Preparation Notes: opencv learning: line detection

Line detection generally uses functions HoughLines or HoughLinesP, The second method is the probabilistic version Hoygh Transformation , This function is an optimized version , Faster calculation

import cv2
import numpy as np

cap = cv2.VideoCapture(0)
while True:
    ret, frame = cap.read()
    x, y = frame.shape[0:2]
    small_frame = cv2.resize(frame, (int(y / 2), int(x / 2)))
    
    gray = cv2.cvtColor(small_frame, cv2.COLOR_BGR2GRAY)
    edges = cv2.Canny(gray, 50, 120)
    minLineLength = 10
    maxLineGap = 5
    lines = cv2.HoughLinesP(edges, 1, np.pi / 180, 100, minLineLength, maxLineGap)
        
    for x1, y1, x2, y2 in lines[0]:
        cv2.line(small_frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
    cv2.imshow("lines", small_frame)
    
    if cv2.waitKey(1) & 0xFF == ord("q"):
        break
        
cap.release()
cv2.destroyAllWindows()

Program description ：
1 x, y = frame.shape[0:2]
small_frame = cv2.resize(frame, (int(y / 2), int(x / 2)))
gray = cv2.cvtColor(small_frame, cv2.COLOR_BGR2GRAY)
Zoom the image to a quarter of the original and convert it into a grayscale image , To reduce the amount of calculation

2 edges = cv2.Canny(gray, 50, 120)
Use Canny Function to extract edges

3 lines = cv2.HoughLinesP(edges, 1, np.pi / 180, 100, minLineLength, maxLineGap)
Use HoughLineP Extracting lines
Parameter description ：
Parameters 1： Binary image to be processed
Parameters 2：rho and theta, The general values 1 and np.pi / 180
Parameters 3： threshold , Below this threshold will be ignored
Parameters 4： Minimum line length , Less than this length will be ignored
Parameters 5： Maximum segment gap , Greater than this gap will be considered as two lines