计算机科学 ›› 2015, Vol. 42 ›› Issue (11): 118-122.doi: 10.11896/j.issn.1002-137X.2015.11.025

• 第十四届中国多值逻辑与模糊逻辑学术会议 • 上一篇    下一篇

基于视觉运动特性的视频时空显著性区域提取方法

周莺,张基宏,梁永生,柳 伟   

  1. 深圳大学信息工程学院 深圳518060;深圳信息职业技术学院可视媒体处理与传输深圳市重点实验室 深圳518172,深圳大学信息工程学院 深圳518060,深圳信息职业技术学院可视媒体处理与传输深圳市重点实验室 深圳518172,深圳信息职业技术学院可视媒体处理与传输深圳市重点实验室 深圳518172
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然科学基金项目(61172165),广东省自然科学基金项目(S2011010006113)资助

Motion Characteristics Based Video Salient Region Extraction Method

ZHOU Ying, ZHANG Ji-hong, LIANG Yong-sheng and LIU Wei   

  • Online:2018-11-14 Published:2018-11-14

摘要: 为了更准确有效地提取人眼观察视频的显著性区域,提出一种基于视觉运动特性的视频时空显著性区域提取方法。该方法首先通过分析视频每帧的频域对数谱得到空域显著图,利用全局运动估计和块匹配得到时域显著图,再结合人眼观察视频时的视觉特性,根据对不同运动特性视频的主观感知,动态融合时空显著图。实验分析从主客观两个方面衡量。视觉观测和量化指标均表明, 与其他经典方法相比,所提方法提取的显著性区域能够更准确地反映人眼的视觉注视区域。

关键词: 显著性区域,视觉注意模型,时域显著度,空域显著度,运动特性

Abstract: The human eyes only observe the salient region of the video.Thus a motion characteristics based salient region extraction method was proposed.Spatial saliency map is extracted by analyzing the log spectrum of each frame in the frequency domain.Temporal saliency map is obtained by global motion estimation and block matching.According to the human visual characteristics and the subjective perception of different motion characteristics,the region of saliency is fused dynamically by spatial and temporal saliency map.The experiment was analyzed from both subjective and objective indicators.Visual observation and quantitative indicators show that the proposed method can reflect the human visual attention area more accurately than other classical extraction methods.

Key words: Region of saliency,Visual attention model,Temporal saliency,Spatial saliency,Motion characteristics

[1] 张菁,卓力,李晓光.新一代高效视频编码技术[M].北京:人民邮电出版社,2013Zhang Jing,Zhuo Li,Li Xiao-guang.High efficiency Video Co-ding Techniques for Next Generation[M].Beijing:Posts & Telecom Press,2013
[2] 王岩.视觉注意模型的研究与应用[D].上海:上海交通大学,2012Wang Yan.Reaserch and Application of Visual Attention Model[D].Shanghai:Jiaotong University,2012
[3] Koch C,Itti L,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
[4] Koch C,Harel J,Perona P.Graph-Based Visual Saliency[M]∥Advances in Neural Information Processing Systems.2007:681-688
[5] Walther D,Koch C.Modeling Attention to Salient Proto-objcets[J].Neural Networks,2006,19(9):1395-1407
[6] Bamidele A,Stentiford F W M.An attention based similarity measure used to identify image clusters.http://www.doc88.com/P-9592796942640.html
[7] Hou X,Harel J,Koch C.Image Signature:Highlighting Sparse Salient Regions[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(1):194-201
[8] 刘晓辉,金志刚,赵安安,等.融合运动和空间关系特性的显著性区域检测[J].华中科技大学学报,2013,41(6):45-49 Liu Xiao-hui,Jin Zhi-gang,Zhao An-an,et al.Salient region detection of interfusing motion and spatial relationships[J].Journal of Huazhong University of Science and Technology,2013,1(6):45-49
[9] Luo Y,Tian Q.Spatio-temporal enhanced sparse feature selection for video saliency estimation[C]∥2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops(CVPRW).2012:33-38
[10] Fang Y,Lin W,Chen Z,et al.A Video Saliency Detection Model in Compressed Domain[J].IEEE Transactions on Circuits and Systems for Video Technology,2014,24(1):27-38
[11] Hou X,Zhang L.Saliency Detection:A Spectral Residual Approach[M].MinneaPolis,MN,USA,2007
[12] 周莺,柳伟,张基宏.基于内容感知的可分级视频码流排序方法[J].信号处理,2013,29(8):1012-1018 Zhou Ying,Liu Wei,Zhang Ji-hong.Conetent aware based sorting approach of scalable video bitstream[J].Journal of Signal Processing,2013,9(8):1012-1018
[13] Gopalakrishnan V,Hu Yi-qun,Rajan D.Salient region detection by modeling distributions of color and orientation[J].IEEE transactions on multimedia,2011,2(5):892-905

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!