CPL - Chalmers Publication Library
| Utbildning | Forskning | Styrkeområden | Om Chalmers | In English In English Ej inloggad.

Co-saliency detection via similarity-based saliency propagation

Chenjie Ge (Institutionen för signaler och system, Signalbehandling) ; Keren Fu (Institutionen för signaler och system, Signalbehandling) ; Yijun Li ; Jie Yang ; Pengfei Shi ; Li Bai
2015 IEEE International Conference on Image Processing (ICIP) p. 1845 - 1849. (2015)
[Konferensbidrag, refereegranskat]

In this paper, we present a method for discovering the common salient objects from a set of images. We treat co-saliency detection as a pairwise saliency propagation problem, which utilizes the similarity between each pair of images to measure the common property with the guidance of a single saliency map image. Given the pairwise co-salient foreground maps, pairwise saliency is optimized by combining the initial background cues. Pairwise co-salient maps are then fused according to a novel fusion strategy based on the focus of human attention. Finally we adopt an integrated multi-scale scheme to obtain the pixel-level saliency map. Our proposed model makes the existing single saliency model perform well in co-saliency detection and is not overly sensitive to the initial saliency model selected. Extensive experiments on two benchmark databases show the superiority of our co-saliency model against the state-of-the-art methods both subjectively and objectively.

Nyckelord: Co-saliency detection, pairwise saliency propagation, optimization, attention based fusion



Denna post skapades 2016-11-30. Senast ändrad 2017-07-03.
CPL Pubid: 245744

 

Institutioner (Chalmers)

Institutionen för signaler och system, Signalbehandling (1900-2017)

Ämnesområden

Bildanalys

Chalmers infrastruktur