE) / 255
segmentation = segmentation * roi
segmentation = postprocess_fg(segmentation)
if params[
'save_results'] and frame_id >= 1169 and frame_id < 1229: # if frame_id >= 535 and frame_id < 550
cv2.imwrite(
params['results_path'] +
f"seg_{str(frame_id)}_pp_{str(params['alpha'])}.bmp",
segmentation.astype(int))
det_bboxes = fg_bboxes(segmentation, frame_id, params)
detections += det_bboxes
gt_bboxes = []
if frame_id in gt:
gt_bboxes = gt[frame_id]
annotations[frame_id] = gt_bboxes
if params['show_boxes']:
seg = cv2.cvtColor(segmentation.astype(np.uint8),
cv2.COLOR_GRAY2RGB)
seg_boxes = draw_boxes(image=seg,
boxes=det_bboxes,
color='r',
linewidth=3)
seg_boxes = draw_boxes(image=seg_boxes,
boxes=gt_bboxes,
color='g',
linewidth=3)
cv2.imshow("Segmentation mask with detected boxes and gt",
seg_boxes)
if cv2.waitKey() == 113: # press q to quit
break
frame_id += 1
detections = temporal_filter(group_by_frame(detections),
init=init_frame,
end=frame_id)
rec, prec, ap = voc_evaluation.voc_eval(detections,
annotations,
ovthresh=0.5,
use_confidence=False)
return ap
def task2(gt_path, det_path, video_path, results_path):
plot_frames_path = os.path.join(results_path, 'plot_frames/')
video_frames_path = os.path.join(results_path, 'video_frames/')
print(plot_frames_path)
# If folder doesn't exist -> create it
os.makedirs(plot_frames_path, exist_ok=True)
os.makedirs(video_frames_path, exist_ok=True)
show_det = True
show_noisy = False
gt = read_annotations(gt_path, grouped=False, use_parked=True)
det = read_detections(det_path, grouped=True)
grouped_gt = group_by_frame(gt)
noise_params = {
'add': False,
'drop': 0.0,
'generate_close': 0.0,
'generate_random': 0.0,
'type': 'specific', # options: 'specific', 'gaussian', None
'std': 40, # pixels
'position': False,
'size': True,
'keep_ratio': True
}
if noise_params['add']:
noisy_gt = add_noise(gt, noise_params)
grouped_noisy_gt = group_by_frame(noisy_gt)
cap = cv2.VideoCapture(video_path)
# cap.set(cv2.CAP_PROP_POS_FRAMES, frame_id) # to start from frame #frame_id
num_frames = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
iou_list = {}
for frame_id in range(20):
_, frame = cap.read()
frame = draw_boxes(frame, grouped_gt[frame_id], color='g')
if show_det:
frame = draw_boxes(frame, det[frame_id], color='b', det=True)
frame_iou = mean_iou(det[frame_id], grouped_gt[frame_id], sort=True)
if show_noisy:
frame = draw_boxes(frame, grouped_noisy_gt[frame_id], color='r')
frame_iou = mean_iou(grouped_noisy_gt[frame_id], grouped_gt[frame_id])
iou_list[frame_id] = frame_iou
plot = plot_iou(iou_list, num_frames)
'''
if show:
fig.show()
cv2.imshow('frame', frame)
if cv2.waitKey() == 113: # press q to quit
break
'''
imageio.imwrite(video_frames_path + '{}.png'.format(frame_id), frame)
plot.savefig(plot_frames_path + 'iou_{}.png'.format(frame_id))
plt.close(plot)
frame_id += 1
save_gif(plot_frames_path, results_path + 'iou.gif')
save_gif(video_frames_path, results_path + 'bbox.gif')
# cv2.destroyAllWindows()
return
if __name__ == '__main__':
args = parse_args()
det_path = 'results/task1_1/' + args.model + '/detections.txt'
if args.detect:
det_path = model_detect[args.model](args.video_path)
if args.visualize:
gt = read_annotations(args.gt_path, grouped=True, use_parked=True)
det = read_detections(det_path, grouped=False)
det = group_by_frame(filter_by_conf(det, conf_thr=args.min_conf))
vidcap = cv2.VideoCapture(args.video_path)
# vidcap.set(cv2.CAP_PROP_POS_FRAMES, initial_frame) # to start from frame #frame_id
num_frames = int(vidcap.get(cv2.CAP_PROP_FRAME_COUNT))
for frame_id in range(num_frames):
_, frame = vidcap.read()
if frame_id >= 1755 and frame_id <= 1835:
frame = draw_boxes(frame, gt[frame_id], color='g')
frame = draw_boxes(frame, det[frame_id], color='b', det=True)
cv2.imshow('frame', frame)
if cv2.waitKey() == 113: # press q to quit
break