GitHub - KaiJin1995/dense_flow: OpenCV Implementation of optical flow algorithms of denseFlow

KaiJin1995 / dense_flow Public

forked from wanglimin/dense_flow

Notifications You must be signed in to change notification settings
Fork 0
Star 1

OpenCV Implementation of optical flow algorithms of denseFlow_gpu

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 28 Commits
.gitignore		.gitignore
CMakeLists.txt		CMakeLists.txt
README		README
denseFlow.cpp		denseFlow.cpp
denseFlow_gpu.cpp		denseFlow_gpu.cpp
denseImage.cpp		denseImage.cpp
extracOpticalFlow.m		extracOpticalFlow.m
extractOpticalFlow.m		extractOpticalFlow.m
extractOpticalFlow_gpu.m		extractOpticalFlow_gpu.m
test.cpp		test.cpp

Repository files navigation

这个文件主要用来对yj xiong 的论文“towards good practices for very deep two-stream convnets"中的image 和　optical flow图片提取进行修改。
修改后的代码可以跟其源码中的数据输入匹配，完成训练。


We should use test.cpp

mkdir build
cd build
cmake -D CUDA_USE_STATIC_CUDA_RUNTIME=OFF ..
make 
./denseflow



then  you can get the image and the flow

add:   在test.cpp中，需要注意光流算法的选取，type选取为0时，光流算法是farn光流法，当type选取为1时，为tvl1光流法，当type选取2时，为brox光流法。
经过测试，发现使用tvl1光流法要优于farn光流法，具体区别参考博客http://blog.csdn.net/small_arm/article/details/78283205