The Emerging Field of Graph Signal Processing for Moving Object Segmentation

Jhony H. Giraldo, Sajid Javed, Maryam Sultana, Soon Ki Jung, Thierry Bouwmans

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

41 Scopus citations

Abstract

Moving Object Segmentation (MOS) is an important topic in computer vision. MOS becomes a challenging problem in the presence of dynamic background and moving camera videos such as Pan–Tilt–Zoom cameras (PTZ). The MOS problem has been solved using unsupervised and supervised learning strategies. Recently, new ideas to solve MOS using semi-supervised learning have emerged inspired from the theory of Graph Signal Processing (GSP). These new algorithms are usually composed of several steps including: segmentation, background initialization, features extraction, graph construction, graph signal sampling, and a semi-supervised learning algorithm inspired from reconstruction of graph signals. In this work, we summarize and explain the theoretical foundations as well as the technical details of MOS using GPS. We also propose two architectures for MOS using semi-supervised learning and a new evaluation procedure for GSP-based MOS algorithms. GSP-based algorithms are evaluated in the Change Detection (CDNet2014) dataset for MOS, outperforming numerous State-Of-The-Art (SOTA) methods in several challenging conditions.

Original languageEnglish
Title of host publicationFrontiers of Computer Vision - 27th International Workshop, IW-FCV 2021, Revised Selected Papers
EditorsHieyong Jeong, Kazuhiko Sumi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages31-45
Number of pages15
ISBN (Print)9783030816377
DOIs
StatePublished - 2021
Event27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021 - Virtual, Online
Duration: 22 Feb 202123 Feb 2021

Publication series

NameCommunications in Computer and Information Science
Volume1405
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference27th International Workshop on Frontiers of Computer Vision, IW-FCV 2021
CityVirtual, Online
Period22/02/2123/02/21

Keywords

  • Graph Signal Processing
  • Moving Object Segmentation
  • Semi-supervised learning

Fingerprint

Dive into the research topics of 'The Emerging Field of Graph Signal Processing for Moving Object Segmentation'. Together they form a unique fingerprint.

Cite this