Please Note: This repository is no longer maintained. For extracting optical flow from videos please use this latest tool from Open-MMLAB.
Extracting dense flow field given a video.
- LibZip:
to install on ubuntu
apt-get install libzip-devon macbrew install libzip
Please see the opencv-3.1 branch. Many thanks to @victorhcm for the contributions!
git clone --recursive http://github.com/yjxiong/dense_flow
mkdir build && cd build
cmake .. && make -j
./extract_gpu -f=test.avi -x=tmp/flow_x -y=tmp/flow_y -i=tmp/image -b=20 -t=1 -d=0 -s=1 -o=dir
test.avi: input videotmp: folder containing RGB images and optical flow imagesdir: output generated images to folder. if set tozip, will write images to zip files instead.
The warp optical flow is used in the following paper
@inproceedings{TSN2016ECCV,
author = {Limin Wang and
Yuanjun Xiong and
Zhe Wang and
Yu Qiao and
Dahua Lin and
Xiaoou Tang and
Luc {Van Gool}},
title = {Temporal Segment Networks: Towards Good Practices for Deep Action Recognition},
booktitle = {ECCV},
year = {2016},
}
To extract warp flow, use the command
./extract_warp_gpu -f test.avi -x tmp/flow_x -y tmp/flow_y -i tmp/image -b 20 -t 1 -d 0 -s 1 -o dir