期刊文献+

基于视觉注意模型的自适应视频关键帧提取 被引量:17

Adaptive Key-frames Extraction Based on Visual Attention Model
下载PDF
导出
摘要 关键帧提取是基于内容视频检索领域中一个重要的研究课题。提出了一种基于视觉注意模型的自适应视频关键帧提取方法。该方法分别提取视频中的运动和空间显著度,并用一种运动优先非线性混合模式将显著度合成为视觉注意度。在此基础上提出一种基于视觉注意度的局部和整体两级关键帧提取策略,先采用局部策略,选择镜头内注意度最大的帧作为关键帧候选;再根据视觉注意度的变化,为各个镜头自适应分配关键帧数目作为整体关键帧分配策略。实验证明,该方法提取的关键帧较为符合人类的视觉系统特性,而且该方法具有根据内容变化自适应提取关键帧等特点。 In this paper, we propose a novel video key-frame extraction method based on visual attention model. Firstly, the spatiotemporal saliency levels are generated and fused in a motion priority fashion to produce the overall attention degree. Then, a new adaptive key-frame extraction algorithm using attention and the variation of attention is put forward. For the shot level, the frames with higher attention value are selected as the candidates of the key-frames. For the clip level, the key-frame number is generated by the attention variation in a shot. Experimental results indicate the proposed method performs well in key-frame extraction with high efficiency.
作者 蒋鹏 秦小麟
出处 《中国图象图形学报》 CSCD 北大核心 2009年第8期1650-1655,共6页 Journal of Image and Graphics
基金 国家自然科学基金项目(60673127)
关键词 关键帧 视觉注意模型 自适应 key-frame, visual attention model, adaptive
  • 相关文献

参考文献6

  • 1Liu Li-jie, Fan Guo-liang. Combined key-frame extraction and object-based video segmentation[ J]. IEEE Transactions on Circuits and Systems for Video Technology, 2005 ,IS(7) :869-884. 被引量:1
  • 2Itti L, Koch C. Feature combination strategies for saliency-based visual attention systems [ J ]. Journal of Electronic Imaging, 2001, 10(1) :161-169. 被引量:1
  • 3张鹏,王润生.基于视点转移和视区追踪的图像显著区域检测[J].软件学报,2004,15(6):891-898. 被引量:53
  • 4Ansgar R. Koene,Li Zhao-ping. Feature-specific interactions in salience from combined feature contrasts: Evidence for a bottom-up saliency map in V1 [J]. Journal of Vision,2007,7(7) : 1-14. 被引量:1
  • 5Ma YF, Hua X S. A generic framework of user attention model and its application in video summarization [J]. IEEE Transactions on Multimedia,2005,10(7 ) :907-919. 被引量:1
  • 6Yun Zhai, Mubarak Shah. Visual attention detection in video sequences using spatiotemporal cues[ A]. In:Proceedings of 14th Annual ACM International Conference on Multimedia [ C ], Santa Barbara, CA, USA, 2006 : 815 - 824. 被引量:1

二级参考文献13

  • 1Bourque E, Dudek G, Ciaravola P. Robotic sightseeing: A method for automatically creating virtual environments. In: Giralt G, ed.Proc. of the IEEE Conf. on Robotics and Automation. Leuven: IEEE Press, 1998. 3186~3191. 被引量:1
  • 2Kadir T, Brady M. Saliency, scale and image description. International Journal of Computer Vision, 2001,45(2):83-105. 被引量:1
  • 3Gesu VD, Valenti C, Strinati L. Local operators to detect regions of interest. Pattern Recognition Letters, 1997,18(11-13):1077-1081. 被引量:1
  • 4Wai WYK, Tsotsos JK. Directing attention to onset and offset of image events for eye-head movement control. In: Huang T, ed.Proc. of the Int'l Association for Pattern Recognition Workshop on Visual Behaviors. Seattle: IEEE Press, 1994. 79~84. 被引量:1
  • 5Stentiford FWM. An evolutionary programming approach to the simulation of visual attention. In: Kim JH, ed. Proc. of the IEEE Congress on Evolutionary Computation. Seoul: IEEE Press, 2001. 851-858. 被引量:1
  • 6Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998,20(11):1254-1259. 被引量:1
  • 7Itti L, Koch C. Computational modeling of visual attention. Nature Reviews Neuroscience, 2001,2(3):194-230. 被引量:1
  • 8Itti L, Koch C. Feature combination strategies for saliency-based visual attention systems. Journal of Electronic Imaging,2001,10(1):161-169. 被引量:1
  • 9Yee H, Pattanaik SN, Greenberg DP. Spatiotemporal sensitivity and visual attention for efficient rendering of dynamic environments. ACM Trans. on Computer Graphics, 2001,20(1):39-65. 被引量:1
  • 10Boccignone G, Ferraro M, Caelli T. Generalized spatio-chromatic diffusion. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2002,24(10): 1298-1309. 被引量:1

共引文献52

同被引文献238

引证文献17

二级引证文献56

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