ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1811.12004
11
291

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

29 November 2018
D. Osokin
    3DH
ArXivPDFHTML
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, 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\unicodexAE\unicode{xAE}\unicodexAE NUC 6i7KYB mini PC and 26 fps on CoreTM^{TM}TM 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\unicodexAE\unicode{xAE}\unicodexAE OpenVINOTM^{TM}TM Toolkit.

View on arXiv
Comments on this paper