首页 | 本学科首页   官方微博 | 高级检索  
     

基于颜色信息相位谱的显著性检测
引用本文:李武跃,李志强,方涛,霍宏,葛卫丽. 基于颜色信息相位谱的显著性检测[J]. 上海交通大学学报, 2008, 42(10): 1613-1617
作者姓名:李武跃  李志强  方涛  霍宏  葛卫丽
作者单位:上海交通大学,图像处理与模式识别研究所,上海,200240;武警工程学院,指挥自动化教研室,西安,710086
基金项目:国家重点基础研究发展计划(973计划),国家重点基础研究发展计划(973计划)
摘    要:为了快速搜索场景中的重要目标,依据人类视觉系统的特点,提出了一种基于颜色信息相位谱的显著性检测模型. 通过分析图像颜色相位谱信息,建立显著性图谱,它能够表示出场景中重要目标的位置. 实验结果表明,在复杂背景下,该算法能够较好地检测出和人类视觉相一致的重要区域.

关 键 词:目标检测  离散余弦变换  相位谱  视觉显著性
收稿时间:2007-10-22

Saliency Detection Based on Phase Spectrum of Color Information
LI Wu-yue,LI Zhi-qiang,FANG Tao,HUO Hong,GE Wei-li. Saliency Detection Based on Phase Spectrum of Color Information[J]. Journal of Shanghai Jiaotong University, 2008, 42(10): 1613-1617
Authors:LI Wu-yue  LI Zhi-qiang  FANG Tao  HUO Hong  GE Wei-li
Affiliation:(1. Institute of Pattern Recognition & Image Processing, Shanghai Jiaotong University,Shanghai 200240, China; 2. Staff Room of Command Automatization, Engineering College of Chinese Armed Force Police, Xi’an 710086, China)
Abstract:It is still a challenge to build a computing model of saliency detection by simulating the complex human vision system. Combining the characteristics of human visual system and previous studies in saliency, a saliency detection model based on phase spectrum of color information was proposed. A saliency map, in which the regions of important targets are pop out, was generated by using the proposed model. The experimental results indicate that the saliency regions in complex scene detected by our method are consistent with the attention regions of human vision in bottom up stage.
Keywords:target detection  discrete cosine transform  phase spectrum  visual saliency
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《上海交通大学学报》浏览原始摘要信息
点击此处可从《上海交通大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号