Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement

Yijun Yan, Jinchang Ren, Genyun Sun, Huimin Zhao, Junwei Han, Xuelong Li, Stephen Marshall, Jin Zhan

Research output: Contribution to journalArticle

73 Citations (Scopus)
187 Downloads (Pure)

Abstract

Visual attention is a kind of fundamental cognitive capability that allows human beings to focus on the region of interests (ROIs) under complex natural environments. What kind of ROIs that we pay attention to mainly depends on two distinct types of attentional mechanisms. The bottom-up mechanism can guide our detection of the salient objects and regions by externally driven factors, i.e. color and location, whilst the top-down mechanism controls our biasing attention based on prior knowledge and cognitive strategies being provided by visual cortex. However, how to practically use and fuse both attentional mechanisms for salient object detection has not been sufficiently explored. To the end, we propose in this paper an integrated framework consisting of bottom-up and top-down attention mechanisms that enable attention to be computed at the level of salient objects and/or regions. Within our framework, the model of a bottom-up mechanism is guided by the gestalt-laws of perception. We interpreted gestalt-laws of homogeneity, similarity, proximity and figure and ground in link with color, spatial contrast at the level of regions and objects to produce feature contrast map. The model of top-down mechanism aims to use a formal computational model to describe the background connectivity of the attention and produce the priority map. Integrating both mechanisms and applying to salient object detection, our results have demonstrated that the proposed method consistently outperforms a number of existing unsupervised approaches on five challenging and complicated datasets in terms of higher precision and recall rates, AP (average precision) and AUC (area under curve) values.
Original languageEnglish
Pages (from-to)65-78
Number of pages14
JournalPattern Recognition
Volume79
Early online date5 Feb 2018
DOIs
Publication statusPublished - 31 Jul 2018

Keywords

  • background connectivity
  • Gestalt laws guided optimization
  • image saliency detection
  • feature fusion
  • human vision perception

Fingerprint Dive into the research topics of 'Unsupervised image saliency detection with Gestalt-laws guided optimization and visual attention based refinement'. Together they form a unique fingerprint.

  • Projects

    Research Output

    • 73 Citations
    • 2 Article
    • 1 Doctoral Thesis
  • Cognitive fusion of thermal and visible imagery for effective detection and tracking of pedestrians in videos

    Yan, Y., Ren, J., Zhao, H., Sun, G., Wang, Z., Zheng, J., Marshall, S. & Soraghan, J., 4 Dec 2017, In : Cognitive Computation. 11 p.

    Research output: Contribution to journalArticle

    Open Access
    File
  • 36 Citations (Scopus)
    52 Downloads (Pure)

    Background prior-based salient object detection via deep reconstruction residual

    Han, J., Zhang, D., Hu, X., Guo, L., Ren, J. & Wu, F., Aug 2015, In : IEEE Transactions on Circuits and Systems for Video Technology. 25, 8, p. 1309-1321 13 p.

    Research output: Contribution to journalArticle

    Open Access
    File
  • 311 Citations (Scopus)
    317 Downloads (Pure)

    Student Theses

    Cognitive feature fusion for effective pattern recognition in multi-modal images and videos

    Author: Yan, Y., 15 Oct 2018

    Supervisor: Ren, J. (Supervisor) & Soraghan, J. (Supervisor)

    Student thesis: Doctoral Thesis

    Cite this