一种新的视觉运动注意力计算方法

刘龙; 赵晶; 樊波阳

doi:doi:10.3969/j.issn.1003-501x.2014.03.003

光电工程, 2014, 41 (3): 12, 网络出版: 2014-04-09

一种新的视觉运动注意力计算方法

A New Computational Method of Visual Motion Attention

论文大纲

刘龙 ^*赵晶樊波阳

作者单位

西安理工大学自动化学院, 西安 710048

运动注意力可变块运动估计多尺度融合 motion attention variable block motion estimation multi-scale fusion

摘要

由于运动注意力模型不合理、光流估算的局限性和噪声影响, 对于复杂运动场景, 现有运动注意力计算方法往往不能准确计算出运动显著图。本文提出了一种新的运动注意力计算方法, 该方法首先根据注意力形成机理构建运动注意力模型; 在可变块大小运动估计的基础上计算运动注意力; 最后采用空间多尺度融合得到最终的运动显著图。通过对多个高清视频序列的测试, 表明本文提出的方法比现有方法更能准确地计算出运动显著图。

Abstract

For unreasonable attention model, limitations of optical estimation and noise, the result of existing computational method of visual motion attention sometimes can not reflect real motion attention information for video scene of motion complex. A new computational method of visual motion attention is suggested. In the method, motion attention model is firstly built according to the mechanism of attention. Then, the visual motion attention is computed on basis of variable size block motion estimation. Finally, the final salience map come from the fusion of multi-scale motion attention salience map. The experimental results also show the calculation result of this method is better than that of the existing method.

参考文献

[1] Marr D. Vision [M]. San Francisco: W.H. Freeman, 1982.

[2] Koch C , Ullman S. Shift in selective visual attention : towards the underlying neural circuitry [J]. Human Neurobiology(S0721-9075), 1985, 4(4): 219-227.

[3] Treisman A M, Gelade G. Feature-integration theory of Attention [J]. Cognitive Psychology(S0010-0285), 1980, 12: 97-136.

[4] Treisman A. Features and objects in Visual Processing [J]. Scientific American(S0036-8733), 1986, 253: 114-125.

[5] Itti L, Koch C, Niebur E A. Model of saliency -based visual attention for rapid scene analysis [J]. IEEE Transaction on PAMI (S0162-8828), 1998, 20(11): 1254-1259.

[6] Itti L, Koch C. Computational Modeling of Visual Attention [J]. Nature Reviews Neuroscience(S1759-4758), 2001, 2(3): 194-203.

[7] Ming-Chieh Chi, Chia-Hung Yeh, Mei-Juan Chen. Robust Region-of-Interest Determination Based on User Attention Model Through Visual Rhythm Analysis [J]. IEEE Transaction on Circuits and Systems for Video Technology(S1095-2055), 2009: 1025-1038.

[8] YU Zhiwen, WONG Hausan. A Rule Based Technique for Extraction of Visual Attention Regions Based on Real-Time Clustering [J]. IEEE Transaction on Multimedia(S1520-9210), 2007, 9(4): 766-784.

[9] GU Xiaodong, CHEN Zhibo, CHEN Quqing. Refinement of Extracted Visual Attention Areas in Video Sequences [C]//ICASSP, 2010: 966-969.

[10] Wen-Fu Lee, Tai-Hsiang Huang, Su-Ling Yeh, et al. Learning-Based Prediction of Visual Attention for Video Signals [J]. IEEE Transactions on Image Processing(S1057-7149), 2011, 20(11): 3028-3038.

[11] WANG Hui, LIU Gang, DANG Yuanyuan. The Target Quick Searching Strategy Based on Visual Attention [C]//International Conference on Computer Science and Electronics Engineering, 2012: 460-462.

[12] YU Zhiwen, WONG Hausan. A Rule Based Technique for Extraction of Visual Attention Regions Based on Real-Time Clustering [J]. IEEE Transaction on Multimedia(S1520-9210), 2007, 9(4): 766-784.

[13] Guironnet M, Guyader N, Pellerin D, et al. Spatio-temporal attention model for video content analysis [C]// ICIP, 2005, 3: III - 1156-9.

[14] MA Yufei, HUA Xiansheng, LU Lie. A Generic Framework of User Attention Model and Its Application in Video Summarization [J]. IEEE Transaction on Multimedia(S1520-9210), 2005, 7(5): 907-919.

[15] HAN Junwei. Object Segmentation from Consumer Video: A Unified Framework Based on Visual Attention [J]. IEEE Transactions on Consumer Electronics(S0098-3063), 2009, 55(3): 1597-1605.

[16] CAO Wei, HOU Hui, TONG Jiarong, et al. A High-performance Reconfigurable VLSI Architecture for VBSME in H.264 [J]. IEEE Transactions on Consumer Electronics(S0098-3063), 2008, 54(3): 1338-1345.

[17] Injong Rhee, Graham R Martin, Packwood Muthukrishnan S. Quadtree-Structured Variable-Size Block-Matching Motion Estimation with Minimal Error [J]. IEEE Transactions Circuits Systems Video Technology(S1051-8215), 2000, 10(2): 42-50.

刘龙, 赵晶, 樊波阳. 一种新的视觉运动注意力计算方法[J]. 光电工程, 2014, 41(3): 12. LIU Long, ZHAO Jing, FAN Boyang. A New Computational Method of Visual Motion Attention[J]. Opto-Electronic Engineering, 2014, 41(3): 12.

一种新的视觉运动注意力计算方法

关于本站 Cookie 的使用提示

全站搜索

一种新的视觉运动注意力计算方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索