yolo v8 webcam read

你可以使用以下代码片段来使用YOLO v8模型读取网络摄像头中的视频流：

import cv2
import numpy as np

# 加载YOLO v3配置和权重文件
net = cv2.dnn.readNetFromDarknet('yolov3.cfg', 'yolov3.weights')

# 获取输出层的名称
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]
# 打开网络摄像头
cap = cv2.VideoCapture(0)

while True:
    # 读取视频帧
    ret, frame = cap.read()

    # 对帧进行预处理
    blob = cv2.dnn.blobFromImage(frame, 0.00392, (416, 416), (0, 0, 0), True, crop=False)
    net.setInput(blob)
    outs = net.forward(output_layers)

    # 解析输出并绘制边界框
    class_ids = []
    confidences = []
    boxes = []
    height, width, channels = frame.shape
    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > 0.5:
                # 检测到对象
                center_x = int(detection[0] * width)
                center_y = int(detection[1] * height)
                w = int(detection[2] * width)
                h = int(detection[3] * height)

                # 边界框的坐标
                x = int(center_x - w / 2)
                y = int(center_y - h / 2)

                boxes.append([x, y, w, h])
                confidences.append(float(confidence))
                class_ids.append(class_id)

    indexes = cv2.dnn.NMSBoxes(boxes, confidences, 0.5, 0.4)
    font = cv2.FONT_HERSHEY_SIMPLEX
    for i in range(len(boxes)):
        if i in indexes:
            x, y, w, h = boxes[i]
            label = str(class_ids[i])
            confidence = confidences[i]
            color = (255, 0, 0)  # 边界框颜色为红色
            cv2.rectangle(frame, (x, y), (x + w, y + h), color, 2)
            cv2.putText(frame, label + ' ' + str(round(confidence, 2)), (x, y - 10), font, 0.5, color, 2)

    # 显示输出图像
    cv2.imshow('YOLO v3', frame)

    # 按下q键退出循环
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放资源
cap.release()
cv2.destroyAllWindows()

请确保你已经下载了YOLO v3的配置文件（`yolov3.cfg`）和权重文件（`yolov3.weights`），并将其放在与你的代码相同的目录下。此代码将从网络摄像头中读取视频流，并在检测到的对象周围绘制边界框。