Question

所以我正在学习车道检测，我想检测视频上的车道线。我收集了一些受欢迎的视频，人们可以进行车道检测，并且效果很好。当我从互联网上收到新视频时，我偶然发现了此错误。我检查了视频的路径及其正确性，但给了我一个错误，我不知道为什么。这是我的代码：

from moviepy.editor import VideoFileClip
from IPython.display import HTML

def process_image(image, 
                  kernel_size = 5, 
                  low_threshold = 100, high_threshold = 250, 
                  rho = 1, theta = np.pi/180, threshold = 30,
                  min_line_len = 100, max_line_gap = 200): 
    
    
    #turn in grayscale
    gray = grayscale(image)
    
    #apply blur
    blur_gray = gaussian_blur(gray, kernel_size)
    
    #finding edges
    edges = canny(image, low_threshold, high_threshold)
    
    #setting vertices
    vertices = np.array([[(0,image.shape[0]),(450, 315), (490, 315), 
                          (image.shape[1],image.shape[0])]], dtype=np.int32)
    
    #creating a region of interest
    masked_edges = region_of_interest(edges, vertices)
    
    #finding lines
    lines = hough_lines(masked_edges, rho, theta, threshold, min_line_len, max_line_gap)
    
    #merge with original image
    lines_edges = weighted_img(lines, image, α=0.8, β=1., λ=0.)
    
    return lines_edges

white_output = 'test_videos_output/video1.mp4'
clip1 = VideoFileClip("test_videos/video1.mp4")
white_clip = clip1.fl_image(process_image) #NOTE: this function expects color images!!
%time white_clip.write_videofile(white_output, audio=False)

错误：无法将float NaN转换为整数

0 个答案: