计算机工程 ›› 2012, Vol. 38 ›› Issue (17): 209-213.doi: 10.3969/j.issn.1000-3428.2012.17.057

• 人工智能及识别技术 • 上一篇    下一篇

多目标场景下的显著物体提取

马志峰,李 颖,郑 芳,高智勇   

  1. (中南民族大学生物医学工程学院,武汉 430074)
  • 收稿日期:2011-11-25 修回日期:2012-01-12 出版日期:2012-09-05 发布日期:2012-09-03
  • 作者简介:马志峰(1987-),男,硕士研究生,主研方向:图像处理;李 颖、郑 芳,硕士研究生;高智勇(通讯作者),副教授、博士
  • 基金项目:
    国家自然科学基金资助项目(60972158);中南民族大学中央高校基本科研业务费专项基金资助项目(czy12012)

Extraction of Salient Object in Multi-object Scene

MA Zhi-feng, LI Ying, ZHENG Fang, GAO Zhi-yong   

  1. (College of Biomedical Engineering, South-central University for Nationalities, Wuhan 430074, China)
  • Received:2011-11-25 Revised:2012-01-12 Online:2012-09-05 Published:2012-09-03

摘要: 已有获取显著区域的方法存在不能适应实际物体的大小、包含冗余信息及应用范围有限的问题。为此,提出一种多目标场景下的显著物体提取方法。对基于空间的计算模型得到的显著图进行聚类,将多目标场景划分为多个单目标的子场景,在子场景集合中,引入注意转移机制,并使用基于物体的计算模型依次提取显著物体。实验结果表明,该方法能提取图像中的多个显著目标。

关键词: 显著物体, 场景分割, 聚类, 视觉注意, 注意转移

Abstract: Traditional method of significant area obtaining can not adapt the size of real objects, have redundant information, and the application scope is limited. In order to solve the problems above, this paper proposes an extraction method of salient object in multi-object scene. It clusters the saliency map obtained by space-based model to divide the multi-object scene into several sub-scenes, and introduces a transference of attention mechanism on the sub-scene sets and the object-based model in order to extract salient objects. Experimental results show that the proposed method can completely and correctly extract the multi-object of the images.

Key words: salient object, scene segmentation, clustering, visual attention, attention shift

中图分类号: