75 lines
3.3 KiB
Python
75 lines
3.3 KiB
Python
|
"""Camera 01 录像：直接 YOLO 与共享实时缩图管线的一致性抽样验证。
|
|||
|
|
|
|||
|
|
手动运行：python tests/validate_yolo_replay.py <video> <weights> [sample_count] [device]
|
|||
|
|
"""
|
|||
|
|
import sys
|
|||
|
|
|
|||
|
|
import cv2
|
|||
|
|
from ultralytics import YOLO
|
|||
|
|
|
|||
|
|
|
|||
|
|
def iou(a, b):
|
|||
|
|
x1, y1, x2, y2 = max(a[0], b[0]), max(a[1], b[1]), min(a[2], b[2]), min(a[3], b[3])
|
|||
|
|
inter = max(0, x2 - x1) * max(0, y2 - y1)
|
|||
|
|
union = (a[2] - a[0]) * (a[3] - a[1]) + (b[2] - b[0]) * (b[3] - b[1]) - inter
|
|||
|
|
return inter / union if union > 0 else 0
|
|||
|
|
|
|||
|
|
|
|||
|
|
def boxes(result):
|
|||
|
|
if result.boxes is None:
|
|||
|
|
return []
|
|||
|
|
return [list(map(float, row)) for row in result.boxes.xyxy.cpu().numpy()]
|
|||
|
|
|
|||
|
|
|
|||
|
|
def main(video_path, weights_path, sample_count=5, device="cpu"):
|
|||
|
|
model = YOLO(weights_path)
|
|||
|
|
names = model.names if isinstance(model.names, dict) else dict(enumerate(model.names))
|
|||
|
|
person_ids = [cid for cid, name in names.items() if name == "person"]
|
|||
|
|
cap = cv2.VideoCapture(video_path)
|
|||
|
|
total = int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
|
|||
|
|
indices = [int((i + 1) * total / (sample_count + 1)) for i in range(sample_count)]
|
|||
|
|
direct_count = matched_count = 0
|
|||
|
|
matched_ious = []
|
|||
|
|
for index in indices:
|
|||
|
|
cap.set(cv2.CAP_PROP_POS_FRAMES, index)
|
|||
|
|
ok, frame = cap.read()
|
|||
|
|
if not ok:
|
|||
|
|
continue
|
|||
|
|
h, w = frame.shape[:2]
|
|||
|
|
precision = 16 if str(device).lower() != "cpu" else None
|
|||
|
|
direct = boxes(model.predict(frame, imgsz=640, conf=.3, iou=.5,
|
|||
|
|
classes=person_ids, device=device,
|
|||
|
|
quantize=precision, verbose=False)[0])
|
|||
|
|
scale = min(1.0, 2560.0 / max(w, h))
|
|||
|
|
small = (frame if scale == 1.0 else
|
|||
|
|
cv2.resize(frame, (int(w * scale), int(h * scale)), interpolation=cv2.INTER_AREA))
|
|||
|
|
ok, encoded = cv2.imencode(".jpg", small, [cv2.IMWRITE_JPEG_QUALITY, 95])
|
|||
|
|
realtime = boxes(model.predict(cv2.imdecode(encoded, cv2.IMREAD_COLOR), imgsz=640,
|
|||
|
|
conf=.3, iou=.5, classes=person_ids,
|
|||
|
|
device=device, quantize=precision,
|
|||
|
|
verbose=False)[0]) if ok else []
|
|||
|
|
realtime = [[v / scale for v in box] for box in realtime]
|
|||
|
|
unused = set(range(len(realtime)))
|
|||
|
|
for box in direct:
|
|||
|
|
direct_count += 1
|
|||
|
|
candidates = [(iou(box, realtime[j]), j) for j in unused]
|
|||
|
|
best = max(candidates, default=(0, None))
|
|||
|
|
if best[0] >= .8:
|
|||
|
|
matched_count += 1
|
|||
|
|
matched_ious.append(best[0])
|
|||
|
|
unused.remove(best[1])
|
|||
|
|
print("frame=%d direct_person=%d realtime_person=%d" % (index, len(direct), len(realtime)))
|
|||
|
|
cap.release()
|
|||
|
|
recall = matched_count / direct_count if direct_count else 1.0
|
|||
|
|
mean_iou = sum(matched_ious) / len(matched_ious) if matched_ious else 0.0
|
|||
|
|
print("matched=%d/%d recall=%.3f mean_iou=%.3f" %
|
|||
|
|
(matched_count, direct_count, recall, mean_iou))
|
|||
|
|
return 0 if recall >= .95 and (not matched_ious or min(matched_ious) >= .8) else 1
|
|||
|
|
|
|||
|
|
|
|||
|
|
if __name__ == "__main__":
|
|||
|
|
if len(sys.argv) < 3:
|
|||
|
|
raise SystemExit("usage: validate_yolo_replay.py VIDEO WEIGHTS [SAMPLES] [DEVICE]")
|
|||
|
|
raise SystemExit(main(sys.argv[1], sys.argv[2], int(sys.argv[3]) if len(sys.argv) > 3 else 5,
|
|||
|
|
sys.argv[4] if len(sys.argv) > 4 else "cpu"))
|