我在形态掩码上遇到错误

Question

我编写了一个程序，可以找到2个ROI，在2个单独的帧中选择它们，然后计算每个帧的绿色像素数。它可以正常工作，但是当我将形态掩码应用于相机时，它会给我错误：/home/pi/opencv/opencv-3.4.0/modules/core/src/arithm.cpp:1769：错误：（-209）较低边界既不是相同大小的数组，也不是SRC相同的类型，也不是函数inrange的标量我怎样才能解决这个问题？

问题在这里发生

maskClose=cv2.morphologyEx(maskOpen,cv2.MORPH_CLOSE,kernelClose) maskFinal=maskClose ... for i in range(len(conts)): x,y,w,h=cv2.boundingRect(conts[i]) area=maskFinal[y:y+h, x:x+w] pixcount = cv2.inRange(area,lowerBound,upperBound ) pixNum = cv2.countNonZero(pixcount)

完整代码

import cv2
import numpy as np
from picamera.array import PiRGBArray
from picamera import PiCamera
import time
import sys
prevNrOfContours = 0
lowerBound=np.array([43,53,30])
upperBound=np.array([132,255,255])

camera = PiCamera()
camera.rotation = 180
camera.resolution = (640, 480)
camera.framerate = 30
font=cv2.FONT_HERSHEY_SIMPLEX
rawCapture = PiRGBArray(camera, size=(640, 480))
GREEN_MIN = np.array([0, 0, 0])
GREEN_MAX = np.array([0, 0, 0])

# allow the camera to warmup
time.sleep(0.1)
kernelOpen=np.ones((5,5))
kernelClose=np.ones((20,20))
# capture frames from the camera
for frame in camera.capture_continuous(rawCapture, format="bgr", use_video_port=True):
        img = frame.array
        imgHSV= cv2.cvtColor(img,cv2.COLOR_BGR2HSV)
        mask=cv2.inRange(imgHSV,lowerBound,upperBound)
#morphology
        maskOpen=cv2.morphologyEx(mask,cv2.MORPH_OPEN,kernelOpen)
        maskClose=cv2.morphologyEx(maskOpen,cv2.MORPH_CLOSE,kernelClose)
        maskFinal=maskClose
        _, conts, _=cv2.findContours(maskFinal.copy(),cv2.RETR_EXTERNAL,cv2.CHAIN_APPROX_NONE)
        nrOfContours = len(conts)
        for i in range(len(conts)):
            x,y,w,h=cv2.boundingRect(conts[i])
            area=maskFinal[y:y+h, x:x+w] ######## problem is here
            pixcount = cv2.inRange(area,lowerBound,upperBound )
            pixNum = cv2.countNonZero(pixcount)
            print("Area No."+str(i), "Green pixels = " + str(no_black))
            cv2.rectangle(img,(x,y),(x+w,y+h),(0,0,255), 2)
            cv2.imshow("area" + str(i), area)
        # close unnecessary windows
        if prevNrOfContours > nrOfContours:
          for i in range(nrOfContours, prevNrOfContours):
            cv2.destroyWindow("area" + str(i))
        prevNrOfContours = nrOfContours
        cv2.imshow("cam",img)
        # clear the stream in preparation for the next frame
        key = cv2.waitKey(1) & 0xFF
        rawCapture.truncate(0)
        if key == ord("q"):
                break

Answer 1

您正在创建MaskFinal的子图像。面膜是二进制图像，它与3通道lowerBound不兼容。

要求解它，您实际上可以删除线pixcount = cv2.inRange(area,lowerBound,upperBound )蒙版图像对绿色区域的图像为白色，因此计算nonzeros就足够了。

注意：当前的子图像包括形态变换。如果您不想计算由这些像素引起的像素，则必须创建mask