Video sequence learning and recognition via dynamic SOM

Information contained in video sequences is crucial for an autonomous robot or a computer to learn and respond to its surrounding environment. In the past, robot vision mainly concentrated on still image processing and small "image cube" processing. Continuous video sequence learning and recognition is rarely addressed in the literature due to its high requirement of dynamic processing. In this paper, we propose a novel neural network structure called dynamic self-organizing map (DSOM) for video sequence processing. The proposed technique has been tested on simulation data sets, and the results validate its learning/recognition ability.

[1]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[2]  Christoph von der Malsburg,et al.  Tracking and Learning Graphs on Image Sequences of Faces , 1996, ICANN.

[3]  Christoph von der Malsburg,et al.  Tracking and learning graphs and pose on image sequences of faces , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[4]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[5]  John J. Hopfield,et al.  Neurons, Dynamics and Computation , 1994 .

[6]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[7]  Masafumi Hagiwara,et al.  Theoretical derivation of momentum term in back-propagation , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[8]  Sophocles J. Orfanidis,et al.  Introduction to signal processing , 1995 .

[9]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

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