无人驾驶（一）| lane detection | Udacity | 色彩空间（含代码）

Lane detection 中的色彩检验

起因：我们通常分析图片都用RGB，如果直接转成gray，或者简单的利用threshhold进行颜色提取，会丢掉许多的颜色信息

Note: If you read in an image using matplotlib.image.imread() you will get an RGB image, but if you read it in using OpenCV cv2.imread() this will give you a BGR image.

解决方案：采取HLS或者HSV进行处理。HLS分别是

Hue：色相，深红浅红暗红，他们的Hue均相同

Lightness：不用说，亮度，都懂

Saturation： 饱和度，打个比方接近于白色的红饱和度低，浓郁的红（intensive）饱和度高

opencv中也直接给出了转换公式

hls = cv2.cvtColor(im, cv2.COLOR_RGB2HLS
           

举个例子：ABC都是紫，所以三者Hue相同。但是 L C > L B > L A L_C>L_B>L_A LC​>LB​>LA​

具体使用我们可以见得S在检测中起了相当robust的作用

import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import numpy as np
import cv2

# Read in an image, you can also try test1.jpg or test4.jpg
image = mpimg.imread('test6.jpg') 

# TODO: Define a function that thresholds the S-channel of HLS
# Use exclusive lower bound (>) and inclusive upper (<=)
def hls_select(img, thresh=(0, 255)):
    # 1) Convert to HLS color space
    hls = cv2.cvtColor(img, cv2.COLOR_RGB2HLS)
    S = hls[:,:,2]
    # 2) Apply a threshold to the S channel
    # 3) Return a binary image of threshold result
    binary_output = np.copy(S) # placeholder line
    binary_output[(S > thresh[0]) & (S<=thresh[1]) ]  = 1
    return binary_output
    
# Optional TODO - tune the threshold to try to match the above image!    
hls_binary = hls_select(image, thresh=(90, 255))

# Plot the result
f, (ax1, ax2) = plt.subplots(1, 2, figsize=(24, 9))
f.tight_layout()
ax1.imshow(image)
ax1.set_title('Original Image', fontsize=50)
ax2.imshow(hls_binary, cmap='gray')
ax2.set_title('Thresholded S', fontsize=50)
plt.subplots_adjust(left=0., right=1, top=0.9, bottom=0.)