一、色彩空间

1、什么是色彩空间？
色彩空间是定义的颜色范围。

2、常见的色彩空间有哪些？
①RGB

②HSV

在OpenCV中，Hue的值为0~180°，之所以不是360°是因为，8位存不下，故进行归一化操作，使得Hue取值在0 ~180°，可以通过一个字节来存储。
③HIS
Hue：色调
Intensity：强度
Saturation ：饱和度
④YCrCb
主要在早期的人的皮肤检测方面应用
⑤YUV
Android开发中常用，Linux的色彩空间

3、色彩空间之间的相互转化

import cv2


def color_space(image):
    gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
    cv2.imshow("gray",gray)
    
    hsv = cv2.cvtColor(image,cv2.COLOR_BGR2HSV)
    cv2.imshow("hsv",hsv)
    
    yuv = cv2.cvtColor(image,cv2.COLOR_BGR2YUV)
    cv2.imshow("yuv",yuv)
    
    ycrcb = cv2.cvtColor(image,cv2.COLOR_BGR2YCrCb)
    cv2.imshow("ycrcb",ycrcb)
    
    
src = cv2.imread("G:/Juptyer_workspace/study/opencv/opencv3/cat.png")#BGR
cv2.namedWindow("input image",cv2.WINDOW_AUTOSIZE)
cv2.imshow("input image",src)
t1 = cv2.getTickCount()
color_space(src)
t2 = cv2.getTickCount()
time = (t2-t1)/cv2.getTickFrequency()#显示当前运行时间
print("time:%s ms"%(time*1000))#输出当前运行时间单位为ms
cv2.waitKey(0)

cv2.destroyAllWindows()

运行效果图如下：

二、对视频中的目标(青色水杯)进行跟踪

cv2.inRange(hsv,lowerb=lower,upperb=upper)：对HSV颜色过滤，lowerb和upperb需要查上面的表进行颜色转换
方法一：目标物体白色，其余黑色

import cv2
import numpy as np


def extrace_object():
    capture = cv2.VideoCapture("G:/Juptyer_workspace/study/data/yy.mp4")
    while(True):
        ret,frame = capture.read()
        if ret==False:
            break
        hsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
        lower = np.array([78,43,46])#由于水杯是青色的故需要根据表格选出hsv对应的min值
        upper = np.array([99,255,255])#由于水杯是青色的故需要根据表格选出hsv对应的max值
        mask = cv2.inRange(hsv,lowerb=lower,upperb=upper)
        cv2.imshow("video",frame)
        cv2.imshow("mask",mask)
        c = cv2.waitKey(40)
        if c==27:
            break

            
t1 = cv2.getTickCount()
extrace_object()
t2 = cv2.getTickCount()
time = (t2-t1)/cv2.getTickFrequency()#显示当前运行时间
print("time:%s ms"%(time*1000))#输出当前运行时间单位为ms
cv2.waitKey(0)

cv2.destroyAllWindows()

效果图如下：

方法二：目标物体颜色保留，其余黑色

import cv2
import numpy as np


def extrace_object():
    capture = cv2.VideoCapture("G:/Juptyer_workspace/study/data/yy.mp4")
    while(True):
        ret,frame = capture.read()
        if ret==False:
            break
        hsv = cv2.cvtColor(frame,cv2.COLOR_BGR2HSV)
        lower = np.array([78,43,46])#由于水杯是青色的故需要根据表格选出hsv对应的min值
        upper = np.array([99,255,255])#由于水杯是青色的故需要根据表格选出hsv对应的max值
        mask = cv2.inRange(hsv,lowerb=lower,upperb=upper)
        dst = cv2.bitwise_and(frame,frame,mask=mask)
        cv2.imshow("video",frame)
        #cv2.imshow("mask",mask)
        cv2.imshow("dst",dst)
        c = cv2.waitKey(40)
        if c==27:
            break

            
t1 = cv2.getTickCount()
extrace_object()
t2 = cv2.getTickCount()
time = (t2-t1)/cv2.getTickFrequency()#显示当前运行时间
print("time:%s ms"%(time*1000))#输出当前运行时间单位为ms
cv2.waitKey(0)

cv2.destroyAllWindows()

效果图如下：

三、对彩色图像三颜色通道进行分割显示并合并显示

cv2.split(src)：对src三颜色通道的彩色图像进行分割
cv2.merge([b,g,r])：将b,g,r三个单颜色通道图像进行合并

import cv2
import numpy as np


src = cv2.imread("G:/Juptyer_workspace/study/opencv/opencv3/cat.png")#BGR
cv2.namedWindow("input image",cv2.WINDOW_AUTOSIZE)
cv2.imshow("input image",src)
t1 = cv2.getTickCount()

b,g,r = cv2.split(src)#拆分彩色通道图像
cv2.imshow("blue",b)
cv2.imshow("green",g)
cv2.imshow("red",r)

src = cv2.merge([b,g,r])#将拆分的三个单颜色通道进行合并还原
src[:,:,0]=0#将第0个颜色通道，即B颜色通道赋值为0
cv2.imshow("changed",src)

t2 = cv2.getTickCount()
time = (t2-t1)/cv2.getTickFrequency()#显示当前运行时间
print("time:%s ms"%(time*1000))#输出当前运行时间单位为ms
cv2.waitKey(0)

cv2.destroyAllWindows()

效果图如下：