不使用cv.HoughLines与cv.HoughLinesP实现Hough直线检测的Python代码

以下是一个实现Hough直线检测的Python代码，不使用cv.HoughLines和cv.HoughLinesP：

import numpy as np
import cv2

def hough_lines(image):
    # Convert image to grayscale
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    
    # Apply Canny edge detection
    edges = cv2.Canny(gray, 50, 150)
    
    # Define the Hough transform parameters
    rho = 1
    theta = np.pi/180
    threshold = 50
    
    # Initialize accumulator matrix
    acc = np.zeros((edges.shape[0], edges.shape[1]))
    
    # Loop over every pixel in the edges image
    for x in range(edges.shape[0]):
        for y in range(edges.shape[1]):
            # Check if pixel is an edge
            if edges[x,y] != 0:
                # Loop over every possible theta value
                for t in range(int(np.pi/theta)):
                    # Calculate rho for this theta value
                    r = int(x*np.cos(t*theta) + y*np.sin(t*theta))
                    
                    # Increment accumulator cell
                    acc[r,t] += 1
                    
    # Find the indices of the cells with the highest values in the accumulator matrix
    indices = np.argwhere(acc > threshold)
    
    # Initialize list to hold lines
    lines = []
    
    # Loop over the indices and convert rho and theta back to x,y coordinates
    for i in range(len(indices)):
        r = indices[i][0]
        t = indices[i][1]
        a = np.cos(t*theta)
        b = np.sin(t*theta)
        x0 = a*r
        y0 = b*r
        x1 = int(x0 + 1000*(-b))
        y1 = int(y0 + 1000*(a))
        x2 = int(x0 - 1000*(-b))
        y2 = int(y0 - 1000*(a))
        lines.append((x1,y1,x2,y2))
        
    return lines

# Test the function on an image
image = cv2.imread('test_image.jpg')
lines = hough_lines(image)

# Draw the lines on the image
for line in lines:
    x1,y1,x2,y2 = line
    cv2.line(image, (x1,y1), (x2,y2), (0,255,0), 2)

# Display the image
cv2.imshow('Hough Lines', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

该代码的实现过程与cv.HoughLinesP类似，但是没有使用OpenCV的函数，而是手动实现了Hough变换和线段检测。