扫描手机二维码

欢迎您的访问
您是第 位访客

开通时间:..

最后更新时间:..

  • 曹俊杰 ( 副教授 )

    的个人主页 http://faculty.dlut.edu.cn/jjcao/en/index.htm

  •   副教授   硕士生导师
论文成果 当前位置: jjcao >> 科学研究 >> 论文成果
OBJECT LEVEL IMAGE SALIENCY BY HIERARCHICAL SEGMENTATION

点击次数:
论文类型:会议论文
发表时间:2013-09-15
收录刊物:EI、CPCI-S、Scopus
页面范围:1772-1776
关键字:Object level image saliency; hierarchical segmentation; random walks; heat diffusion
摘要:Conventional saliency detection approaches are human fixation detection and single dominant region detection. However, real-world photographs usually consist of multiple dominant regions. We propose a saliency detection method with the aim to highlight objects as a whole and distinguish objects with different saliency levels. It combines the bottom-up approach and top-down approach via two nested levels of hierarchical segmentations - the coarse level objects and fine level details. We first calculate a preliminary saliency on the fine patches with a random walk model. Then a location cue and an object-level cue are fused to refine the preliminary saliency to emphasize the objects against the background. At last, the object-level saliency map is synthesized via a heat diffusion process restricted by the coarse level patches to enhance object saliency and distinguish saliency between different objects. Extensive evaluation on a publicly available database verifies that our method outperforms the state-of-the-art algorithms.

 

辽ICP备05001357号 地址:中国·辽宁省大连市甘井子区凌工路2号 邮编:116024
版权所有:大连理工大学