def draw_box3d_on_camera(rgb, boxes3d, color=(255, 0, 255), thickness=1, text_lables=[]):
projections = box3d.box3d_to_rgb_box(boxes3d)
rgb = box3d.draw_rgb_projections(rgb, projections, color=color, thickness=thickness)
font = cv2.FONT_HERSHEY_SIMPLEX
for i,text in enumerate(text_lables):
text_pos = (np.min(projections[i,:, 0]), max(np.min(projections[i,:, 1]), 15) )
cv2.putText(rgb, text, text_pos, font, 0.7, (0, 255, 100), 1, cv2.LINE_AA)
return rgb
def draw_box3d_on_camera(rgb, boxes3d, color=(255, 0, 255), thickness=1, text_lables=[]):
projections = box3d.box3d_to_rgb_box(boxes3d)
rgb = box3d.draw_rgb_projections(rgb, projections, color=color, thickness=thickness)
font = cv2.FONT_HERSHEY_SIMPLEX
for i,text in enumerate(text_lables):
text_pos = (np.min(projections[i,:, 0]), max(np.min(projections[i,:, 1]), 15) )
cv2.putText(rgb, text, text_pos, font, 0.7, (0, 255, 100), 1, cv2.LINE_AA)
return rgb
def project_to_rgb_roi(rois3d, calib_velo_to_rgb):
num = len(rois3d)
rois = np.zeros((num, 5), dtype=np.int32)
projections = box.box3d_to_rgb_box(rois3d, calib_velo_to_rgb)
for n in range(num):
qs = projections[n]
minx = np.min(qs[:, 0])
maxx = np.max(qs[:, 0])
miny = np.min(qs[:, 1])
maxy = np.max(qs[:, 1])
rois[n, 1:5] = minx, miny, maxx, maxy
return rois
def project_to_rgb_roi(rois3d):
num = len(rois3d)
rois = np.zeros((num,5),dtype=np.int32)
projections = box.box3d_to_rgb_box(rois3d)
for n in range(num):
qs = projections[n]
minx = np.min(qs[:,0])
maxx = np.max(qs[:,0])
miny = np.min(qs[:,1])
maxy = np.max(qs[:,1])
rois[n,1:5] = minx,miny,maxx,maxy
return rois
def pred_and_save(tracklet_pred_dir,
dataset,
generate_video=False,
frame_offset=16,
log_tag=None,
weights_tag=None):
# Tracklet_saver will check whether the file already exists.
tracklet = Tracklet_saver(tracklet_pred_dir, 'pred')
os.makedirs(os.path.join(log_dir, 'image'), exist_ok=True)
gt_tracklet = Tracklet_saver(tracklet_pred_dir, 'gt')
top_shape, front_shape, rgb_shape = dataset.get_shape()
predict = mv3d.Predictor(top_shape,
front_shape,
rgb_shape,
log_tag=log_tag,
weights_tag=weights_tag)
if generate_video:
vid_in = skvideo.io.FFmpegWriter(os.path.join(log_dir, 'output.mp4'))
# timer
timer_step = 100
if cfg.TRACKING_TIMER:
time_it = timer()
print('dataset.size')
print(dataset.size)
lenght = []
gt_lenght = []
frame_num = 0
for i in range(dataset.size if fast_test == False else frame_offset + 1):
rgb, top, front, _, _, _ = dataset.load(size=1)
frame_num = i - frame_offset
print('frame_num')
print(frame_num)
if frame_num < 0:
continue
gt_boxes3d_tmp = np.load(
'/home/mohsen/Desktop/MV3D/data/preprocessed/kitti/gt_boxes3d/object3d/test/%05d.npy'
% i)
#remove gt boxes with hiegh less than 40
gt_boxes3d_list = []
for gt_box3d_tmp in gt_boxes3d_tmp:
# if gt_box3d_tmp[0,0]>0:
gt_box3d_tmp_list = []
gt_box3d_tmp_list.append(gt_box3d_tmp)
gt_project = box3d.box3d_to_rgb_box(gt_box3d_tmp_list)
if abs(gt_project[0][0, 1] - gt_project[0][4, 1]) >= 40:
gt_box3d = gt_box3d_tmp
gt_boxes3d_list.append(gt_box3d)
gt_boxes3d = np.array(gt_boxes3d_list)
# gt_boxes3d = gt_boxes3d_tmp
#####################################
boxes3d_tmp, probs = predict(top, front, rgb)
predict.dump_log(log_subdir=log_subdir, n_frame=i)
# time timer_step iterations. Turn it on/off in config.py
if cfg.TRACKING_TIMER and i % timer_step == 0 and i != 0:
predict.track_log.write('It takes %0.2f secs for inferring %d frames. \n' % \
(time_it.time_diff_per_n_loops(), timer_step))
# for debugging: save image and show image.
top_image = draw_top_image(top[0])
rgb_image = rgb[0]
if len(gt_boxes3d) != 0:
gt_lenght.append(len(gt_boxes3d))
gt_translation, gt_size, gt_rotation = boxes3d_decompose(
gt_boxes3d[:, :, :])
# todo: remove it after gtbox is ok
gt_size[:, 1:3] = gt_size[:, 1:3] / cfg.TRACKLET_GTBOX_LENGTH_SCALE
for j in range(len(gt_translation)):
gt_tracklet.add_tracklet(frame_num, gt_size[j],
gt_translation[j], gt_rotation[j])
#remove predicted boxes with hiegh less than 40
boxes3d_list = []
for box3d_tmp in boxes3d_tmp:
# if box3d_tmp[0, 0] > 0:
box3d_tmp_list = []
box3d_tmp_list.append(box3d_tmp)
project = box3d.box3d_to_rgb_box(box3d_tmp_list)
if abs(project[0][0, 1] - project[0][4, 1]) >= 40:
print(project[0][0, 1] - project[0][4, 1])
pred_box3d = box3d_tmp
boxes3d_list.append(pred_box3d)
boxes3d = np.array(boxes3d_list)
# boxes3d = boxes3d_tmp
#####################################
print('sizes')
print(np.size(boxes3d))
print(gt_boxes3d)
print(np.size(gt_boxes3d))
if len(boxes3d) != 0:
lenght.append(len(boxes3d))
top_image = draw_box3d_on_top(top_image,
boxes3d[:, :, :],
color=(80, 80, 0),
thickness=3)
rgb_image = draw_box3d_on_camera(rgb_image,
boxes3d[:, :, :],
color=(0, 0, 80),
thickness=3)
if len(gt_boxes3d) != 0:
rgb_image = draw_box3d_on_camera(rgb_image,
gt_boxes3d[:, :, :],
color=(0, 80, 0),
thickness=3)
translation, size, rotation = boxes3d_decompose(boxes3d[:, :, :])
# todo: remove it after gtbox is ok
size[:, 1:3] = size[:, 1:3] / cfg.TRACKLET_GTBOX_LENGTH_SCALE
for j in range(len(translation)):
tracklet.add_tracklet(frame_num, size[j], translation[j],
rotation[j])
resize_scale = top_image.shape[0] / rgb_image.shape[0]
rgb_image = cv2.resize(
rgb_image,
(int(rgb_image.shape[1] * resize_scale), top_image.shape[0]))
rgb_image = cv2.cvtColor(rgb_image, cv2.COLOR_BGR2RGB)
new_image = np.concatenate((top_image, rgb_image), axis=1)
cv2.imwrite(os.path.join(log_dir, 'image', '%5d_image.jpg' % i),
new_image)
if generate_video:
vid_in.writeFrame(new_image)
vid_in.close()
print(lenght)
print(sum(lenght))
tracklet.write_tracklet()
predict.dump_weigths(os.path.join(log_dir, 'pretrained_model'))
print(gt_lenght)
print(sum(gt_lenght))
gt_tracklet.write_tracklet()
if cfg.TRACKING_TIMER:
predict.log_msg.write('It takes %0.2f secs for inferring the whole test dataset. \n' % \
(time_it.total_time()))
print("tracklet file named tracklet_labels.xml is written successfully.")
return tracklet.path, gt_tracklet.path