andr3w's profile - activity

You have set the path for bin directory of CUDA, in environment variables?

I do not know how things work in python, but in c++ you can do the following

cv::Mat bgrImage = cv::imread("test.jpg");
std::vector<cv::Mat> bgrChannels;

cv::split(bgrImage, bgrChannels);  // split multi-channels into single-channel
int blue = cv::countNonZero(bgrChannels[0]) // count the non-zero pixels on Blue channel

cv::split wrap for python cv2.split()

Work for me

const  IplImage *test;
test = cvLoadImage(argv[3], false);
cv::Mat mat(test, false);

pkg-config --modversion opencv
2.4.4

Hi, u can install the opencv library from the RPi repository

What object you want to detect?

U can use medianblur/Gaussianblur to reduce some noise and also u can use algorithms from photo module(this algorithms are slowly)

First you need to set Properties > Configuration Properties > Linker > Advanced > Target Machine and select x64 Second you have to recompile OpenCV for x64

You need to install cmake and mingw if you don't have them. Then set the environment variable for them.