yolov5-7.0调用摄像头的代码

### YOLOv5 7.0 调用摄像头 Python 示例代码

为了使用YOLOv5版本7.0调用摄像头并执行实时目标检测，可以采用Python脚本实现这一功能。下面提供了一个具体的例子来展示如何操作：

import torch
from utils.general import non_max_suppression, scale_coords
from models.experimental import attempt_load
import cv2
import numpy as np


def letterbox(img, new_shape=(640, 640), color=(114, 114, 114)):
    shape = img.shape[:2]  # current shape [height, width]

    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
    ratio = r, r  # width, height ratios
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding

    dw /= 2  # divide padding into 2 sides
    dh /= 2

    if shape[::-1] != new_unpad:  # resize
        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)

    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))

    img = cv2.copyMakeBorder(
        img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color
    )  # add border
    return img, ratio, (dw, dh)


device = 'cuda' if torch.cuda.is_available() else 'cpu'
model = attempt_load('yolov5s.pt', map_location=device)  # 加载预训练模型[^1]
cap = cv2.VideoCapture(0)  # 打开默认摄像头

while cap.isOpened():
    ret, frame = cap.read()
    if not ret:
        break
    
    img = letterbox(frame)[0]
    
    img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
    img = np.ascontiguousarray(img)
    
    img = torch.from_numpy(img).to(device)
    img = img.float()  # uint8 to fp16/32
    img /= 255.0  # 归一化处理
    
    if img.ndimension() == 3:
        img = img.unsqueeze(0)

    pred = model(img)[0]
    pred = non_max_suppression(pred, conf_thres=0.25, iou_thres=0.45)

    for i, det in enumerate(pred):  # detections per image
        gn = torch.tensor(frame.shape)[[1, 0, 1, 0]]  # normalization gain whwh
        
        if len(det):
            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], frame.shape).round()

            for *xyxy, conf, cls in reversed(det):
                label = f'{conf:.2f}'
                
                plot_one_box(xyxy, frame, label=label, color=[0, 255, 0])  # 绘制边界框
                
    cv2.imshow("Frame", frame)
    
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

cap.release()
cv2.destroyAllWindows()

此段代码实现了通过摄像头捕获视频流，并利用加载好的YOLOv5模型对其进行逐帧的目标检测。对于每一帧图像，在完成必要的预处理之后将其送入模型预测；接着对输出的结果应用非极大值抑制（NMS），从而筛选出高质量的候选区域；最后将这些区域映射回原图尺寸，并在画面上标注出来。