Skip to main content

Research Repository

Advanced Search

Human Pose Estimation via Convolutional Part Heatmap Regression

Bulat, Adrian; Tzimiropoulos, Georgios

Authors

Adrian Bulat

Georgios Tzimiropoulos



Abstract

This paper is on human pose estimation using Convolutional Neural Networks. Our main contribution is a CNN cascaded architecture specifically designed for learning part relationships and spatial context, and robustly inferring pose even for the case of severe part occlusions. To this end, we propose a detection-followed-by-regression CNN cascade. The first part of our cascade outputs part detection heatmaps and the second part performs regression on these heatmaps. The benefits of the proposed architecture are multi-fold: It guides the network where to focus in the image and effectively encodes part constraints and context. More importantly, it can effectively cope with occlusions because part detection heatmaps for occluded parts provide low confidence scores which subsequently guide the regression part of our net-work to rely on contextual information in order to predict the location of these parts. Additionally, we show that the proposed cascade is flexible enough to readily allow the integration of various CNN architectures for both detection and regression, including recent ones based on residual learning. Finally, we illustrate that our cascade achieves top performance on the MPII and LSP data sets. Code can be downloaded from http://www.cs.nott.ac.uk/~psxab5/

Citation

Bulat, A., & Tzimiropoulos, G. (2016). Human Pose Estimation via Convolutional Part Heatmap Regression. In Computer Vision – ECCV 2016 (717-732). https://doi.org/10.1007/978-3-319-46478-7_44

Conference Name 14th European Conference on Computer Vision (EECV 2016)
Conference Location Amsterdam, The Netherlands
Start Date Oct 11, 2016
End Date Oct 14, 2016
Acceptance Date Jul 11, 2016
Online Publication Date Sep 16, 2016
Publication Date Sep 16, 2016
Deposit Date Sep 9, 2016
Publicly Available Date Mar 29, 2024
Publisher Springer
Peer Reviewed Peer Reviewed
Volume 9911
Pages 717-732
Series Title Lecture Notes in Computer Science
Series ISSN 1611-3349
Book Title Computer Vision – ECCV 2016
ISBN 978-3-319-46477-0
DOI https://doi.org/10.1007/978-3-319-46478-7_44
Keywords Human pose estimation, Part heatmap regression, Convolutional Neural Networks
Public URL https://nottingham-repository.worktribe.com/output/824157
Publisher URL https://link.springer.com/chapter/10.1007/978-3-319-46478-7_44
Related Public URLs http://www.eccv2016.org/
Additional Information The final publication is available at http://link.springer.com/book/10.1007%2F978-3-319-46478-7

Workshops/short Courses were held October 8-10 and 15-16, 2016

Files





You might also like



Downloadable Citations