undefined

Multi-Channel Fused Lasso for Motion Detection in Dynamic Video Scenarios

Year of publication

2023

Authors

Gao Rong; Liu Xin; Yang Jingyu; Yue Huanjing

Abstract

Motion detection is a fundamental step in analyzing video sequences, capable of enhancing consumer electronics products with increased intelligence, interactivity, and convenience. Structured and fused sparsity has been used in previous works to normalize the foreground signal due to the foreground’s spatial and temporal coherence. As far as we are aware, no previous works have studied the group prior to multi-channels (such as the RGB) to the foreground signals. However, a multi-channel signal is the correct representation of a pixel. Under the condition that one pixel is equal (similar) to its neighboring pixels, it’s reasonable that the three channels of RGB should also be identical (similar). This work investigates the smoothness of multi-channel signals by proposing a novel regularizer named the Multi-Channel Fused Lasso (MCFL). Specifically, we introduce a two-channel structure to implement motion detection. First, low-rank matrix decomposition is performed on the video footage along different planes. Low-rank background and sparse foreground (rough foreground candidate for the second pass) are segmented from the video sequence. Further, MCFL regularization is used for sparse signal recovery to improve the performance of the foreground mask. The proposed method is validated on different challenging videos. Sufficient experimental results show that our method is effective in a variety of challenging scenarios. Compared with the current best sparsely-based method, the performance of F-Measure improves by 0.4, 0.4, and 0.1 respectively on the I2R, BMC, and CDnet2014 datasets. Our approach is also competitive compared to the deep learning models. Our code can be obtained at https://github.com/linuxsino/MCFL.
Show more

Organizations and authors

Publication type

Publication format

Article

Parent publication type

Journal

Article type

Original article

Audience

Scientific

Peer-reviewed

Peer-Reviewed

MINEDU's publication type classification code

A1 Journal article (refereed), original research

Publication channel information

​Publication forum

57531

​Publication forum level

1

Open access

Open access in the publisher’s service

No

Open access of publication channel

Partially open publication channel

Self-archived

No

Other information

Fields of science

Computer and information sciences

Keywords

[object Object],[object Object],[object Object],[object Object],[object Object],[object Object]

Internationality of the publisher

International

International co-publication

Yes

Co-publication with a company

No

DOI

10.1109/TCE.2023.3341908

The publication is included in the Ministry of Education and Culture’s Publication data collection

Yes