12.12音视频内容结构化分析选购

import cv2

# 加载预训练模型
net = cv2.dnn.readNetFromCaffe('deploy.prototxt', 'res10_300x300_ssd_iter_140000.caffemodel')

# 打开摄像头
cap = cv2.VideoCapture(0)

while True:
    ret, frame = cap.read()
    if not ret:
        break

    # 预处理图像
    blob = cv2.dnn.blobFromImage(cv2.resize(frame, (300, 300)), 1.0, (300, 300), (104.0, 177.0, 123.0))

    # 设置输入并进行推理
    net.setInput(blob)
    detections = net.forward()

    # 处理检测结果
    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > 0.5:
            box = detections[0, 0, i, 3:7] * np.array([frame.shape[1], frame.shape[0], frame.shape[1], frame.shape[0]])
            (x, y, x1, y1) = box.astype("int")
            cv2.rectangle(frame, (x, y), (x1, y1), (0, 255, 0), 2)

    # 显示结果
    cv2.imshow('Frame', frame)

    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()