環境：

• Python：3.7.3
• opencv-python：3.4.6.27

main.py文件

#!/usr/bin/env python # coding: UTF-8 #顯示攝像頭組件 import cv2 import sys, os HSV_Configwidgets_path = os.getcwd() sys.path.append(HSV_Configwidgets_path) from time import time from IPython.display import display import HSV_Configimage = cv2.VideoCapture(0)image.set(3, 320) image.set(4, 240) image.set(5, 30) #設置幀率 image.set(cv2.CAP_PROP_FOURCC, cv2.VideoWriter.fourcc('M', 'J', 'P', 'G')) image.set(cv2.CAP_PROP_BRIGHTNESS, 62) #設置亮度 -64 - 64 0.0 image.set(cv2.CAP_PROP_CONTRAST, 63) #設置對比度 -64 - 64 2.0 image.set(cv2.CAP_PROP_EXPOSURE, 4800) #設置曝光值 1.0 - 5000 156.0update_hsv = HSV_Config.update_hsv()color_hsv = {"red" : ((0, 70, 72), (7, 255, 255)),"green" : ((54, 109, 78), (77, 255, 255)),"blue" : ((92, 100, 62), (121, 251, 255)),"yellow": ((26, 100, 91), (32, 255, 255))}print("開始檢測...") while True:start_time = time()ret, frame = image.read()frame, binary = update_hsv.get_contours(frame, color_hsv)parsing_time = time() - start_timecv2.putText(frame, "infer time(ms): %.3f, FPS: %.2f" % (parsing_time * 1000, 1 / (parsing_time + 0.0001)), (15, 55), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255, 0, 255), 1)# 顯示檢測結果cv2.imshow('capture', frame)# 檢測按鍵k = cv2.waitKey(1)if k==27:breakimage.release() cv2.destroyAllWindows()

HSV_Config.py 文件

# !/usr/bin/env python # coding: utf-8 import random import cv2 as cv import numpy as np import tkinter as tkclass update_hsv:def __init__(self):'''初始化一些參數'''self.image = Noneself.binary = Nonedef Image_Processing(self, hsv_range):'''形態學變換去出細小的干擾因素:param img: 輸入初始圖像:return: 檢測的輪廓點集(坐標)'''(lowerb, upperb) = hsv_range# 復制原始圖像,避免處理過程中干擾color_mask = self.image.copy()# 將圖像轉換為HSV。hsv_img = cv.cvtColor(self.image, cv.COLOR_BGR2HSV)# 篩選出位于兩個數組之間的元素。color = cv.inRange(hsv_img, lowerb, upperb)# 設置非掩碼檢測部分全為黑色color_mask[color == 0] = [0, 0, 0]# 將圖像轉為灰度圖gray_img = cv.cvtColor(color_mask, cv.COLOR_RGB2GRAY)# 獲取不同形狀的結構元素kernel = cv.getStructuringElement(cv.MORPH_RECT, (5, 5))# 形態學閉操作dst_img = cv.morphologyEx(gray_img, cv.MORPH_CLOSE, kernel)# 圖像二值化操作ret, binary = cv.threshold(dst_img, 10, 255, cv.THRESH_BINARY)# 獲取輪廓點集(坐標) python2和python3在此處略有不同# _, contours, heriachy = cv.findContours(binary, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE) #python2contours, heriachy = cv.findContours(binary, cv.RETR_EXTERNAL, cv.CHAIN_APPROX_SIMPLE) # python3return contours, binarydef draw_contours(self, hsv_name, contours):'''采用多邊形逼近的方法繪制輪廓'''for i, cnt in enumerate(contours):# 計算多邊形的矩mm = cv.moments(cnt)if mm['m00'] == 0:continuecx = mm['m10'] / mm['m00']cy = mm['m01'] / mm['m00']# 獲取多邊形的中心(x, y) = (np.int(cx), np.int(cy))# 計算輪廓的?積area = cv.contourArea(cnt)# ?積?于10000if area > 800:# 繪制中?cv.circle(self.image, (x, y), 5, (0, 0, 255), -1)# 計算最小矩形區域rect = cv.minAreaRect(cnt)# 獲取盒?頂點box = cv.boxPoints(rect)# 轉成long類型box = np.int0(box)# 繪制最小矩形cv.drawContours(self.image, [box], 0, (255, 0, 0), 2)cv.putText(self.image, hsv_name, (int(x - 15), int(y - 15)),cv.FONT_HERSHEY_SIMPLEX, 1, (255, 0, 255), 2)def get_contours(self, img, color_hsv):binary = None# 規范輸入圖像大小self.image = cv.resize(img, (320, 240), )for key, value in color_hsv.items():# 檢測輪廓點集color_contours, binary = self.Image_Processing(color_hsv[key])# 繪制檢測圖像,并控制跟隨self.draw_contours(key, color_contours)return self.image, binary

識別效果：

總結

以上是生活随笔為你收集整理的Raspberry Pi 4B 颜色检测的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。