Spectral salient object detection
Paper i proceeding, 2014

Many existing methods for salient object detection are performed by over-segmenting images into non-overlapping regions, which facilitate local/global color statistics for saliency computation. In this paper, we propose a new approach: spectral salient object detection, which is benefited from selected attributes of normalized cut, enabling better retaining of holistic salient objects as comparing to conventionally employed pre-segmentation techniques. The proposed saliency detection method recursively bi-partitions regions that render the lowest cut cost in each iteration, resulting in binary spanning tree structure. Each segmented region is then evaluated under criterion that fit Gestalt laws and statistical prior. Final result is obtained by integrating multiple intermediate saliency maps. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method against 13 state-of-the-art approaches to salient object detection.

Pre-segmentation

Gestalt laws

Normalized cut

Salient object detection

Partition

Författare

Keren Fu

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

C Gong

Shanghai Jiaotong University

Irene Yu-Hua Gu

Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Jie Yang

Shanghai Jiaotong University

Xiangjian He

University of Technology Sydney

Proceedings - IEEE International Conference on Multimedia and Expo

19457871 (ISSN) 1945788X (eISSN)

Vol. 2014-September 6- 6890142

Styrkeområden

Informations- och kommunikationsteknik

Transport

Ämneskategorier

Systemvetenskap

Signalbehandling

Datorseende och robotik (autonoma system)

DOI

10.1109/ICME.2014.6890142

ISBN

978-1-4799-4761-4