Graph model-based salient object detection using objectness and multiple saliency cues

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalNot applicablepeer-review

View graph of relations

Author(s)

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)188-202
Journal / PublicationNeurocomputing
Volume323
Early online date5 Oct 2018
StatePublished - 5 Jan 2019

Abstract

Recent years have witnessed increasing interest in salient object detection, which aims at stimulating the human visual attention mechanism to detect and segment the most attractive object in natural scenes, and can be widely applied in numerous computer vision tasks. In this paper, by considering both objectness cue and saliency detection, we propose a graph model-based bottom-up salient object detection framework by fusing multiple saliency maps using low-level features and objectness features under a manifold ranking framework. Specifically, for each feature, we utilize geodesic distance between any two superpixels to construct the affinity matrix and un-normalized Laplacian matrix of the graph. Then, we apply saliency optimization to refine each saliency map generated by manifold ranking with the first-stage query, and integrate saliency maps corresponding to different features by multilayer cellular automata in the final stage. Extensive experimental results demonstrate that our method can deliver promising performance in comparison to several state-of-the-art bottom-up methods on many benchmark datasets.

Research Area(s)

  • Graph model, Manifold ranking, Multiple cues, Objectness, Salient object

Citation Format(s)

Graph model-based salient object detection using objectness and multiple saliency cues. / Ji, Yuzhu; Zhang, Haijun; Tseng, Kuo-Kun; Chow, Tommy W.S.; Wu, Q. M. Jonathan.

In: Neurocomputing, Vol. 323, 05.01.2019, p. 188-202.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalNot applicablepeer-review