Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose

Daniil Osokin

Abstract

In this work we adapt multi-person pose estimation architecture to use it on edge devices. We follow the bottom-up approach from OpenPose (Cao et al., 2017), the winner of COCO 2016 Keypoints Challenge, because of its decent quality and robustness to number of people inside the frame. With proposed network design and optimized post-processing code the full solution runs at 28 frames per second (fps) on Intel® NUC 6i7KYB mini PC and 26 fps on Core i7-6850K CPU. The network model has 4.1M parameters and 9 billions floating-point operations (GFLOPs) complexity, which is just ∼15% of the baseline 2-stage OpenPose with almost the same quality. The code and model are available as a part of Intel® OpenVINOTM Toolkit.

Download


Paper Citation


in Harvard Style

Osokin D. (2019). Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 744-748. DOI: 10.5220/0007555407440748


in Bibtex Style

@conference{icpram19,
author={Daniil Osokin},
title={Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={744-748},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007555407440748},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose
SN - 978-989-758-351-3
AU - Osokin D.
PY - 2019
SP - 744
EP - 748
DO - 10.5220/0007555407440748