opencv3.2提供了cuda很好的支持，cuda的opencv接口，让用户想使用opencv那样去使用cuda，不用写cuda代码

一开始编译opencv有关cuda的代码，opencv 里samples文件夹里有cmakelist可以参考，但是试了之后出现一堆错误，于是去找编译cuda cmake脚本

后来发现cmake里已经自带FindCUDA.cmake了，find_package(CUDA)(注意是大写）就能够找到了，而且像平时那样

target_link_libraries(optical_flow ${OpenCV_LIBS})就好了，但是附上一些最近找的cuda编译方法链接

opencv getting started with cuda: http://on-demand.gputechconf.com/gtc/2013/webinar/gtc-express-itseez-opencv-webinar.pdf

cuda opencv link:

http://opencv.org/platforms/cuda.html

http://docs.opencv.org/2.4/modules/gpu/doc/gpu.html

compile cuda code:

https://stackoverflow.com/questions/31881249/cmake-cuda-opencv

cmake_minimum_required(VERSION 2.8)find_package(CUDA REQUIRED)IF(CUDA_FOUND)    SET(CUDA_NVCC_FLAGS ${CUDA_NVCC_FLAGS};-O3 -gencode arch=compute_20,code=sm_20)    cuda_compile(CudaKernel CudaKernels.cu)    cuda_add_library(CudaKernels CudaKernels.cu)    add_definitions(-DGPU_OPENCV_ENABLE)ENDIF()

cmake findCUDA:

https://cmake.org/cmake/help/v3.0/module/FindCUDA.html#findcuda

cmake CUDA:

How to let cmake find CUDA

https://stackoverflow.com/questions/19980412/how-to-let-cmake-find-cuda

build CUDA with cmake

https://codeyarns.com/2013/09/13/how-to-build-cuda-programs-using-cmake/