Peeking into Occluded Joints: A Novel Framework for Crowd Pose Estimation

Lingteng Qiu, Xuanye Zhang, Yanran Li, Guanbin Li, Xiaojun Wu, Zixiang Xiong, Xiaoguang Han, Shuguang Cui

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Although occlusion widely exists in nature and remains a fundamental challenge for pose estimation, existing heatmap-based approaches suffer serious degradation on occlusions. Their intrinsic problem is that they directly localize the joints based on visual information; however, the invisible joints are lack of that. In contrast to localization, our framework estimates the invisible joints from an inference perspective by proposing an Image-Guided Progressive GCN module which provides a comprehensive understanding of both image context and pose structure. Moreover, existing benchmarks contain limited occlusions for evaluation. Therefore, we thoroughly pursue this problem and propose a novel OPEC-Net framework together with a new Occluded Pose (OCPose) dataset with 9k annotated images. Extensive quantitative and qualitative evaluations on benchmarks demonstrate that OPEC-Net achieves significant improvements over recent leading works. Notably, our OCPose is the most complex occlusion dataset with respect to average IoU between adjacent instances. Source code and OCPose will be publicly available.
Original languageEnglish
Title of host publicationComputer Vision -- ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIX
EditorsAndrea Vedaldi, Horst Bischof, Thomas Brox, Jan-Michael Frahm
Place of PublicationCham
PublisherSpringer
Pages488-504
Number of pages17
ISBN (Electronic)978-3-030-58529-7
ISBN (Print)978-3-030-58528-0
DOIs
Publication statusPublished - 13 Nov 2020
Event16th European Conference on Computer Vision - Virtual conference
Duration: 23 Aug 202028 Aug 2020
https://eccv2020.eu/

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Cham
Volume12364
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference16th European Conference on Computer Vision
Abbreviated titleECCV 2020
CityVirtual conference
Period23/08/2028/08/20
Internet address

Keywords / Materials (for Non-textual outputs)

  • Pose estimation
  • Occlusion
  • Progressive GCN

Fingerprint

Dive into the research topics of 'Peeking into Occluded Joints: A Novel Framework for Crowd Pose Estimation'. Together they form a unique fingerprint.

Cite this