通过HSV空间颜色转换进行汽车车身颜色判断

目前，有很多对车的颜色进行识别的，传统的基于颜色空间的，以及目前较为火的机器学习、深度学习等方法，深度学习准确度高，但是需要进行训练，存储权重文件等，传统办法就较为简单，几十行代码就解决了。

汽车车身颜色判断定义函数和识别方法如下：

import numpy as np
import collections
import cv2
#定义字典存放颜色分量上下限
#例如：{颜色: [min分量, max分量]}
#{'red': [array([160,  43,  46]), array([179, 255, 255])]}
 
def getColorList():
    dict = collections.defaultdict(list)
 
    # 黑色
#     lower_black = np.array([0, 0, 0])   
    lower_black = np.array([5, 5, 5])
    upper_black = np.array([180, 255, 46])
    color_list = []
    color_list.append(lower_black)
    color_list.append(upper_black)
    dict['black'] = color_list
 
#     #灰色
#     lower_gray = np.array([0, 0, 46])
#     upper_gray = np.array([180, 43, 220])
#     color_list = []
#     color_list.append(lower_gray)
#     color_list.append(upper_gray)
#     dict['gray']=color_list
 
    # 白色 
#     lower_white = np.array([0, 0, 221])  #官方值
#     upper_white = np.array([180, 30, 255])
    lower_white = np.array([0, 0, 221])   #201  211
    upper_white = np.array([180, 80, 255])   #130
    color_list = []
    color_list.append(lower_white)
    color_list.append(upper_white)
    dict['white'] = color_list
 
    #红色
    lower_red = np.array([156, 43, 46])
    upper_red = np.array([180, 255, 255])
    color_list = []
    color_list.append(lower_red)
    color_list.append(upper_red)
    dict['red']=color_list
 
#     # 红色2
#     lower_red = np.array([0, 43, 46])
#     upper_red = np.array([10, 255, 255])
#     color_list = []
#     color_list.append(lower_red)
#     color_list.append(upper_red)
#     dict['red2'] = color_list
 
    #橙色
    lower_orange = np.array([0, 43, 46])
    upper_orange = np.array([15, 255, 255])  #25
    color_list = []
    color_list.append(lower_orange)
    color_list.append(upper_orange)
    dict['orange'] = color_list
 
    #黄色
    lower_yellow = np.array([16, 43, 46])  #26
    upper_yellow = np.array([34, 255, 255])
    color_list = []
    color_list.append(lower_yellow)
    color_list.append(upper_yellow)
    dict['yellow'] = color_list
 
    #绿色
    lower_green = np.array([35, 43, 46])
    upper_green = np.array([77, 255, 255])
    color_list = []
    color_list.append(lower_green)
    color_list.append(upper_green)
    dict['green'] = color_list
 
    #青色
    lower_cyan = np.array([78, 43, 46])
    upper_cyan = np.array([99, 255, 255])
    color_list = []
    color_list.append(lower_cyan)
    color_list.append(upper_cyan)
    dict['cyan'] = color_list
 
    #蓝色
#     lower_blue = np.array([100, 43, 46])
#     upper_blue = np.array([124, 255, 255])
    lower_blue = np.array([100, 83, 86]) #123
    upper_blue = np.array([124, 255, 255])
    color_list = []
    color_list.append(lower_blue)
    color_list.append(upper_blue)
    dict['blue'] = color_list
 
    # 紫色
    lower_purple = np.array([125, 43, 46])
    upper_purple = np.array([155, 255, 255])
    color_list = []
    color_list.append(lower_purple)
    color_list.append(upper_purple)
    dict['purple'] = color_list
 
    return dict

# filename='E:/AI_projects/10.jpg'
# #处理图片
# def get_color(frame):
# #     print('go in get_color')
#     hsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
#     maxsum = -100
#     color = None
#     color_dict = getColorList()
#     for d in color_dict:
#         mask = cv2.inRange(hsv,color_dict[d][0],color_dict[d][1])
# #         cv2.imwrite(d+'.jpg',mask)
#         binary = cv2.threshold(mask, 127, 255, cv2.THRESH_BINARY)[1]
#         binary = cv2.dilate(binary,None,iterations=2)        
#         cnts, hiera = cv2.findContours(binary.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_SIMPLE)
#         summ = 0
#         for c in cnts:
#             summ+=cv2.contourArea(c)
#         if summ > maxsum :
#             maxsum = summ
#             color = d 
#     return color

# if __name__ == '__main__':
#     frame = cv2.imread(filename)
#     print(get_color(frame))

filename='E:/AI_projects/14.jpg'
filename=cv2.imread(filename)
hsv = cv2.cvtColor(filename,cv2.COLOR_BGR2HSV)
maxsum = 0
color = None
color_dict = getColorList()

colordic=[]
for d in color_dict:    
    mask = cv2.inRange(hsv,color_dict[d][0],color_dict[d][1])
    res_green = cv2.bitwise_and(filename,filename, mask= mask)
#     res_green = cv2.bitwise_and(hsv,hsv, mask= mask)
    cv2.imshow(d,res_green)    
   
    summ=0
    for i in range(len(res_green)):
        if np.any(res_green[i]>0)==True:
            summ=summ+1
#         for j in range(len(res_green[i])):
#             if True==np.any(res_green[i][j]>0):
#                 summ=summ+1
    colordic.append(summ)
    if summ > maxsum :
        maxsum = summ
        color = d 
print(color)

以上是直接进行整个图像统计颜色域的范围内某种颜色的数量来判断目标的颜色，这种办法存在较大的缺陷是当周围环境也会被考虑进来，产生误判。

解决办法是利用OpenCV grabcut函数进行背景去除，再进行判断。

运行上面的代码后再运行下面的代码，为了简化代码，可以把上面代码后面那部分删除，把两部分合并。

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

filename='E:/AI_projects/21.jpg'
filename=cv2.imread(filename)


img=filename
img2 = img.copy()                               
mask = np.zeros(img.shape[:2], dtype = np.uint8) 
output = np.zeros(img.shape, np.uint8)           
rect_or_mask = 0
rect=(2,1,img.shape[0],img.shape[1])
bgdmodel = np.zeros((1, 65), np.float64)
fgdmodel = np.zeros((1, 65), np.float64)
cv.grabCut(img2, mask, rect, bgdmodel, fgdmodel, 1, cv.GC_INIT_WITH_RECT)
mask2 = np.where((mask==1) + (mask==3), 255, 0).astype('uint8')
output = cv.bitwise_and(img2, img2, mask=mask2)


# hsv = cv2.cvtColor(filename,cv2.COLOR_BGR2HSV)
hsv = cv2.cvtColor(output,cv2.COLOR_BGR2HSV)

maxsum = 0
color = None
color_dict = getColorList()

colordic=[]
for d in color_dict:    
    mask = cv2.inRange(hsv,color_dict[d][0],color_dict[d][1])
    res_green = cv2.bitwise_and(filename,filename, mask= mask)
#     res_green = cv2.bitwise_and(hsv,hsv, mask= mask)
    cv2.imshow(d,res_green)    
   
    summ=0
    for i in range(len(res_green)):
        if np.any(res_green[i]>0)==True:
            summ=summ+1
#         for j in range(len(res_green[i])):
#             if True==np.any(res_green[i][j]>0):
#                 summ=summ+1
    colordic.append(summ)
    if summ > maxsum :
        maxsum = summ
        color = d 
print(color)

cv2.waitKey(0)
cv2.destroyAllWindows()  

通过这个就可把路和车旁边的其他东西去除掉，减少干扰，提高识别精确度。