OpenCV Error: Assertion Failed in MixChannels(..)

Question

I'm attempting to convert a MATLAB .mat file to openCV MAT and then applying several masks to those files. I am building from cvmatio source code. I am receiving the following error:

OpenCV Error: Assertion failed (A.size == arrays[i0]->size) in init, file /home/derek/Documents/Libraries/opencv-3.0.0-beta/modules/core/src/matrix.cpp, line 4279 terminate called after throwing an instance of 'cv::Exception' what(): /home/derek/Documents/Libraries/opencv-3.0.0-beta/modules/core/src/matrix.cpp:4279: error: (-215) A.size == arrays[i0]->size in function init

Here is the source file I've written. It occurs at the line with MixChannels. Note that SrcImage is a 3 channel Mat. lower and upper are the threshold values in an array who's length is equal to the number of channels.

/*
 * Mask.cpp
 *
 *  Created on: Mar 16, 2015
 *      Author: derek
 */


#include <cv.h>
#include <highgui.h>
#include "imgcodecs.hpp"
#include "highgui.hpp"
#include "imgproc.hpp"

using namespace cv;


Mat Mask(Mat SrcImage, double lower[], double upper[]){
    int height=SrcImage.rows;
    int width=SrcImage.cols;
    int depth=SrcImage.depth();
    Mat B2d = Mat::ones(height, width,depth);

    Mat out(height, width, depth);
    Mat outL(height, width, depth);
    Mat outU(height,width, depth);
    for (int i=1; i< SrcImage.channels(); i=i+1){
        int from_to[]={i,1};
        mixChannels(&SrcImage, 3, &out, 1, from_to, 1 );
        threshold(out, outL, lower[i], 1, THRESH_BINARY);
        threshold(out, outU, upper[i], 1, THRESH_BINARY);
        bitwise_and(B2d, outL, B2d);
        bitwise_and(B2d, outU, B2d);

    }

    return B2d;
}

Also, here is an excerpt of the actual CV_Assertion error location. As indicated in the error, it occurs at "(A.size == arrays[i0]->size)".

void NAryMatIterator::init(const Mat** _arrays, Mat* _planes, uchar** _ptrs, int _narrays)
{
    CV_Assert( _arrays && (_ptrs || _planes) );
    int i, j, d1=0, i0 = -1, d = -1;

    arrays = _arrays;
    ptrs = _ptrs;
    planes = _planes;
    narrays = _narrays;
    nplanes = 0;
    size = 0;

    if( narrays < 0 )
    {
        for( i = 0; _arrays[i] != 0; i++ )
            ;
        narrays = i;
        CV_Assert(narrays <= 1000);
    }

    iterdepth = 0;

    for( i = 0; i < narrays; i++ )
    {
        CV_Assert(arrays[i] != 0);
        const Mat& A = *arrays[i];
        if( ptrs )
            ptrs[i] = A.data;

        if( !A.data )
            continue;

        if( i0 < 0 )
        {
            i0 = i;
            d = A.dims;

            // find the first dimensionality which is different from 1;
            // in any of the arrays the first "d1" step do not affect the continuity
            for( d1 = 0; d1 < d; d1++ )
                if( A.size[d1] > 1 )
                    break;
        }
        else
            CV_Assert( A.size == arrays[i0]->size );

        if( !A.isContinuous() )
        {
            CV_Assert( A.step[d-1] == A.elemSize() );
            for( j = d-1; j > d1; j-- )
                if( A.step[j]*A.size[j] < A.step[j-1] )
                    break;
            iterdepth = std::max(iterdepth, j);
        }
    }

    if( i0 >= 0 )
    {
        size = arrays[i0]->size[d-1];
        for( j = d-1; j > iterdepth; j-- )
        {
            int64 total1 = (int64)size*arrays[i0]->size[j-1];
            if( total1 != (int)total1 )
                break;
            size = (int)total1;
        }

        iterdepth = j;
        if( iterdepth == d1 )
            iterdepth = 0;

        nplanes = 1;
        for( j = iterdepth-1; j >= 0; j-- )
            nplanes *= arrays[i0]->size[j];
    }
    else
        iterdepth = 0;

    idx = 0;

    if( !planes )
        return;

    for( i = 0; i < narrays; i++ )
    {
        CV_Assert(arrays[i] != 0);
        const Mat& A = *arrays[i];

        if( !A.data )
        {
            planes[i] = Mat();
            continue;
        }

        planes[i] = Mat(1, (int)size, A.type(), A.data);
    }
}

Answer 1

Well it's obviously too late of an answer, but here is the reason why your code failed:

Since your SrcImage is a single Mat with multiple channels, you should'we written:

mixChannels(&SrcImage, 1, &out, 1, from_to, 1 );

(The assert error was related to this, since mixChannels expected 3 Mats, which is 3 times bigger than your Mat.)

Also opencv MixChannels labels channels from 0, not sure if the i=1 was intended, or just a typo.

Cheers!