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',
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, '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='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('-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:
object_detector = DetectionsFromFileReader(args.detections,
args.t_detector)
elif args.m_segmentation:
object_detector = MaskRCNN(ie, args.m_segmentation,
config['obj_segm']['trg_classes'],
args.t_segmentation,
args.device, args.cpu_extension,
capture.get_num_sources())
else:
object_detector = Detector(ie, args.m_detector,
config['obj_det']['trg_classes'],
args.t_detector,
args.device, args.cpu_extension,
capture.get_num_sources())
if args.m_reid:
object_recognizer = VectorCNN(ie, args.m_reid, args.device,
args.cpu_extension)
else:
object_recognizer = None
run(args, config, capture, object_detector, object_recognizer)
log.info('Demo finished successfully')
def main():
"""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('-m', '--m_detector', type=str, required=True, help='Path to the person detection model')
parser.add_argument('-m',
'--m_detector',
type=str,
default='model/person-detection-retail-0013.xml')
parser.add_argument('--t_detector',
type=float,
default=0.6,
help='Threshold for the person detection model')
#parser.add_argument('--m_reid', type=str, required=True, help='Path to the person reidentification model')
parser.add_argument(
'--m_reid',
type=str,
default='model/person-reidentification-retail-0031.xml')
parser.add_argument('--output_video', type=str, default='', required=False)
#parser.add_argument('--config', type=str, default='', required=False)
parser.add_argument('--config',
type=str,
default='config.py',
required=False)
parser.add_argument('--history_file', type=str, default='', required=False)
parser.add_argument('-d', '--device', type=str, default='CPU')
#parser.add_argument('-d', '--device', type=str, default='MYRIAD')
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("--no_show",
help="Optional. Don't show output",
action='store_true')
args = parser.parse_args()
# 위에서 가져온 옵션에 대한 것들 args에 저장됨.
# args.i 해서 옵션 i 에 저장된것 가져올 수 있음
capture = MulticamCapture(
args.i) # video.py 에 있는 클래스 변수에 포인터 지정함. capture 호출해서 그 안에 있는 함수 사용가능
log.info("Creating Inference Engine")
ie = IECore(
) #추론엔진 인터페이스 지정하기 (https://docs.openvinotoolkit.org/2019_R3/classie__api_1_1IECore.html)
person_detector = Detector(ie, args.m_detector, args.t_detector,
args.device, args.cpu_extension,
capture.get_num_sources())
# capture.get_num_sources() : 영상의 갯수
if args.m_reid:
person_recognizer = VectorCNN(ie, args.m_reid, args.device)
else:
person_recognizer = None
# 20200511 추가
jot = JotTable()
run(args, capture, person_detector, person_recognizer, jot)
log.info('Demo finished successfully')
def main():
"""Visualize the results of the multi camera multi person tracker demo"""
parser = argparse.ArgumentParser(description='Multi camera multi person \
tracking visualization demo script'
)
parser.add_argument('-i', type=str, nargs='+', help='Input videos')
parser.add_argument('--history_file',
type=str,
default='',
required=True,
help='File with tracker history')
parser.add_argument('--output_video',
type=str,
default='',
required=False,
help='Output video file')
parser.add_argument('--gt_files',
type=str,
nargs='+',
required=False,
help='Files with ground truth annotation')
parser.add_argument('--timeline',
type=str,
default='',
help='Plot and save timeline')
parser.add_argument('--match_gt_ids',
default=False,
action='store_true',
help='Match GT ids to ids from history')
parser.add_argument('--merge_outputs',
default=False,
action='store_true',
help='Merge GT and history tracks into one frame')
args = parser.parse_args()
capture = MulticamCapture(args.i)
with open(args.history_file) as hist_f:
history = json.load(hist_f)
assert len(history) == capture.get_num_sources()
output_video = None
output_video_gt = None
frames_read = False
set_output_params = False
# Read GT tracks if necessary
if args.gt_files:
assert len(args.gt_files) == capture.get_num_sources()
gt_tracks, _ = read_gt_tracks(args.gt_files)
accs = [mm.MOTAccumulator(auto_id=True) for _ in args.gt_files]
else:
gt_tracks = None
# If we need for matching GT IDs, accumulate metrics
if gt_tracks and args.match_gt_ids:
accumulate_mot_metrics(accs, gt_tracks, history)
match_gt_indices(gt_tracks, history, accs)
metrics_accumulated = True
else:
metrics_accumulated = False
# Process frames
win_name = 'Multi camera tracking history visualizer'
time = 0
key = -1
while True:
print('\rVisualizing frame: {}'.format(time), end="")
key = check_pressed_keys(key)
if key == 27:
break
has_frames, frames = capture.get_frames()
frames_read = True
if not has_frames:
break
if gt_tracks:
gt_detections = get_detections_from_tracks(gt_tracks, time)
vis_gt = visualize_multicam_detections(copy.deepcopy(frames),
gt_detections,
fps='Ground truth')
else:
vis_gt = None
active_detections = get_detections_from_tracks(history, time)
vis = visualize_multicam_detections(frames, active_detections)
if vis_gt is not None:
if args.merge_outputs:
vis = np.hstack([vis, vis_gt])
cv.imshow(win_name, vis)
else:
cv.imshow('GT', vis_gt)
cv.imshow(win_name, vis)
else:
cv.imshow(win_name, vis)
time += 1
if frames_read and not set_output_params:
set_output_params = True
if len(args.output_video):
frame_size = [frame.shape[::-1] for frame in frames]
fps_source = capture.get_fps()
video_output_size, fps = calc_output_video_params(
frame_size, fps_source, args.gt_files, args.merge_outputs)
fourcc = cv.VideoWriter_fourcc(*'XVID')
output_video = cv.VideoWriter(args.output_video, fourcc, fps,
video_output_size)
if args.gt_files and not args.merge_outputs:
ext = args.output_video.split('.')[-1]
output_path = args.output_video[:len(args.output_video) -
len(ext) -
1] + '_gt.' + ext
output_video_gt = cv.VideoWriter(output_path, fourcc, fps,
video_output_size)
if output_video:
output_video.write(cv.resize(vis, video_output_size))
if vis_gt is not None and output_video_gt is not None:
output_video_gt.write(cv.resize(vis_gt, video_output_size))
if len(args.timeline):
for i in range(len(history)):
log.info('Source_{}: drawing timeline...'.format(i))
plot_timeline(i,
time,
history[i],
save_path=args.timeline,
name='SCT')
if gt_tracks:
for i in range(len(gt_tracks)):
log.info('GT_{}: drawing timeline...'.format(i))
plot_timeline(i,
time,
gt_tracks[i],
save_path=args.timeline,
name='GT')
if gt_tracks:
if not metrics_accumulated:
accumulate_mot_metrics(accs, gt_tracks, history)
mh = mm.metrics.create()
summary = mh.compute_many(
accs,
metrics=mm.metrics.motchallenge_metrics,
generate_overall=True,
names=['video ' + str(i) for i in range(len(accs))])
strsummary = mm.io.render_summary(
summary,
formatters=mh.formatters,
namemap=mm.io.motchallenge_metric_names)
print(strsummary)
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)