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.
Similar content being viewed by others
References
Akutsu A, Tonomura Y, Hashimoto H, Ohba Y (1992) Video indexing using motion vectors. In: Proc SPIE (Visual Commun Image Process) 1818:1522-1530
Astola J, Haavisto P, Neuvo Y (1990) Vector median filters. Proc IEEE 78(4):678-689
Bouthemy P, Gelgon M, Ganansia F (1999) A unified approach to shot change detection and camera motion characterization. IEEE Trans Circuits Sys Video Technol 9(7):1030-1044
Cao X, Suganthan PN (2001) Video sequence boundary detection using neural gas networks. In: Proceedings of ICANN, Vienna, Austria, Lecture notes in computer science, vol 2130. Springer, Berlin Heidelberg New York, pp 1048-1053
Ford RM, Robson C, Temple D, Gerlach M (2000) Metrics for shot boundary detection in digital video sequences. ACM Multimedia Sys 8(1):37-46
Fritzke B (1994) Growing cell structures: a self-organizing network for unsupervised and supervised learning. Neural Netw 7(9):1441-1460
Fritzke B (1995) A growing neural gas network learns topologies. In: Tesauro G, Touretzky DS, Keen TK (eds) Advances in neural information processing systems, MIT Press, Cambridge, MA, pp 625-632
Fritzke B (1996) Automatic construction of radial basis function networks with the growing neural gas model and its relevance for fuzzy logic. In: Proceedings of the 1996 ACM symposium on applied computing, Philadelphia, PA, 17-19 February 1996, pp 624-627
Kohonen T (1997) Self-organizing maps, 2nd edn. Springer, Berlin Heidelberg New York
Koprinska I, Carrato S (2002) Hybrid rule-based/neural approach for segmentation of MPEG compressed video. Multimedia Tools Applicat 18(3):187-212
Lee M-S, Yang Y-M, Lee S-W (2001) Automatic video parsing using shot boundary detection and camera operation analysis. Pattern Recog 34:711-719
Maeda J (1994) Method for extracting camera operations to describe sub-scenes in video sequences. In: Pproceedings of IS&T/SPIE conference on digital video compression on personal computers: algorithm and technologies, San Jose, 2187:56-67
Mann S, Picard RW (1995) Video orbits: characterizing the coordinate transformation between two images using the projective group. Technical report 278, MIT Media Lab, Perceptual Computing, Cambridge, MA
Martinetz TM (1993) Competitive hebbian learning rule forms perfectly topology preserving maps. In: Proceedings of ICANN’93 - international conference artificial neural networks, Amsterdam, 13-16 September 1993, pp 427-434
Martinetz TM, Berkovich SG, Schulten KJ (1993) “Neural-gas” network for vector quantization and its application to time-series prediction. IEEE Trans Neural Netw 4(4):558-569
Milanese R, Deguillaume F, Jacot-Descombes A (1999) Efficient segmentation and camera motion indexing of compressed video. Real-Time Imag 5(4):231-241
Patel NV, Sethi IK (1997) Video shot detection and characterization for video databases. Pattern Recog (Special Issue on Multimedia) 30(4):583-592
Rui Y, Huang TS (1999) Constructing table-of-content for videos. ACM Multimedia Sys 7(5):359-368
Shanableh T, Ghanbari M (2000) Heterogeneous video transcoding to lower spatio-temporal resolutions and different encoding formats. IEEE Trans Multimedia 2(2):101-110
Suganthan PN (1999) Hierarchical overlapped SOM’s for pattern classification. IEEE Trans Neural Netw 10(1):193-196
Suganthan PN (2001) Pattern classification using multiple hierarchical overlapped self-organising maps. Pattern Recog 34(11):2173-2179
Wang R, Huang T (1999) Fast camera motion analysis in MPEG domain. In: Proceedings of the international conference on image processing, Kobe, Japan, 24-28 October 1999, 3:691-694
Xiong W, Lee J C-M (1998) Efficient scene change detection and camera motion annotation for video classification. Comput Vis Image Understand 71(2):166-181
Zhang HJ, Kankanhalli A, Smoliar SW (1993) Automatic partitioning of full-motion video. ACM Multimedia Sys 1(1):10-28
Zhang HJ, Low CY, Smolliar SW (1995) Video parsing and browsing using compressed data. Multimedia Tools Applicat 1:89-111
Author information
Authors and Affiliations
Corresponding author
Additional information
P.N. Suganthan: Correspondence to
Rights and permissions
About this article
Cite this article
Cao, X., Suganthan, P.N. Video shot motion characterization based on hierarchical overlapped growing neural gas networks. Multimedia Systems 9, 378–385 (2003). https://doi.org/10.1007/s00530-003-0107-2
Issue Date:
DOI: https://doi.org/10.1007/s00530-003-0107-2