python - OpenCV 错误 : Assertion failed (mask. size == src1.size) in binary_op

Question

我正在尝试将帽子的 png 图像图像放在网络摄像头的头上喂养。

import cv2
import numpy as np

face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_default.xml')

# Load the overlay image: hat.png
imghat = cv2.imread('hat2.png', -1)

print imghat is None

# Create the mask for the hat
imghatGray = cv2.cvtColor(imghat, cv2.COLOR_BGR2GRAY)
#cv2.imwrite("imghatGray.png", imghatGray)

ret, orig_mask = cv2.threshold(imghatGray, 0, 255, cv2.THRESH_BINARY)
#cv2.imwrite("orig_mask.png", orig_mask)

# Create the inverted mask for the hat
orig_mask_inv = cv2.bitwise_not(orig_mask)
#cv2.imwrite("orig_mask_inv.png", orig_mask_inv)

# Convert hat image to BGR
# and save the original image size (used later when re-sizing the image)
imghat = imghat[:,:,0:3]
origHatHeight, origHatWidth = imghat.shape[:2]

video_capture = cv2.VideoCapture(0)

while True:

    ret, frame = video_capture.read()

    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    faces = face_cascade.detectMultiScale(gray, 1.3, 5, flags=cv2.cv.CV_HAAR_SCALE_IMAGE)

    for (x, y, w, h) in faces:
        print "x : %d , y : %d, w: %d, h: %d " %(x,y,w,h)
        cv2.rectangle(frame, (x,y), (x+w, y+h), (255,0,0), 2)
        #cv2.rectangle(frame, (x-15,y-h), (x+w+15, y), (255,255,0), 2)

        hatWidth = w
        hatHeight = hatWidth * origHatHeight / origHatWidth

            roi_gray = gray[y:y+h, x:x+w]
            roi_color = frame[y:y+h, x:x+w]

        # Center the hat
        x1 = x - 15
        y1 = y - h
        x2 = x1 + w + 30
        y2 = y1 + h

        #cv2.rectangle(frame, (x1,y1), (x2, y2), (0,255,0), 2)

        # Check for clipping
        if x1 < 0:
            x1 = 0
        if y1 < 0:
            y1 = 0
        if x2 > 640:
            x2 = w
        if y2 > 360:
            y2 = h


        print "x1: %d , y1 : %d, x2: %d, y2: %d " %(x1,y1,x2,y2)
        # Re-calculate the width and height of the hat image
        hatWidth = x2 - x1
        hatHeight = y2 - y1

        cv2.rectangle(frame, (x1,y1), (x2, y2), (255,255,0), 2)
        print "hatWidth: %d, hatHeight: %d" %(hatWidth, hatHeight)      
        # Re-size the original image and the masks to the hat sizes
        # calcualted above
        hat = cv2.resize(imghat, (hatWidth,hatHeight), interpolation = cv2.INTER_AREA)
        mask = cv2.resize(orig_mask, (hatWidth,hatHeight), interpolation = cv2.INTER_AREA)
        mask_inv = cv2.resize(orig_mask_inv, (hatWidth,hatHeight), interpolation = cv2.INTER_AREA)

        # take ROI for hat from background equal to size of hat image
        roi = roi_color[y1:y2, x1:x2]

        # roi_bg contains the original image only where the hat is not
        # in the region that is the size of the hat.
        roi_bg = cv2.bitwise_and(roi,roi,mask = mask_inv)

        # roi_fg contains the image of the hat only where the hat is
        roi_fg = cv2.bitwise_and(hat,hat,mask = mask)

        # join the roi_bg and roi_fg
        dst = cv2.add(roi_bg,roi_fg)

        # place the joined image, saved to dst back over the original image
        roi_color[y1:y2, x1:x2] = dst

        break



    # Display the resulting frame
        cv2.imshow('Video', frame)


        if cv2.waitKey(1) & 0xFF == ord('q'):
            break

# When everything is done, release the capture
video_capture.release()
cv2.destroyAllWindows()

当我执行程序时，相机突然打开和关闭。显示的错误在下面一行 -

roi_bg = cv2.bitwise_and(roi, roi, mask = mask_inv)

Answer 1

错误是

Assertion failed (mask.size == src1.size)

即蒙版图像的大小与您正在执行按位运算的源图像的大小不匹配_and on

源图像是您的投资返回率

roi = roi_color[ y1:y2, x1:x2 ]

看起来像 y2-y1 x x2-x1

掩码大小为

mask = cv2.resize(orig_mask, (hatWidth,hatHeight), interpolation = cv2.INTER_AREA)

看起来像 hatWidth x hatHeight 即 (x2-x1) x (y2-y1)除非括号做了一些事情来颠倒宽度和高度的顺序——我不是 Python 大师，但这似乎不太可能。