opencv error:输入参数的大小不匹配

Question

我正在使用金字塔进行图像混合... m得到一个opencv错误..我正在关注官方opencv教程. http://docs.opencv.org/3.0-beta/doc/py_tutorials/py_tutorials.html

import cv2
import numpy as np,sys

A = cv2.imread('/home/grayhat/apple.jpg')
B = cv2.imread('/home/grayhat/orange.jpg')

# generate Gaussian pyramid for A
G = A.copy()
gpA = [G]
for i in xrange(6):
    G = cv2.pyrDown(G)
    gpA.append(G)

# generate Gaussian pyramid for B
G = B.copy()
gpB = [G]
for i in xrange(6):
    G = cv2.pyrDown(G)
    gpB.append(G)

# generate Laplacian Pyramid for A
lpA = [gpA[5]]
for i in xrange(5,0,-1):
   GE = cv2.pyrUp(gpA[i])
   L = cv2.subtract(gpA[i-1],GE)
   lpA.append(L)

# generate Laplacian Pyramid for B
lpB = [gpB[5]]
for i in xrange(5,0,-1):
    GE = cv2.pyrUp(gpB[i])
    L = cv2.subtract(gpB[i-1],GE)
    lpB.append(L)

# Now add left and right halves of images in each level
LS = []
for la,lb in zip(lpA,lpB):
    rows,cols,dpt = la.shape
    ls = np.hstack((la[:,0:cols/2], lb[:,cols/2:]))
    LS.append(ls)

# now reconstruct
ls_ = LS[0]
for i in xrange(1,6):
    ls_ = cv2.pyrUp(ls_)
    ls_ = cv2.add(ls_, LS[i])

# image with direct connecting each half
real = np.hstack((A[:,:cols/2],B[:,cols/2:]))

cv2.imwrite('Pyramid_blending2.jpg',ls_)
cv2.imwrite('Direct_blending.jpg',real)

以下是错误: -

OpenCV Error: Sizes of input arguments do not match (The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array') in arithm_op, file /build/buildd/opencv-2.4.8+dfsg1/modules/core/src/arithm.cpp, line 1287
Traceback (most recent call last):
  File "programs/test11.py", line 25, in <module>
    L = cv2.subtract(gpA[i-1],GE)
cv2.error: /build/buildd/opencv-2.4.8+dfsg1/modules/core/src/arithm.cpp:1287: error: (-209) The operation is neither 'array op array' (where arrays have the same size and the same number of channels), nor 'array op scalar', nor 'scalar op array' in function arithm_op

Answer 1

看来你在这里没有正确生成高斯金字塔:

# generate Gaussian pyramid for A
G = A.copy()
gpA = [G]
for i in xrange(6):
    G = cv2.pyrDown(G)
    gpA.append(G)

根据关于cv2.pyrDown的 OpenCV文档,如果你没有指定dstsize,它将默认为((src.cols+1)/2, (src.rows+1)/2).但是,您始终在原始G副本上进行下采样.如果我没有正确理解,我认为你必须将它应用于最后一个下采样图像:

# generate Gaussian pyramid for A
G = A.copy()
gpA = [G]
for i in xrange(6):
    G = cv2.pyrDown(gpA[i])
    gpA.append(G)

很明显,这同样适用于你的B金字塔.

现在,如果您的图像具有均匀的形状但不具有奇怪的形状,则您的脚本将起作用,因为cv2.pyrDown计算默认大小的方式.在这种情况下,你必须根据你用来做(或)的图像给予cv2.pyrUp适当的dstsize参数.cv2.substractcv2.add

# generate Laplacian Pyramid for A
lpA = [gpA[5]]
for i in xrange(5,0,-1):
    size = (gpA[i-1].shape[1], gpA[i-1].shape[0])
    GE = cv2.pyrUp(gpA[i], dstsize = size)
    L = cv2.subtract(gpA[i-1],GE)
    lpA.append(L)

# generate Laplacian Pyramid for B
lpB = [gpB[5]]
for i in xrange(5,0,-1):
    size = (gpB[i-1].shape[1], gpB[i-1].shape[0])
    GE = cv2.pyrUp(gpB[i], dstsize = size)
    L = cv2.subtract(gpB[i-1],GE)
    lpB.append(L)

然后,这一点也适用于重建部分:

# now reconstruct
ls_ = LS[0]
for i in xrange(1,6):
    size = (LS[i].shape[1], LS[i].shape[0])
    ls_ = cv2.pyrUp(ls_, dstsize = size)
    ls_ = cv2.add(ls_, LS[i])