OpenCV cuda::meanStdDev support for CV_32FC1 - opencv

Question

I want to find the mean pixel value and standard deviation of a GPUMat and do this reduction on the GPU rather than having to download the image and compute the mean on the CPU (since this will slow me down considerably in my application). The thing is, the GpuMat images I am dealing with are 32 bit floats - the opencv documentation however states that
CV_8UC1 matrices are supported for now
I have no trouble compiling the following code:
#include <opencv2/core/core.hpp>
#include <opencv2/core/cuda.hpp>
#include <opencv2/cudaarithm.hpp>
int main(int argc, char** argv)
{
cv::cuda::GpuMat img = cv::cuda::GpuMat(cv::Mat::zeros(cv::Size(kIWEWidth,kIWEHeight), CV_32FC1));
cv::Scalar mean, std;
cv::cuda::meanStdDev(img, mean, std);
}
However, when I try to actually execute this, I'm hit with
error: (-215:Assertion failed) src.type() == CV_8UC1 in function 'meanStdDev'
So, I was wondering if anyone knows if it's possible to compile OpenCV with 32 bit float support on the meanStdDev method, or if there are any alternative methods that can be recommended. I realise for example, that I should be able to find the average using cuda::sum, cuda::subtract and cuda::sqrSum. But this requires a bunch of kernel launches, and in my particular case, every microsecond counts.
Anyways, thanks in advance for your help!

Answer 1

I find it really weird that the cv::cuda version only supports CV_8U1, because it literally calls the npp function nppiMean_StdDev_8u_C1R, and versions for more image types exist.
void meanStdDev_32FC1M(cv::cuda::GpuMat src, cv::cuda::GpuMat mask, double *mean, double *stddev)
{
CV_Assert(src.type() == CV_32FC1);
double *mean_dev, *stddev_dev;
cudaMalloc((void**)&mean_dev, sizeof(double));
cudaMalloc((void**)&stddev_dev, sizeof(double));
NppiSize sz;
sz.width = src.cols;
sz.height = src.rows;
int bufSize;
nppiMeanStdDevGetBufferHostSize_32f_C1R(sz, &bufSize);//nppSafeCall
cv::cuda::BufferPool pool(cv::cuda::Stream::Null());
cv::cuda::GpuMat buf = pool.getBuffer(1, bufSize, CV_8UC1);
nppiMean_StdDev_32f_C1MR(src.ptr<Npp32f>(), static_cast<int>(src.step), mask.ptr<Npp8u>(), static_cast<int>(mask.step), sz, buf.ptr<Npp8u>(), mean_dev, stddev_dev);
cudaMemcpy(mean, mean_dev, sizeof(double), cudaMemcpyDeviceToHost);
cudaMemcpy(stddev, stddev_dev, sizeof(double), cudaMemcpyDeviceToHost);
cudaFree(mean_dev);
cudaFree(stddev_dev);
}