Video shot motion characterization based on hierarchical overlapped growing neural gas networks

Abstract.Automatic video shot motion characterization is an important step in video indexing and retrieval after temporal video segmentation. This paper describes a hierarchical overlapped architecture (HOGNG) based upon the growing neural gas (GNG) network [7] to perform this task. The proposed architecture combines the unsupervised and supervised learning schemes in GNG. As higher-level GNGs overlap, the final classification is obtained by fusing the individual classifications generated by the top-level overlapping GNGs. In addition, we employ prefiltering and postfiltering for improving the classification accuracy. Experimental results are presented to show the good classification accuracy of the proposed algorithm on real MPEG video sequences.

[1]  Ponnuthurai N. Suganthan.  Hierarchical overlapped SOM's for pattern classification , 1999, IEEE Trans. Neural Networks.

[2]  Thomas S. Huang,et al.  Fast camera motion analysis in MPEG domain , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[3]  Irena Koprinska,et al.  Hybrid Rule-Based/Neural Approach for Segmentation of MPEG Compressed Video , 2002, Multimedia Tools and Applications.

[4]  Atreyi Kankanhalli,et al.  Automatic partitioning of full-motion video , 1993, Multimedia Systems.

[5]  Wei Xiong,et al.  Efficient Scene Change Detection and Camera Motion Annotation for Video Classification , 1998, Comput. Vis. Image Underst..

[6]  Alain Jacot-Descombes,et al.  Efficient Segmentation and Camera Motion Indexing of Compressed Video , 1999, Real Time Imaging.

[7]  Seong-Whan Lee,et al.  Automatic video parsing using shot boundary detection and camera operation analysis , 2001, Pattern Recognit..

[8]  Nilesh V. Patel,et al.  Video shot detection and characterization for video databases , 1997, Pattern Recognit..

[9]  Ponnuthurai N. Suganthan.  Pattern classification using multiple hierarchical overlapped self-organising maps , 2001, Pattern Recognit..

[10]  Junji Maeda.  Method for extracting camera operations in order to describe subscenes in video sequences , 1994, Electronic Imaging.

[11]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[12]  Mohammed Ghanbari,et al.  Heterogeneous Video Transcoding to Lower Spatio-Temporal Resolutions and Different Encoding Formats , 2000, IEEE Trans. Multim..

[13]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[14]  Hideo Hashimoto,et al.  Video indexing using motion vectors , 1992, Other Conferences.

[15]  Xiang Cao,et al.  Video Sequence Boundary Detection Using Neural Gas Networks , 2001, ICANN.

[16]  Thomas S. Huang,et al.  Constructing table-of-content for videos , 1999, Multimedia Systems.

[17]  Rosalind W. Picard,et al.  Orbits': Characterizing the Coordinate Transformation between Two Images Using the Projective Group , 1995 .

[18]  J. Astola,et al.  Vector median filters , 1990, Proc. IEEE.

[19]  Ralph M. Ford,et al.  Metrics for shot boundary detection in digital video sequences , 2000, Multimedia Systems.

[20]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[21]  B Fritzke,et al.  A growing neural gas network learns topologies. G. Tesauro, DS Touretzky, and TK Leen, editors , 1995, NIPS 1995.

[22]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[23]  Bernd Fritzke.  Automatic construction of radial basis function networks with the growing neural gas model and its relevance for fuzzy logic , 1996, SAC '96.

[24]  Stephen W. Smoliar,et al.  Video parsing and browsing using compressed data , 1995, Multimedia Tools and Applications.

[25]  Teuvo Kohonen,et al.  Self-Organizing Maps, Second Edition , 1997, Springer Series in Information Sciences.

[26]  T. Martínez,et al.  Competitive Hebbian Learning Rule Forms Perfectly Topology Preserving Maps , 1993 .

[27]  Patrick Bouthemy,et al.  A unified approach to shot change detection and camera motion characterization , 1999, IEEE Trans. Circuits Syst. Video Technol..