如何使用opencv-python中的摄像头分别对红 蓝 黄三种物体进行识别 并对识别到的物体进行形状与颜色标注并进行展示

可以按照以下步骤来实现：

1. 导入所需库

import cv2
import numpy as np

2. 定义颜色范围

# 定义颜色范围
lower_red = np.array([0, 50, 50])
upper_red = np.array([10, 255, 255])
lower_blue = np.array([110, 50, 50])
upper_blue = np.array([130, 255, 255])
lower_yellow = np.array([20, 50, 50])
upper_yellow = np.array([30, 255, 255])

3. 打开摄像头并进行物体识别

# 打开摄像头
cap = cv2.VideoCapture(0)

while True:
    # 读取摄像头中的图像
    ret, frame = cap.read()
    
    # 将图像转换为HSV格式
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)
    
    # 对红色物体进行识别
    mask_red = cv2.inRange(hsv, lower_red, upper_red)
    contours_red, _ = cv2.findContours(mask_red, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    for contour in contours_red:
        area = cv2.contourArea(contour)
        if area > 500:
            # 绘制物体的轮廓
            cv2.drawContours(frame, contour, -1, (0, 0, 255), 2)
            # 获取物体的形状
            approx = cv2.approxPolyDP(contour, 0.015 * cv2.arcLength(contour, True), True)
            corners = len(approx)
            if corners == 3:
                shape = "三角形"
            elif corners == 4:
                shape = "矩形"
            else:
                shape = "圆形"
            # 在物体上方标注形状和颜色
            x, y, w, h = cv2.boundingRect(contour)
            cv2.putText(frame, "Red " + shape, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255), 2)
    
    # 对蓝色物体进行识别
    mask_blue = cv2.inRange(hsv, lower_blue, upper_blue)
    contours_blue, _ = cv2.findContours(mask_blue, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    for contour in contours_blue:
        area = cv2.contourArea(contour)
        if area > 500:
            cv2.drawContours(frame, contour, -1, (255, 0, 0), 2)
            approx = cv2.approxPolyDP(contour, 0.015 * cv2.arcLength(contour, True), True)
            corners = len(approx)
            if corners == 3:
                shape = "三角形"
            elif corners == 4:
                shape = "矩形"
            else:
                shape = "圆形"
            x, y, w, h = cv2.boundingRect(contour)
            cv2.putText(frame, "Blue " + shape, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 0), 2)
    
    # 对黄色物体进行识别
    mask_yellow = cv2.inRange(hsv, lower_yellow, upper_yellow)
    contours_yellow, _ = cv2.findContours(mask_yellow, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    for contour in contours_yellow:
        area = cv2.contourArea(contour)
        if area > 500:
            cv2.drawContours(frame, contour, -1, (0, 255, 255), 2)
            approx = cv2.approxPolyDP(contour, 0.015 * cv2.arcLength(contour, True), True)
            corners = len(approx)
            if corners == 3:
                shape = "三角形"
            elif corners == 4:
                shape = "矩形"
            else:
                shape = "圆形"
            x, y, w, h = cv2.boundingRect(contour)
            cv2.putText(frame, "Yellow " + shape, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 255), 2)
    
    # 显示识别后的图像
    cv2.imshow("Object Detection", frame)
    
    # 按下q键退出程序
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# 释放摄像头并关闭窗口
cap.release()
cv2.destroyAllWindows()

在程序中，首先打开摄像头，然后将读取到的图像转换为HSV格式，接着分别对红色、蓝色和黄色物体进行识别，获取它们的轮廓、形状和颜色，并在物体上方标注出来，最后将识别后的图像展示在窗口中。当按下q键时，程序退出，释放摄像头并关闭窗口。