Python和OpenCV库实现识别人物出现并锁定

pip install opencv-python
pip install imutils

import cv2
import imutils

video_path = "path/to/your/video.mp4"

# 打开视频
cap = cv2.VideoCapture(video_path)

while True:
    ret, frame = cap.read()

    if not ret:
        break

    # 缩放以提高处理速度
    frame = imutils.resize(frame, width=600)

    cv2.imshow("Input Video", frame)

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

cap.release()
cv2.destroyAllWindows()

prototxt_path = "path/to/your/MobileNetSSD_deploy.prototxt"
model_path = "path/to/your/MobileNetSSD_deploy.caffemodel"

# 加载预训练模型
net = cv2.dnn.readNetFromCaffe(prototxt_path, model_path)

# 设置置信度阈值
confidence_threshold = 0.5

while True:
    ret, frame = cap.read()

    if not ret:
        break

    frame = imutils.resize(frame, width=600)
    (h, w) = frame.shape[:2]

    # 将图像转换为blob
    blob = cv2.dnn.blobFromImage(frame, 0.007843, (w, h), 127.5)

    net.setInput(blob)
    detections = net.forward()

    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        if confidence > confidence_threshold:
            idx = int(detections[0, 0, i, 1])

            if idx == 15:  # 15 代表人类
                box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
                (startX, startY, endX, endY) = box.astype("int")

                # 在检测到的人物周围绘制边界框
                cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 255, 0), 2)

    cv2.imshow("Input Video", frame)

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

# 创建 VideoWriter 对象以保存处理后的视频
fourcc = cv2.VideoWriter_fourcc(*"mp4v")
out = cv2.VideoWriter("output.mp4", fourcc, 30, (w, h))

while True:
    ret, frame = cap.read()

    if not ret:
        break

    frame = imutils.resize(frame, width=600)
    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(frame, 0.007843, (w, h), 127.5)

    net.setInput(blob)
    detections = net.forward()

    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        if confidence > confidence_threshold:
            idx = int(detections[0, 0, i, 1])

            if idx == 15:
                box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
                (startX, startY, endX, endY) = box.astype("int")
                cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 255, 0), 2)

    # 将帧写入输出视频
    out.write(frame)

    cv2.imshow("Input Video", frame)

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

cap.release()
out.release()
cv2.destroyAllWindows()