Advertisement

Two Important Action Scenes Detection Based on Probability Neural Networks

  • Yu-Liang Geng
  • De Xu
  • Jia-Zheng Yuan
  • Song-He Feng
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3972)

Abstract

In this paper, an effective classification approach for action scenes is proposed, which exploits the film grammar used by filmmakers as guideline to extract features, detect and classify action scenes. First, action scenes are detected by analyzing film rhythm of video sequence. Then four important features are extracted to characterize chase and fight scenes. After then the Probability Neural Networks is employed to classify the detected action scenes into fight, chase and uncertain scenes. Experimental results show that the proposed method works well over the real movie videos.

Keywords

Probability Neural Network Salient Region Action Scene Audio Event Semantic Scene 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Lee, S.H., Yeh, C.H., Kuo, C.C.J.: Video Skimming Based on Story Units via General Tempo Analysis. In: Proc. of IEEE ICME, vol. 2, pp. 1099–1102 (2004)Google Scholar
  2. Ma, Y.F., Lu, L., Zhang, H.J., Li, M.J.: A User Attention Model for Video Summarization. In: Proc. of ACM Multimedia, pp. 533–542 (2002)Google Scholar
  3. Li, Y., Narayanan, S., JayKuo, C.C.: Content-Based Movie Analysis and Indexing Based on AudioVisual Cues. IEEE Trans. on Circuits and Systems for Video Technology 14(8), 1073–1085 (2004)CrossRefGoogle Scholar
  4. Chu, W.T., Cheng, W.H., Wu, J.L.: Generative and Discriminative Modeling toward Semantic Context Detection in Audio Tracks. In: Proc. of the 11th International Multimedia Modelling Conference, pp. 38–45 (2005)Google Scholar
  5. Arijon, D.: Grammar of The Film Language. Silman-James Press, Los Angeles (1991)Google Scholar
  6. Geng, Y.L., Xu, D., Wu, A.M.: Effective Video Scene Detection Approach Based on Cinematic Rules. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds.) KES 2005. LNCS (LNAI), vol. 3682, pp. 1197–1203. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. Geng, Y.L., Xu, D.: Efficient Key Frames Extraction Based on Hierarchical Clustering. In: Proc. of IEEE TENCON, vol. B, pp. 77–80 (2004)Google Scholar
  8. Hu, Y.Q., Xie, X., et al.: Salient Region Detection Using Weighted Feature Maps Based on Human Visual Attention Model. In: Proc. of IEEE PCM, pp. 993–1000 (2004)Google Scholar
  9. Specht, D.: Probabilitic Neual Networks. Neual Networks 3(1), 109–118 (1990)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yu-Liang Geng
    • 1
    • 2
  • De Xu
    • 1
  • Jia-Zheng Yuan
    • 1
  • Song-He Feng
    • 1
    • 2
  1. 1.Institute of Computer Science and TechnologyBeijing Jiaotong UniversityBeijingChina
  2. 2.Beijing Key Lab of Intelligent Telecommunications Software MultimediaBeijing University of Posts and CommunicationsBeijingChina

Personalised recommendations