Official implementation of Pose Flow: Efficient Online Pose Tracking .

Results on PoseTrack Challenge validation set:

1. Task2: Multi-Person Pose Estimation (mAP)

2. Task3: Pose Tracking (MOTA)

• Python 2.7.13
• OpenCV 3.4.2.16
• OpenCV-contrib 3.4.2.16
• tqdm 4.19.8

1. Download PoseTrack Dataset from PoseTrack to AlphaPose/PoseFlow/posetrack_data/
2. (Optional) Use DeepMatching to extract dense correspondences between adjcent frames in every video, please refer to DeepMatching Compile Error to compile DeepMatching correctly

pip install -r requirements.txt

# Generate correspondences by DeepMatching
# (More Robust but Slower)
cd deepmatching
make clean all
make
cd ..
python matching.py --orb=0 

# Generate correspondences by Orb
# (Faster but Less Robust)
python matching.py --orb=1 

Firstly, using AlphaPose to generate multi-person pose estimation results on videos, please see alpha-pose-results-sample.json to know json format.

Run pose tracking

python tracker.py --dataset=val/test  --orb=1/0

Original poseval has some instructions on how to convert annotation files from MAT to JSON.

Evaluate pose tracking results on validation dataset:

git clone https://github.com/leonid-pishchulin/poseval.git --recursive
cd poseval/py && export PYTHONPATH=$PWD/../py-motmetrics:$PYTHONPATH
cd ../../
python poseval/py/evaluate.py --groundTruth=./posetrack_data/annotations/val \
                    --predictions=./${track_result_dir}/ \
                    --evalPoseTracking --evalPoseEstimation

Please cite these papers in your publications if it helps your research:

@inproceedings{xiu2018poseflow,
  author = {Xiu, Yuliang and Li, Jiefeng and Wang, Haoyu and Fang, Yinghong and Lu, Cewu},
  title = {{Pose Flow}: Efficient Online Pose Tracking},
  booktitle={BMVC},
  year = {2018}
}