OpenPose


Role: Lead author.

Description: First real-time multi-person system to jointly detect human body, hand, facial, and foot keypoints (in total 135 keypoints) on single images.

GitHub repository: https://github.com/CMU-Perceptual-Computing-Lab/openpose

GitHub repository (training): https://github.com/CMU-Perceptual-Computing-Lab/openpose_train

Press coverage of OpenPose: https://www.gineshidalgo.com/#section-5953e33f5012a

RoboCup acknowledgements: https://github.com/CMU-Perceptual-Computing-Lab/openpose/issues/175#issue-246557917