icme2021template_accepted.pdf (1.16 MB)

ROBUST CROSS-SCENE FOREGROUND SEGMENTATION IN SURVEILLANCE VIDEO

Download (1.16 MB)
conference contribution
posted on 23.03.2021, 14:46 by D Liang, Z Wei, H Sun, Huiyu Zhou
Training only one deep model for large-scale cross-scenevideo foreground segmentation is challenging due to the off-the-shelf deep learning based segmentor relies on scene-specific structural information. This results in deep mod-els that are scene-biased and evaluations that are scene-influenced.In this paper, we integrate dual modalities(foregrounds’ motion and appearance), and then eliminat-ing features without representativeness of foreground throughattention-module-guided selective-connection structures. It isin an end-to-end training manner and to achieve scene adap-tation in the plug and play style. Experiments indicate theproposed method significantly outperforms the state-of-the-art deep models and background subtraction methods in un-trained scenes – LIMU and LASIESTA. (Codes and datasetwill be available after the anonymous stage.)

History

Author affiliation

School of Informatics

Source

IEEE International Conference on Multimedia and Expo (ICME) 2021 July 5-9, 2021

Version

AM (Accepted Manuscript)

Published in

IEEE International Conference on Multimedia and Expo

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Acceptance date

15/03/2021

Copyright date

2021

Available date

09/07/2021

Publisher DOI

Language

en