Video saliency detection based on temporal difference and pixel gradient

Xiangwei Lu, Muwei Jian, Rui Wang, Zhichao Yun*, Peiguang Lin, Hui Yu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Downloads (Pure)

Abstract

Even though temporal information matters for the quality of video saliency detection, many problems such as bad performance in time-space coherence and edge continuity still face present network frameworks. In response to these problems, this paper designs a full convolutional neural network, which integrates temporal differential and pixel gradient to fine tune the edges of targets. Meanwhile, the changes of pixel gradients of original images are used to recursively improve the continuity of target edges and details of central areas. The method presented in the paper has been tested with two available public datasets and its effectiveness been proved after it being compared with 6 other widely accepted methods.

Original languageEnglish
Title of host publication2021 26th International Conference on Automation and Computing
Subtitle of host publicationSystem Intelligence through Automation and Computing, ICAC 2021
EditorsChenguang Yang
PublisherIEEE
Number of pages5
ISBN (Electronic)9781860435577
ISBN (Print)9781665443524
DOIs
Publication statusEarly online - 15 Nov 2021
Event26th International Conference on Automation and Computing - Portsmouth, United Kingdom
Duration: 2 Sep 20214 Sep 2021

Conference

Conference26th International Conference on Automation and Computing
Abbreviated titleICAC 2021
Country/TerritoryUnited Kingdom
CityPortsmouth
Period2/09/214/09/21

Keywords

  • Co-Attention
  • Edge refinement
  • Pixels gradient
  • Temporal difference
  • Video saliency detection

Fingerprint

Dive into the research topics of 'Video saliency detection based on temporal difference and pixel gradient'. Together they form a unique fingerprint.

Cite this