使用 Python 和 OpenCV 在图像中查找红色

Question

我正在尝试从图像中提取红色。我有代码应用阈值以仅保留指定范围内的值：

img=cv2.imread('img.bmp')
img_hsv=cv2.cvtColor(img, cv2.COLOR_BGR2HSV)
lower_red = np.array([0,50,50]) #example value
upper_red = np.array([10,255,255]) #example value
mask = cv2.inRange(img_hsv, lower_red, upper_red)
img_result = cv2.bitwise_and(img, img, mask=mask)

但是，正如我所检查的，红色的色调值可以在 0 到 10 的范围内，也可以在 170 到 180 的范围内。因此，我想保留这两个范围中的任何一个值。我尝试将阈值设置为 10 到 170 并使用 cv2.bitwise_not() 函数，但后来我也得到了所有的白色。我认为最好的选择是为每个范围创建一个蒙版并同时使用它们，所以我必须在继续之前将它们连接在一起。

有没有办法可以使用 OpenCV 连接两个掩码？还是有其他方法可以实现我的目标？

编辑。我带来了不太优雅但有效的解决方案：

image_result = np.zeros((image_height,image_width,3),np.uint8)

for i in range(image_height):  #those are set elsewhere
    for j in range(image_width): #those are set elsewhere
        if img_hsv[i][j][1]>=50 \
            and img_hsv[i][j][2]>=50 \
            and (img_hsv[i][j][0] <= 10 or img_hsv[i][j][0]>=170):
            image_result[i][j]=img_hsv[i][j]

它几乎满足了我的需求，OpenCV 的功能可能也差不多，但是如果有更好的方法（使用一些专用函数并编写更少的代码）请与我分享。 :)

Answer 1

要检测红色，您可以使用 HSV 颜色阈值脚本来确定下限/上限阈值，然后使用cv2.bitwise_and() 获取蒙版。使用这个输入图像，

我们得到这个结果和掩码

代码

import numpy as np
import cv2

image = cv2.imread('1.jpg')
result = image.copy()
image = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
lower = np.array([155,25,0])
upper = np.array([179,255,255])
mask = cv2.inRange(image, lower, upper)
result = cv2.bitwise_and(result, result, mask=mask)

cv2.imshow('mask', mask)
cv2.imshow('result', result)
cv2.waitKey()

带有滑块的HSV颜色阈值脚本，记得更改图像文件路径

import cv2
import sys
import numpy as np

def nothing(x):
    pass

# Load in image
image = cv2.imread('1.jpg')

# Create a window
cv2.namedWindow('image')

# create trackbars for color change
cv2.createTrackbar('HMin','image',0,179,nothing) # Hue is from 0-179 for Opencv
cv2.createTrackbar('SMin','image',0,255,nothing)
cv2.createTrackbar('VMin','image',0,255,nothing)
cv2.createTrackbar('HMax','image',0,179,nothing)
cv2.createTrackbar('SMax','image',0,255,nothing)
cv2.createTrackbar('VMax','image',0,255,nothing)

# Set default value for MAX HSV trackbars.
cv2.setTrackbarPos('HMax', 'image', 179)
cv2.setTrackbarPos('SMax', 'image', 255)
cv2.setTrackbarPos('VMax', 'image', 255)

# Initialize to check if HSV min/max value changes
hMin = sMin = vMin = hMax = sMax = vMax = 0
phMin = psMin = pvMin = phMax = psMax = pvMax = 0

output = image
wait_time = 33

while(1):

    # get current positions of all trackbars
    hMin = cv2.getTrackbarPos('HMin','image')
    sMin = cv2.getTrackbarPos('SMin','image')
    vMin = cv2.getTrackbarPos('VMin','image')

    hMax = cv2.getTrackbarPos('HMax','image')
    sMax = cv2.getTrackbarPos('SMax','image')
    vMax = cv2.getTrackbarPos('VMax','image')

    # Set minimum and max HSV values to display
    lower = np.array([hMin, sMin, vMin])
    upper = np.array([hMax, sMax, vMax])

    # Create HSV Image and threshold into a range.
    hsv = cv2.cvtColor(image, cv2.COLOR_BGR2HSV)
    mask = cv2.inRange(hsv, lower, upper)
    output = cv2.bitwise_and(image,image, mask= mask)

    # Print if there is a change in HSV value
    if( (phMin != hMin) | (psMin != sMin) | (pvMin != vMin) | (phMax != hMax) | (psMax != sMax) | (pvMax != vMax) ):
        print("(hMin = %d , sMin = %d, vMin = %d), (hMax = %d , sMax = %d, vMax = %d)" % (hMin , sMin , vMin, hMax, sMax , vMax))
        phMin = hMin
        psMin = sMin
        pvMin = vMin
        phMax = hMax
        psMax = sMax
        pvMax = vMax

    # Display output image
    cv2.imshow('image',output)

    # Wait longer to prevent freeze for videos.
    if cv2.waitKey(wait_time) & 0xFF == ord('q'):
        break

cv2.destroyAllWindows()

Answer 2

玩这个。

#blurring and smoothin
img1=cv2.imread('marathon.png',1)

hsv = cv2.cvtColor(img1,cv2.COLOR_BGR2HSV)

#lower red
lower_red = np.array([0,50,50])
upper_red = np.array([10,255,255])


#upper red
lower_red2 = np.array([170,50,50])
upper_red2 = np.array([180,255,255])

mask = cv2.inRange(hsv, lower_red, upper_red)
res = cv2.bitwise_and(img1,img1, mask= mask)


mask2 = cv2.inRange(hsv, lower_red2, upper_red2)
res2 = cv2.bitwise_and(img1,img1, mask= mask2)

img3 = res+res2
img4 = cv2.add(res,res2)
img5 = cv2.addWeighted(res,0.5,res2,0.5,0)


kernel = np.ones((15,15),np.float32)/225
smoothed = cv2.filter2D(res,-1,kernel)
smoothed2 = cv2.filter2D(img3,-1,kernel)





cv2.imshow('Original',img1)
cv2.imshow('Averaging',smoothed)
cv2.imshow('mask',mask)
cv2.imshow('res',res)
cv2.imshow('mask2',mask2)
cv2.imshow('res2',res2)
cv2.imshow('res3',img3)
cv2.imshow('res4',img4)
cv2.imshow('res5',img5)
cv2.imshow('smooth2',smoothed2)




cv2.waitKey(0)
cv2.destroyAllWindows()

Answer 3

我只是将蒙版加在一起，然后使用np.where 对原始图像进行蒙版。

img=cv2.imread("img.bmp")
img_hsv=cv2.cvtColor(img, cv2.COLOR_BGR2HSV)

# lower mask (0-10)
lower_red = np.array([0,50,50])
upper_red = np.array([10,255,255])
mask0 = cv2.inRange(img_hsv, lower_red, upper_red)

# upper mask (170-180)
lower_red = np.array([170,50,50])
upper_red = np.array([180,255,255])
mask1 = cv2.inRange(img_hsv, lower_red, upper_red)

# join my masks
mask = mask0+mask1

# set my output img to zero everywhere except my mask
output_img = img.copy()
output_img[np.where(mask==0)] = 0

# or your HSV image, which I *believe* is what you want
output_hsv = img_hsv.copy()
output_hsv[np.where(mask==0)] = 0

这应该比循环遍历图像的每个像素要快得多，可读性要强得多。