245 lines
No EOL
10 KiB
Python
245 lines
No EOL
10 KiB
Python
import argparse
|
|
import cv2
|
|
import os
|
|
os.environ["OMP_NUM_THREADS"] = "1"
|
|
os.environ["OPENBLAS_NUM_THREADS"] = "1"
|
|
os.environ["MKL_NUM_THREADS"] = "1"
|
|
os.environ["VECLIB_MAXIMUM_THREADS"] = "1"
|
|
os.environ["NUMEXPR_NUM_THREADS"] = "1"
|
|
|
|
import sys
|
|
import numpy as np
|
|
from pathlib import Path
|
|
import torch
|
|
|
|
FILE = Path(__file__).resolve()
|
|
ROOT = FILE.parents[0]
|
|
WEIGHTS = ROOT / 'weights'
|
|
|
|
if str(ROOT) not in sys.path:
|
|
sys.path.append(str(ROOT))
|
|
if str(ROOT / 'trackers' / 'strongsort') not in sys.path:
|
|
sys.path.append(str(ROOT / 'trackers' / 'strongsort'))
|
|
|
|
from ultralytics.nn.autobackend import AutoBackend
|
|
from ultralytics.yolo.data.dataloaders.stream_loaders import LoadImages
|
|
from ultralytics.yolo.data.utils import VID_FORMATS
|
|
from ultralytics.yolo.utils import LOGGER, colorstr
|
|
from ultralytics.yolo.utils.checks import check_file, check_imgsz
|
|
from ultralytics.yolo.utils.files import increment_path
|
|
from ultralytics.yolo.utils.torch_utils import select_device
|
|
from ultralytics.yolo.utils.ops import Profile, non_max_suppression, scale_boxes
|
|
from ultralytics.yolo.utils.plotting import Annotator, colors
|
|
|
|
from trackers.multi_tracker_zoo import create_tracker
|
|
from sender.jsonlogger import JsonLogger
|
|
from sender.szmq import ZmqLogger
|
|
|
|
@torch.no_grad()
|
|
def run(
|
|
source='0',
|
|
yolo_weights=WEIGHTS / 'yolov8n.pt',
|
|
reid_weights=WEIGHTS / 'osnet_x0_25_msmt17.pt',
|
|
imgsz=(640, 640),
|
|
conf_thres=0.7,
|
|
iou_thres=0.45,
|
|
max_det=1000,
|
|
device='',
|
|
show_vid=True,
|
|
save_vid=True,
|
|
project=ROOT / 'runs' / 'track',
|
|
name='exp',
|
|
exist_ok=False,
|
|
line_thickness=2,
|
|
hide_labels=False,
|
|
hide_conf=False,
|
|
half=False,
|
|
vid_stride=1,
|
|
enable_json_log=False,
|
|
enable_zmq=False,
|
|
zmq_ip='localhost',
|
|
zmq_port=5555,
|
|
):
|
|
source = str(source)
|
|
is_file = Path(source).suffix[1:] in (VID_FORMATS)
|
|
|
|
if is_file:
|
|
source = check_file(source)
|
|
|
|
device = select_device(device)
|
|
|
|
model = AutoBackend(yolo_weights, device=device, dnn=False, fp16=half)
|
|
stride, names, pt = model.stride, model.names, model.pt
|
|
imgsz = check_imgsz(imgsz, stride=stride)
|
|
|
|
dataset = LoadImages(
|
|
source,
|
|
imgsz=imgsz,
|
|
stride=stride,
|
|
auto=pt,
|
|
transforms=getattr(model.model, 'transforms', None),
|
|
vid_stride=vid_stride
|
|
)
|
|
bs = len(dataset)
|
|
|
|
tracking_config = ROOT / 'trackers' / 'strongsort' / 'configs' / 'strongsort.yaml'
|
|
tracker = create_tracker('strongsort', tracking_config, reid_weights, device, half)
|
|
|
|
save_dir = increment_path(Path(project) / name, exist_ok=exist_ok)
|
|
(save_dir / 'tracks').mkdir(parents=True, exist_ok=True)
|
|
|
|
# Initialize loggers
|
|
json_logger = JsonLogger(f"{source}-strongsort.log") if enable_json_log else None
|
|
zmq_logger = ZmqLogger(zmq_ip, zmq_port) if enable_zmq else None
|
|
|
|
vid_path, vid_writer = [None] * bs, [None] * bs
|
|
dt = (Profile(), Profile(), Profile())
|
|
|
|
for frame_idx, (path, im, im0s, vid_cap, s) in enumerate(dataset):
|
|
|
|
with dt[0]:
|
|
im = torch.from_numpy(im).to(model.device)
|
|
im = im.half() if model.fp16 else im.float()
|
|
im /= 255.0
|
|
if len(im.shape) == 3:
|
|
im = im[None]
|
|
|
|
with dt[1]:
|
|
pred = model(im, augment=False, visualize=False)
|
|
|
|
with dt[2]:
|
|
pred = non_max_suppression(pred, conf_thres, iou_thres, None, False, max_det=max_det)
|
|
|
|
for i, det in enumerate(pred):
|
|
seen = 0
|
|
p, im0, _ = path, im0s.copy(), dataset.count
|
|
p = Path(p)
|
|
|
|
annotator = Annotator(im0, line_width=line_thickness, example=str(names))
|
|
|
|
if len(det):
|
|
# Filter detections for 'car' class only (class 2 in COCO dataset)
|
|
car_mask = det[:, 5] == 2 # car class index is 2
|
|
det = det[car_mask]
|
|
|
|
if len(det):
|
|
det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round()
|
|
|
|
for *xyxy, conf, cls in reversed(det):
|
|
c = int(cls)
|
|
id = f'{c}'
|
|
label = None if hide_labels else (f'{id} {names[c]}' if hide_conf else f'{id} {names[c]} {conf:.2f}')
|
|
annotator.box_label(xyxy, label, color=colors(c, True))
|
|
|
|
t_outputs = tracker.update(det.cpu(), im0)
|
|
|
|
if len(t_outputs) > 0:
|
|
for j, (output) in enumerate(t_outputs):
|
|
bbox = output[0:4]
|
|
id = output[4]
|
|
cls = output[5]
|
|
conf = output[6]
|
|
|
|
# Log tracking data
|
|
if json_logger or zmq_logger:
|
|
track_data = {
|
|
'bbox': bbox.tolist() if hasattr(bbox, 'tolist') else list(bbox),
|
|
'id': int(id),
|
|
'cls': int(cls),
|
|
'conf': float(conf),
|
|
'frame_idx': frame_idx,
|
|
'source': source,
|
|
'class_name': names[int(cls)]
|
|
}
|
|
|
|
if json_logger:
|
|
json_logger.send(track_data)
|
|
if zmq_logger:
|
|
zmq_logger.send(track_data)
|
|
|
|
if save_vid or show_vid:
|
|
c = int(cls)
|
|
id = int(id)
|
|
label = f'{id} {names[c]}' if not hide_labels else f'{id}'
|
|
if not hide_conf:
|
|
label += f' {conf:.2f}'
|
|
annotator.box_label(bbox, label, color=colors(c, True))
|
|
|
|
im0 = annotator.result()
|
|
|
|
if show_vid:
|
|
cv2.imshow(str(p), im0)
|
|
if cv2.waitKey(1) == ord('q'):
|
|
break
|
|
|
|
if save_vid:
|
|
if vid_path[i] != str(save_dir / p.name):
|
|
vid_path[i] = str(save_dir / p.name)
|
|
if isinstance(vid_writer[i], cv2.VideoWriter):
|
|
vid_writer[i].release()
|
|
|
|
if vid_cap:
|
|
fps = vid_cap.get(cv2.CAP_PROP_FPS)
|
|
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
|
|
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
|
|
else:
|
|
fps, w, h = 30, im0.shape[1], im0.shape[0]
|
|
|
|
vid_writer[i] = cv2.VideoWriter(vid_path[i], cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
|
|
|
|
vid_writer[i].write(im0)
|
|
|
|
LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms")
|
|
|
|
for i, vid_writer_obj in enumerate(vid_writer):
|
|
if isinstance(vid_writer_obj, cv2.VideoWriter):
|
|
vid_writer_obj.release()
|
|
|
|
cv2.destroyAllWindows()
|
|
|
|
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")
|
|
|
|
def xyxy2xywh(x):
|
|
# Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
|
|
y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
|
|
y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
|
|
y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
|
|
y[:, 2] = x[:, 2] - x[:, 0] # width
|
|
y[:, 3] = x[:, 3] - x[:, 1] # height
|
|
return y
|
|
|
|
def parse_opt():
|
|
parser = argparse.ArgumentParser()
|
|
parser.add_argument('--source', type=str, default='0', help='file/dir/URL/glob, 0 for webcam')
|
|
parser.add_argument('--yolo-weights', nargs='+', type=str, default=WEIGHTS / 'yolov8n.pt', help='model path')
|
|
parser.add_argument('--reid-weights', type=str, default=WEIGHTS / 'osnet_x0_25_msmt17.pt')
|
|
parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
|
|
parser.add_argument('--conf-thres', type=float, default=0.7, help='confidence threshold')
|
|
parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold')
|
|
parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image')
|
|
parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
|
|
parser.add_argument('--show-vid', action='store_true', help='display results')
|
|
parser.add_argument('--save-vid', action='store_true', help='save video tracking results')
|
|
parser.add_argument('--project', default=ROOT / 'runs' / 'track', help='save results to project/name')
|
|
parser.add_argument('--name', default='exp', help='save results to project/name')
|
|
parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
|
|
parser.add_argument('--line-thickness', default=2, type=int, help='bounding box thickness (pixels)')
|
|
parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels')
|
|
parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences')
|
|
parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference')
|
|
parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride')
|
|
parser.add_argument('--enable-json-log', action='store_true', help='enable JSON file logging')
|
|
parser.add_argument('--enable-zmq', action='store_true', help='enable ZMQ messaging')
|
|
parser.add_argument('--zmq-ip', type=str, default='localhost', help='ZMQ server IP')
|
|
parser.add_argument('--zmq-port', type=int, default=5555, help='ZMQ server port')
|
|
|
|
opt = parser.parse_args()
|
|
opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1
|
|
return opt
|
|
|
|
def main(opt):
|
|
run(**vars(opt))
|
|
|
|
if __name__ == "__main__":
|
|
opt = parse_opt()
|
|
main(opt) |