Optimizing multi-graph learning based salient object detection

作者：

Highlights：

• Multiple features are measured by multiple distance metrics to cope with variant scenes.

• Introducing the eye fixations as foreground seeds to locate salient regions in crowded environments.

• An optimized multi-graph based learning algorithm is proposed to leverage the complementary nature of multiple graphs to obtain the more stable and reliable saliency map.

摘要

Highlights•Multiple features are measured by multiple distance metrics to cope with variant scenes.•Introducing the eye fixations as foreground seeds to locate salient regions in crowded environments.•An optimized multi-graph based learning algorithm is proposed to leverage the complementary nature of multiple graphs to obtain the more stable and reliable saliency map.

论文关键词：Salient object detection,Multi-graph learning,Superpixel,Fixation and boundary cues

论文评审过程：Received 17 December 2016, Revised 12 February 2017, Accepted 28 March 2017, Available online 31 March 2017, Version of Record 5 April 2017.

论文官网地址：https://doi.org/10.1016/j.image.2017.03.023