University of Oulu

S. Gao, Q. Ye, L. Liu, A. Kuijper and X. Ji, "A Graphical Social Topology Model for RGB-D Multi-Person Tracking," in IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 11, pp. 4305-4320, Nov. 2021, doi: 10.1109/TCSVT.2021.3049397

A graphical social topology model for RGB-D Multi-Person Tracking

Saved in:
Author: Gao, Shan1,2; Ye, Qixiang3; Liu, Li4,5;
Organizations: 1Unmanned System Research Institute, Northwestern Polytechnical University, Xi’an, China
2Tsinghua University, Beijing, China
3School of Electronic, Electrical, and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China
4College of System Engineering, National University of Defense Technology, Changsha, China
5Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland
6Fraunhofer Institute for Computer Graphics Research (IGD), Darmstadt, Germany
7Technical University of Darmstadt, Darmstadt, Germany
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 9.8 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2021122162759
Language: English
Published: Institute of Electrical and Electronics Engineers, 2021
Publish Date: 2021-12-21
Description:

Abstract

Tracking multiple persons is a challenging task especially when persons move in groups and occlude one another. Existing research have investigated the problems of group division and segmentation; however, lacking overall person-group topology modeling limits the ability to handle complex person and group dynamics. We propose a Graphical Social Topology (GST) model in the RGB-D data domain, and estimate object group dynamics by jointly modeling the group structure and states of persons using RGB-D topological representation. With our topology representation, moving persons are not only assigned to groups, but also dynamically connected with each other, which enables in-group individuals to be correctively associated and the cohesion of each group to be precisely modeled. Using the learned typical topology pattern and group online update modules, we infer the birth/death and merging/splitting of dynamic groups. With the GST model, the proposed multi-person tracker can naturally facilitate the occlusion problem by treating the occluded object and other in-group members as a whole, while leveraging overall state transition. Experiments on different RGB-D and RGB datasets confirm that the proposed multi-person tracker improves the state-of-the-arts.

see all

Series: IEEE transactions on circuits and systems for video technology
ISSN: 1051-8215
ISSN-E: 1558-2205
ISSN-L: 1051-8215
Volume: 31
Issue: 11
Pages: 4305 - 4320
DOI: 10.1109/TCSVT.2021.3049397
OADOI: https://oadoi.org/10.1109/TCSVT.2021.3049397
Type of Publication: A1 Journal article – refereed
Field of Science: 113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
Subjects:
Copyright information: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.