如何检测被阴影遮挡的黄色物体？

Question

我尝试检测下图中的黄线，但阴影遮住了黄色道路。我们有什么方法可以处理吗？编码如下：import cv2import numpy as npimage = cv2.imread('Road.jpg')hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)low_yellow = np.array([18, 94, 140])up_yellow = np.array([48, 255, 255])mask = cv2.inRange(hsv, low_yellow, up_yellow)edges = cv2.Canny(mask, 75, 150)lines = cv2.HoughLinesP(edges, 1, np.pi / 180, 50, maxLineGap=250)for line in lines:  x1, y1, x2, y2 = line[0]  cv2.line(image, (x1, y1), (x2, y2), (0, 255, 0), 5)  # cv2.imshow('image', img)  cv2.imwrite("result.jpg", edges)

Answer 1

这是转换为实验室和自动阈值的代码您必须使用适当的方法检测线条。一种高级解决方案是训练数据集进行分割（神经网络 Ex：Unet）

import cv2

import numpy as np

img = cv2.imread('YourImagePath.jpg')

cv2.imshow("Original", img)

k = cv2.waitKey(0)

# Convert To lab

lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)

# display b channel

cv2.imshow("Lab", lab[:, :, 2])

k = cv2.waitKey(0)

# auto threshold using Otsu

ret , mask = cv2.threshold(lab[:, :, 2] , 0 , 255 , cv2.THRESH_BINARY+ 

cv2.THRESH_OTSU)

#display Binary

cv2.imshow("Binary", mask)

k = cv2.waitKey(0)

cv2.destroyAllWindows()

输出：