期刊文献+

融合深度信息的视觉注意计算模型 被引量:11

Depth Information Fused Computational Model of Visual Attention
在线阅读 下载PDF
导出
摘要 针对Itti模型在特征选择上的局限性,借鉴心理学中有关视觉注意的研究成果,提出一种融合深度信息的视觉注意计算模型。该模型在基于图像分割的自适应立体匹配基础上提取深度特征,与亮度、方向、颜色特征相结合,实现空间显著性度量,并采用侧抑机制和WTA机制得到注意焦点。实验结果表明,新模型能较好地反映空间立体视觉信息对注意的影响,使计算结果能更符合人类视觉。 The Itti model has a limitation on choosing features.Inspired by the visual attention results in the psychology,this paper proposes a computational model of visual attention.Based on the segment-based stereo matching which using belief propagation and a self-adapting dissimilarity measure,the depth information is computed.Intensity,color,orientation and depth information are deployed and create the saliency map.The saliency map is deployed to the FOA through inhibition of return and WTA mechanism.Experimental results show the model effectively reflects the influence of stereo vision to attention,and the computational result is more consistent with the human vision.
出处 《计算机工程》 CAS CSCD 北大核心 2010年第20期200-202,共3页 Computer Engineering
基金 国家"863"计划基金资助项目(2007AA04Z116) 福建省科技专项课题基金资助项目(2008F5043) 安徽省高校自然科学基金资助项目(KJ2008B107) 福建省教育科研基金资助项目(JA08229)
关键词 注意焦点 深度信息 立体视觉 Itti模型 focus of attention depth information stereo vision Itti model
  • 相关文献

参考文献7

  • 1Laurent I,Christof K,Ernst N.A Model of Sliency-based Visual Attention for Raid Scene Analysis[J].IEEE Transactions on PAMI,1998,20(11):1254-1259.
  • 2Laurent I,Christof K.A Comparison of Feature Combination Strategies for Saliency-based Visual Attention[C] //Proc.of SPIE'99.San Jose,California,USA:[s.n.] ,1999:473-482.
  • 3Laurent I,Gold C,Koch C.Visual Attention and Target Detection in Cluttered Natural Scenes[J].Optical Engineering,2001,40(9):1784-1793.
  • 4Bleyer M,Gelautz M.A Layered Stereo Matching Algorithm Using Image Segmentation and Global Visibility Constraints[J].ISPRS Journal of Photogrammetry and Remote Sensing,2005,59(3):128-150.
  • 5Comaniciu D,Meer P.Mean Shift:A Robust Approach Toward Feature Space Analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
  • 6Boykov Y,Kolmogorov V.An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124-1137.
  • 7Felzenszwalb P F,Huttenlocher D P.Efficient Belief Propagation for Early Vision[C] //Proc.of CVPR'04.Washington D.C.,USA:IEEE Press,2004.

同被引文献119

  • 1罗钟铉,刘成明.灰度图像匹配的快速算法[J].计算机辅助设计与图形学学报,2005,17(5):966-970. 被引量:72
  • 2罗三定,陈海波.基于区域增长的自适应窗口立体匹配算法[J].中南大学学报(自然科学版),2005,36(6):1042-1047. 被引量:11
  • 3刘伟,汪云九,童勤业.基于视觉注意计算模型的图像压缩新方法[J].科技通报,2006,22(6):775-780. 被引量:2
  • 4李博,杨丹,张小洪.基于Harris多尺度角点检测的图像配准新算法[J].计算机工程与应用,2006,42(35):37-40. 被引量:32
  • 5Itti L, Koch C, Niebur E. A Model of Saliency-based Visual Attention for Rapid Scene Analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(11): 1254-1259.
  • 6Wolfe J M. Guided Search 2.0: A Revised Model of Visual Search[J]. Psychonomic Bulletin & Review, 1994, 1(2): 202-238.
  • 7Henderson J M. Human Gaze Control During Real-world Scene Perception[J]. Trends in Cognitive Sciences, 2003, 7(11): 498-504.
  • 8Wolf L, Bileschi S. A Critical View of Context[J]. International Journal of Computer Vision, 2006, 69(2): 251-261.
  • 9Carson C, Belongie S, Greenspan H, et al. Blobworld: Image Segmentation Using Expectation-maximization and Its Application to Image Querying[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(8): 1026-1038.
  • 10Klaus A. Segment-based Stereo Matching Using Belief Propagation and a Self-adapting Dissimilarity Measure [C]//Proc. of International Conference on Patter Recognition, 2006.

引证文献11

二级引证文献24

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部