Unsupervised Adversarial Learning for Dynamic Background Modeling

Maryam Sultana, Arif Mahmood, Thierry Bouwmans, Soon Ki Jung

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

8 Scopus citations


Dynamic Background Modeling (DBM) is a crucial task in many computer vision based applications such as human activity analysis, traffic monitoring, surveillance, and security. DBM is extremely challenging in scenarios like illumination changes, camouflage, intermittent object motion or shadows. In this study, we proposed an end-to-end framework based on Generative Adversarial Network, which can generate dynamic background information for the task of DBM in an unsupervised manner. Our proposed model can handle the problem of DBM in the presence of the challenges mentioned above by generating data similar to the desired information. The primary aim of our proposed model during training is to learn all the dynamic changes in a scene-specific background information. While, during testing, inverse mapping of data to latent space representation in our model generates dynamic backgrounds similar to test data. The comparative analysis of our proposed model upon experimental evaluations on SBM.net and SBI benchmark datasets has outperformed eight existing methods for DBM in many challenging scenarios.

Original languageEnglish
Title of host publicationFrontiers of Computer Vision - 26th International Workshop, IW-FCV 2020, Revised Selected Papers
EditorsWataru Ohyama, Soon Ki Jung
Number of pages14
ISBN (Print)9789811548178
StatePublished - 2020
EventInternational Workshop on Frontiers of Computer Vision, IW-FCV 2020 - Ibusuki, Japan
Duration: 20 Feb 202022 Feb 2020

Publication series

NameCommunications in Computer and Information Science
Volume1212 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


ConferenceInternational Workshop on Frontiers of Computer Vision, IW-FCV 2020


  • Background initialization
  • Generative Adversarial Networks
  • Unsupervised learning


Dive into the research topics of 'Unsupervised Adversarial Learning for Dynamic Background Modeling'. Together they form a unique fingerprint.

Cite this