yolo读取视频并检测

from time import sleep
import cv2 as cv, torch
from ultralytics import YOLO
import logging
import time

logging.basicConfig(
    level=logging.INFO, format="%(asctime)s - %(name)s - %(levelname)s - %(message)s"
)
log = logging.getLogger(__name__)

# log.info("-- OpenCV Info --")
# log.info(cv.getBuildInformation())
# log.info("-" * 50)

# device = "cuda:0" if torch.cuda.is_available() else "cpu"
# log.info(f"Using device: {device}")

yolo_model = YOLO("./yolo_model/yolo11s.pt")
image_size = 640
yolo_model.overrides["imgsz"] = image_size

cls_map = {
    0: "person",
    1: "bicycle",
    2: "car",
    3: "motorcycle",
    5: "bus",
    7: "truck",
}

# 帧率
FPS_TARGET = 12
# 帧间隔
T_INTERVAL = 1.0 / FPS_TARGET
#  上一次时间
last_t = time.time()
# 检测间隔
detect_every = 3
# 检测计数
detect_count = 0

cap = cv.VideoCapture(
    "https://smart.saas.vppark.cn/oss/1.mp4",
)
 

while cap.isOpened():
    ret, frame = cap.read()
    if not ret:
        break
    # if time.time() - last_t < T_INTERVAL:
    #     continue
    # last_t = time.time()

        
    detect_count += 1
    if detect_count % detect_every == 0 or True:
        # 手动 resize
        h0, w0 = frame.shape[:2]
        scale = min(image_size / h0, image_size / w0)
        h1, w1 = int(h0 * scale), int(w0 * scale)
        frame_resize = cv.resize(frame, (w1, h1), interpolation=cv.INTER_LINEAR)

        # 执行检测
        results = yolo_model(
            frame_resize, imgsz=image_size, classes=list(cls_map.keys())
        )
        # 把框映射回原图
        for result in results:
            boxes_data = result.boxes.data.clone()
            boxes_data[..., :4] /= scale
            result.boxes.data = boxes_data
            react_frame = result.plot(img=frame, line_width=2)
            cv.imshow("frame", react_frame)
    else:
        cv.imshow("frame", frame)
    # if cv.waitKey(int(1000 / FPS_TARGET)) & 0xFF == ord("q"):
    if cv.waitKey(1) & 0xFF == ord("q"):
        break

cap.release()
cv.destroyAllWindows()