def main():
current_dir = os.path.dirname(os.path.abspath(__file__))
"""Prepares data for the person recognition demo"""
parser = argparse.ArgumentParser(description='Multi camera multi person \
tracking live demo script')
parser.add_argument('-i',
type=str,
nargs='+',
help='Input sources (indexes \
of cameras or paths to video files)',
required=True)
parser.add_argument('--config',
type=str,
default=os.path.join(current_dir, 'config.py'),
required=False,
help='Configuration file')
parser.add_argument('--detections',
type=str,
help='JSON file with bounding boxes')
parser.add_argument('-m',
'--m_detector',
type=str,
required=False,
help='Path to the person detection model')
parser.add_argument('--t_detector',
type=float,
default=0.6,
help='Threshold for the person detection model')
parser.add_argument('--m_segmentation',
type=str,
required=False,
help='Path to the person instance segmentation model')
parser.add_argument(
'--t_segmentation',
type=float,
default=0.6,
help='Threshold for person instance segmentation model')
parser.add_argument('--m_reid',
type=str,
required=True,
help='Path to the person re-identification model')
parser.add_argument('--output_video',
type=str,
default='',
required=False,
help='Optional. Path to output video')
parser.add_argument(
'--history_file',
type=str,
default='',
required=False,
help='Optional. Path to file in JSON format to save results of the demo'
)
parser.add_argument(
'--save_detections',
type=str,
default='',
required=False,
help='Optional. Path to file in JSON format to save bounding boxes')
parser.add_argument("--no_show",
help="Optional. Don't show output",
action='store_true')
parser.add_argument('-d', '--device', type=str, default='CPU')
parser.add_argument('-l',
'--cpu_extension',
help='MKLDNN (CPU)-targeted custom layers.Absolute \
path to a shared library with the kernels impl.',
type=str,
default=None)
parser.add_argument('-u',
'--utilization_monitors',
default='',
type=str,
help='Optional. List of monitors to show initially.')
args = parser.parse_args()
if check_detectors(args) != 1:
sys.exit(1)
if len(args.config):
log.info('Reading configuration file {}'.format(args.config))
config = read_py_config(args.config)
else:
log.error(
'No configuration file specified. Please specify parameter \'--config\''
)
sys.exit(1)
random.seed(config['random_seed'])
capture = MulticamCapture(args.i)
log.info("Creating Inference Engine")
ie = IECore()
if args.detections:
person_detector = DetectionsFromFileReader(args.detections,
args.t_detector)
elif args.m_segmentation:
person_detector = MaskRCNN(ie, args.m_segmentation,
args.t_segmentation,
args.device, args.cpu_extension,
capture.get_num_sources())
else:
person_detector = Detector(ie, args.m_detector, args.t_detector,
args.device, args.cpu_extension,
capture.get_num_sources())
if args.m_reid:
person_recognizer = VectorCNN(ie, args.m_reid, args.device,
args.cpu_extension)
else:
person_recognizer = None
run(args, config, capture, person_detector, person_recognizer)
log.info('Demo finished successfully')
def main():
parser = argparse.ArgumentParser(description='Whiteboard inpainting demo')
parser.add_argument('-i', '--input', required=True,
help='Required. Path to a video file or a device node of a web-camera.')
parser.add_argument('--loop', default=False, action='store_true',
help='Optional. Enable reading the input in a loop.')
parser.add_argument('-o', '--output', required=False,
help='Optional. Name of the output file(s) to save.')
parser.add_argument('-limit', '--output_limit', required=False, default=1000, type=int,
help='Optional. Number of frames to store in output. '
'If 0 is set, all frames are stored.')
parser.add_argument('-m_i', '--m_instance_segmentation', type=str, required=False,
help='Required. Path to the instance segmentation model.')
parser.add_argument('-m_s', '--m_semantic_segmentation', type=str, required=False,
help='Required. Path to the semantic segmentation model.')
parser.add_argument('-t', '--threshold', type=float, default=0.6,
help='Optional. Threshold for person instance segmentation model.')
parser.add_argument('--no_show', help="Optional. Don't show output.", action='store_true')
parser.add_argument('-d', '--device', type=str, default='CPU',
help='Optional. Specify a target device to infer on. CPU, GPU, HDDL or MYRIAD is '
'acceptable. The demo will look for a suitable plugin for the device specified.')
parser.add_argument('-l', '--cpu_extension', type=str, default=None,
help='MKLDNN (CPU)-targeted custom layers. Absolute \
path to a shared library with the kernels impl.')
parser.add_argument('-u', '--utilization_monitors', default='', type=str,
help='Optional. List of monitors to show initially.')
args = parser.parse_args()
cap = open_images_capture(args.input, args.loop)
if cap.get_type() not in ('VIDEO', 'CAMERA'):
raise RuntimeError("The input should be a video file or a numeric camera ID")
if bool(args.m_instance_segmentation) == bool(args.m_semantic_segmentation):
raise ValueError('Set up exactly one of segmentation models: '
'--m_instance_segmentation or --m_semantic_segmentation')
labels_dir = Path(__file__).resolve().parents[3] / 'data/dataset_classes'
mouse = MouseClick()
if not args.no_show:
cv2.namedWindow(WINNAME)
cv2.setMouseCallback(WINNAME, mouse.get_points)
log.info('OpenVINO Inference Engine')
log.info('\tbuild: {}'.format(get_version()))
core = Core()
model_path = args.m_instance_segmentation if args.m_instance_segmentation else args.m_semantic_segmentation
log.info('Reading model {}'.format(model_path))
if args.m_instance_segmentation:
labels_file = str(labels_dir / 'coco_80cl_bkgr.txt')
segmentation = MaskRCNN(core, args.m_instance_segmentation, labels_file,
args.threshold, args.device, args.cpu_extension)
elif args.m_semantic_segmentation:
labels_file = str(labels_dir / 'cityscapes_19cl_bkgr.txt')
segmentation = SemanticSegmentation(core, args.m_semantic_segmentation, labels_file,
args.threshold, args.device, args.cpu_extension)
log.info('The model {} is loaded to {}'.format(model_path, args.device))
metrics = PerformanceMetrics()
video_writer = cv2.VideoWriter()
black_board = False
frame_number = 0
key = -1
start_time = perf_counter()
frame = cap.read()
if frame is None:
raise RuntimeError("Can't read an image from the input")
out_frame_size = (frame.shape[1], frame.shape[0] * 2)
output_frame = np.full((frame.shape[0], frame.shape[1], 3), 255, dtype='uint8')
presenter = monitors.Presenter(args.utilization_monitors, 20,
(out_frame_size[0] // 4, out_frame_size[1] // 16))
if args.output and not video_writer.open(args.output, cv2.VideoWriter_fourcc(*'MJPG'),
cap.fps(), out_frame_size):
raise RuntimeError("Can't open video writer")
while frame is not None:
mask = None
detections = segmentation.get_detections([frame])
expand_mask(detections, frame.shape[1] // 27)
if len(detections[0]) > 0:
mask = detections[0][0][2]
for i in range(1, len(detections[0])):
mask = cv2.bitwise_or(mask, detections[0][i][2])
if mask is not None:
mask = np.stack([mask, mask, mask], axis=-1)
else:
mask = np.zeros(frame.shape, dtype='uint8')
clear_frame = remove_background(frame, invert_colors=not black_board)
output_frame = np.where(mask, output_frame, clear_frame)
merged_frame = np.vstack([frame, output_frame])
merged_frame = cv2.resize(merged_frame, out_frame_size)
metrics.update(start_time, merged_frame)
if video_writer.isOpened() and (args.output_limit <= 0 or frame_number <= args.output_limit-1):
video_writer.write(merged_frame)
presenter.drawGraphs(merged_frame)
if not args.no_show:
cv2.imshow(WINNAME, merged_frame)
key = check_pressed_keys(key)
if key == 27: # 'Esc'
break
if key == ord('i'): # catch pressing of key 'i'
black_board = not black_board
output_frame = 255 - output_frame
else:
presenter.handleKey(key)
if mouse.crop_available:
x0, x1 = min(mouse.points[0][0], mouse.points[1][0]), \
max(mouse.points[0][0], mouse.points[1][0])
y0, y1 = min(mouse.points[0][1], mouse.points[1][1]), \
max(mouse.points[0][1], mouse.points[1][1])
x1, y1 = min(x1, output_frame.shape[1] - 1), min(y1, output_frame.shape[0] - 1)
board = output_frame[y0: y1, x0: x1, :]
if board.shape[0] > 0 and board.shape[1] > 0:
cv2.namedWindow('Board', cv2.WINDOW_KEEPRATIO)
cv2.imshow('Board', board)
frame_number += 1
start_time = perf_counter()
frame = cap.read()
metrics.log_total()
for rep in presenter.reportMeans():
log.info(rep)
def main():
current_dir = os.path.dirname(os.path.abspath(__file__))
"""Prepares data for the object tracking demo"""
parser = argparse.ArgumentParser(description='Multi camera multi object \
tracking live demo script')
parser.add_argument(
'-i',
'--input',
required=True,
nargs='+',
help=
'Required. Input sources (indexes of cameras or paths to video files)')
parser.add_argument('--loop',
default=False,
action='store_true',
help='Optional. Enable reading the input in a loop')
parser.add_argument('--config',
type=str,
default=os.path.join(current_dir, 'configs/person.py'),
required=False,
help='Configuration file')
parser.add_argument('--detections',
type=str,
help='JSON file with bounding boxes')
parser.add_argument('-m',
'--m_detector',
type=str,
required=False,
help='Path to the object detection model')
parser.add_argument('--t_detector',
type=float,
default=0.6,
help='Threshold for the object detection model')
parser.add_argument('--m_segmentation',
type=str,
required=False,
help='Path to the object instance segmentation model')
parser.add_argument(
'--t_segmentation',
type=float,
default=0.6,
help='Threshold for object instance segmentation model')
parser.add_argument(
'--m_reid',
type=str,
required=True,
help='Required. Path to the object re-identification model')
parser.add_argument('--output_video',
type=str,
default='',
required=False,
help='Optional. Path to output video')
parser.add_argument(
'--history_file',
type=str,
default='',
required=False,
help='Optional. Path to file in JSON format to save results of the demo'
)
parser.add_argument(
'--save_detections',
type=str,
default='',
required=False,
help='Optional. Path to file in JSON format to save bounding boxes')
parser.add_argument("--no_show",
help="Optional. Don't show output",
action='store_true')
parser.add_argument('-d', '--device', type=str, default='CPU')
parser.add_argument('-u',
'--utilization_monitors',
default='',
type=str,
help='Optional. List of monitors to show initially.')
args = parser.parse_args()
if check_detectors(args) != 1:
sys.exit(1)
if len(args.config):
log.debug('Reading config from {}'.format(args.config))
config = read_py_config(args.config)
else:
log.error(
'No configuration file specified. Please specify parameter \'--config\''
)
sys.exit(1)
random.seed(config.random_seed)
capture = MulticamCapture(args.input, args.loop)
log.info('OpenVINO Runtime')
log.info('\tbuild: {}'.format(get_version()))
core = Core()
if args.detections:
object_detector = DetectionsFromFileReader(args.detections,
args.t_detector)
elif args.m_segmentation:
object_detector = MaskRCNN(core, args.m_segmentation,
config.obj_segm.trg_classes,
args.t_segmentation, args.device,
capture.get_num_sources())
else:
object_detector = Detector(core, args.m_detector,
config.obj_det.trg_classes, args.t_detector,
args.device, capture.get_num_sources())
if args.m_reid:
object_recognizer = VectorCNN(core, args.m_reid, args.device)
else:
object_recognizer = None
run(args, config, capture, object_detector, object_recognizer)
def main():
parser = argparse.ArgumentParser(description='Whiteboard inpainting demo')
parser.add_argument('-i', type=str, help='Input sources (index of camera \
or path to a video file)', required=True)
parser.add_argument('-m_i', '--m_instance_segmentation', type=str, required=False,
help='Path to the instance segmentation model')
parser.add_argument('-m_s', '--m_semantic_segmentation', type=str, required=False,
help='Path to the semantic segmentation model')
parser.add_argument('-t', '--threshold', type=float, default=0.6,
help='Threshold for person instance segmentation model')
parser.add_argument('--output_video', type=str, default='', required=False,
help='Optional. Path to output video')
parser.add_argument("--no_show", help="Optional. Don't show output", action='store_true')
parser.add_argument('-d', '--device', type=str, default='CPU',
help='Optional. Specify a target device to infer on. CPU, GPU, FPGA, HDDL or MYRIAD is '
'acceptable. The demo will look for a suitable plugin for the device specified')
parser.add_argument('-l', '--cpu_extension', type=str, default=None,
help='MKLDNN (CPU)-targeted custom layers.Absolute \
path to a shared library with the kernels impl.')
parser.add_argument('-u', '--utilization_monitors', default='', type=str,
help='Optional. List of monitors to show initially')
args = parser.parse_args()
capture = VideoCapture(args.i)
if bool(args.m_instance_segmentation) == bool(args.m_semantic_segmentation):
raise ValueError('Set up exactly one of segmentation models: '\
'--m_instance_segmentation or --m_semantic_segmentation')
frame_size, fps = capture.get_source_parameters()
out_frame_size = (int(frame_size[0]), int(frame_size[1] * 2))
presenter = monitors.Presenter(args.utilization_monitors, 20,
(out_frame_size[0] // 4, out_frame_size[1] // 16))
root_dir = osp.dirname(osp.abspath(__file__))
mouse = MouseClick()
if not args.no_show:
cv2.namedWindow(WINNAME)
cv2.setMouseCallback(WINNAME, mouse.get_points)
if args.output_video:
fourcc = cv2.VideoWriter_fourcc(*'XVID')
output_video = cv2.VideoWriter(args.output_video, fourcc, fps, out_frame_size)
else:
output_video = None
log.info("Initializing Inference Engine")
ie = IECore()
if args.m_instance_segmentation:
labels_file = osp.join(root_dir, 'coco_labels.txt')
segmentation = MaskRCNN(ie, args.m_instance_segmentation, labels_file,
args.threshold, args.device, args.cpu_extension)
elif args.m_semantic_segmentation:
labels_file = osp.join(root_dir, 'cityscapes_labels.txt')
segmentation = SemanticSegmentation(ie, args.m_semantic_segmentation, labels_file,
args.threshold, args.device, args.cpu_extension)
black_board = False
output_frame = np.full((frame_size[1], frame_size[0], 3), 255, dtype='uint8')
frame_number = 0
key = -1
while True:
start = time.time()
_, frame = capture.get_frame()
mask = None
if frame is not None:
detections = segmentation.get_detections([frame])
expand_mask(detections, frame_size[0] // 27)
if len(detections[0]) > 0:
mask = detections[0][0][2]
for i in range(1, len(detections[0])):
mask = cv2.bitwise_or(mask, detections[0][i][2])
else:
break
if mask is not None:
mask = np.stack([mask, mask, mask], axis=-1)
else:
mask = np.zeros(frame.shape, dtype='uint8')
clear_frame = remove_background(frame, invert_colors=not black_board)
output_frame = np.where(mask, output_frame, clear_frame)
merged_frame = np.vstack([frame, output_frame])
merged_frame = cv2.resize(merged_frame, out_frame_size)
if output_video is not None:
output_video.write(merged_frame)
presenter.drawGraphs(merged_frame)
if not args.no_show:
cv2.imshow(WINNAME, merged_frame)
key = check_pressed_keys(key)
if key == 27: # 'Esc'
break
if key == ord('i'): # catch pressing of key 'i'
black_board = not black_board
output_frame = 255 - output_frame
else:
presenter.handleKey(key)
if mouse.crop_available:
x0, x1 = min(mouse.points[0][0], mouse.points[1][0]), \
max(mouse.points[0][0], mouse.points[1][0])
y0, y1 = min(mouse.points[0][1], mouse.points[1][1]), \
max(mouse.points[0][1], mouse.points[1][1])
x1, y1 = min(x1, output_frame.shape[1] - 1), min(y1, output_frame.shape[0] - 1)
board = output_frame[y0: y1, x0: x1, :]
if board.shape[0] > 0 and board.shape[1] > 0:
cv2.namedWindow('Board', cv2.WINDOW_KEEPRATIO)
cv2.imshow('Board', board)
end = time.time()
print('\rProcessing frame: {}, fps = {:.3}' \
.format(frame_number, 1. / (end - start)), end="")
frame_number += 1
print('')
log.info(presenter.reportMeans())
if output_video is not None:
output_video.release()
