yolov5 绘制警戒区域

最新推荐文章于 2024-05-04 15:45:54 发布

fengwenyuan123

最新推荐文章于 2024-05-04 15:45:54 发布

阅读量574

点赞数 7

文章标签： YOLO opencv 计算机视觉

本文链接：https://blog.youkuaiyun.com/2301_79558841/article/details/135815574

版权

import cv2
import numpy as np

# 加载YOLOv5模型
net = cv2.dnn.readNetFromDarknet('yolov5.cfg', 'yolov5.weights')

# 获取输出层信息
layer_names = net.getLayerNames()
output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# 加载图像
image = cv2.imread('image.jpg')

# 对图像进行预处理
blob = cv2.dnn.blobFromImage(image, 1/255.0, (416, 416), swapRB=True, crop=False)

# 将预处理后的图像输入到网络中
net.setInput(blob)

# 运行前向传播
outs = net.forward(output_layers)

# 解析输出结果
class_ids = []
confidences = []
boxes = []
for out in outs:
    for detection in out:
        scores = detection[5:]
        class_id = np.argmax(scores)
        confidence = scores[class_id]
        if confidence > 0.5:
            # 获取目标框的坐标和宽高
            center_x = int(detection[0] * image.shape[1])
            center_y = int(detection[1] * image.shape[0])
            width = int(detection[2] * image.shape[1])
            height = int(detection[3] * image.shape[0])
            # 计算目标框的左上角坐标
            x = int(center_x - width / 2)
            y = int(center_y - height / 2)
            # 保存目标框的信息
            class_ids.append(class_id)
            confidences.append(float(confidence))
            boxes.append([x, y, width, height])

# 绘制警戒区域
for box in boxes:
    x, y, width, height = box
    cv2.rectangle(image, (x, y), (x + width, y + height), (0, 255, 0), 2)

# 显示结果图像
cv2.imshow('image', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

请注意，上述代码中的yolov5.cfg和yolov5.weights是YOLOv5模型的配置文件和权重文件，需要根据实际情况进行替换。另外，image.jpg是输入图像的文件名，我们也需要将其替换为自己的图像文件。