High-speed Multi-person Pose Estimation with Deep Feature Transfer

Huang, Ying, Shum, Hubert, Ho, Edmond and Aslam, Nauman (2020) High-speed Multi-person Pose Estimation with Deep Feature Transfer. Computer Vision and Image Understanding, 197198. p. 103010. ISSN 1077-3142

[img] Text
Paper.pdf - Accepted Version
Restricted to Repository staff only until 9 June 2021.
Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0.

Download (2MB) | Request a copy
Official URL: https://doi.org/10.1016/j.cviu.2020.103010

Abstract

Recent advancements in deep learning have significantly improved the accuracy of multi-person pose estimation from RGB images. However, these deep learning methods typically rely on a large number of deep refinement modules to refine the features of body joints and limbs, which hugely reduce the run-time speed and therefore limit the application domain. In this paper, we propose a feature transfer framework to capture the concurrent correlations between body joint and limb features. The concurrent correlations of these features form a complementary structural relationship, which mutually strengthens the network’s inferences and reduces the needs of refinement modules. The transfer sub-network is implemented with multiple convolutional layers, and is merged with the body part detection network to form an end-to-end system. The transfer relationship is automatically learned from ground-truth data instead of being manually encoded, resulting in a more general and efficient design. The proposed framework is validated on the multiple popular multi-person pose estimation benchmarks - MPII, COCO 2018 and PoseTrack 2017 and 2018. Experimental results show that our method not only significantly increases the inference speed to 73.8 frame per second (FPS), but also attains comparable state-of-the-art performance.

Item Type: Article
Uncontrolled Keywords: Human pose estimation, Feature transfer, Deep learning
Subjects: G400 Computer Science
G500 Information Systems
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Elena Carlaw
Date Deposited: 02 Jun 2020 14:39
Last Modified: 14 Aug 2020 08:00
URI: http://nrl.northumbria.ac.uk/id/eprint/43318

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics