前言

針對Project1- Finding Lane Lines這個項目，提供專案實作說明，包括以下三個部分：
1.程式實作描述
2.可能缺點
3.建議可能的改進

說明

1.程式實作描述

def process_image(image):
    # NOTE: The output you return should be a color image (3 channel) for processing video below
    # TODO: put your pipeline here,
    # you should return the final output (image where lines are drawn on lanes)
    gray_image = grayscale(image)
    gaus_blur = gaussian_blur(gray_image, 3)
    edges = canny(gaus_blur, 50,150)    
    imshape = image.shape
    
    vertices = np.array([[(0,imshape[0]),(450, 320), (500, 320), (imshape[1],imshape[0])]], dtype=np.int32)    
    masked = region_of_interest(edges, vertices)
    
    rho = 2            #distance resolution in pixels of the Hough grid
    theta = np.pi/180  #angular resolution in radians of the Hough grid
    threshold = 5      #minimum number of votes (intersections in Hough grid cell)
    min_line_len = 10  #minimum number of pixels making up a line
    max_line_gap = 20  #maximum gap in pixels between connectable line segments
    line_image = hough_lines(masked, rho, theta, threshold, min_line_len, max_line_gap)
    
    result = weighted_img(line_image, image)
    return result

1. 圖檔灰階處理產出

gray_image = grayscale(image)

2.高斯平滑處理

gray_image = grayscale(image)

3.利用canny檢測邊緣

edges = canny(gaus_blur, 50,150)    

4.於圖檔繪上興趣節點

masked = region_of_interest(edges, vertices)

5.圖檔進行霍夫轉換產出

line_image = hough_lines(masked, rho, theta, threshold, min_line_len, max_line_gap)

2.可能缺點

在可能車道道之取得，利用斜率範圍過濾取得，實際上車道線在圖檔上不一定會直線，可能因為會有不是車道線會納入考量，也可能漏掉可能的車道線。

3.建議可能的改進

將車道線之取得把圖檔切割更小範圍來進行判斷