A Neuro-Immune Inspired Robust Real Time Visual Tracking System
We present a novel Neuro-Immune inspired real-time tracking system that is capable of tracking morphing moving targets over non-benign backgrounds. We have employed ideas from antigen-presenting cells, T-cell interaction, together with cytokine interaction with neural systems. Our experiments show that the neuro-immune tracking system has the ability to maintain tracking a target even if the target changes shape, or is covered for periods of time by other objects.
KeywordsNeuro-Immune inspired Visual tracking Morphing target Non-benign background Cellular Immune Network (CIN)
Unable to display preview. Download preview PDF.
- 1.Strom, J., Jebara, T., Basu, S., Pentland, A.: Real time tracking and modeling of faces: An ekf-based analysis by synthesis approach, Corfu, Greece (1999)Google Scholar
- 2.Jain, R.C., Kasturi, R., Schunck, B.G.: Machine Vision. McGraw-Hill, New York (1995)Google Scholar
- 6.Murguia, M.I.C.: Texture segmentation by the 64x64 cnn chip. In: 7th Int. WS on Cellular Neural Networks and their Application: Nonlinear Information Processing and Intelligent Sensors, pp. 547–554 (2002)Google Scholar
- 7.Murguia, M.I.C., Zimmerman, A.S., Pablo Rivas, P.: Image processing applications with a pcnn. Advances in Neural Networks, 884–893 (2007)Google Scholar
- 8.de Castro, L.N., Timmis, J.: Artificial Immune systems: A new Computation Intelligence Approach. Springer, Heidelberg (2002)Google Scholar
- 9.Timmis, J., Neal, M.: Artificial homeostasis: Integrating biologically inspired computing. Technical Report UWA-DCS-03-043, University of Wales, Aberystwyth (February 2003)Google Scholar
- 11.Wan, E.A., Nelson, A.T.: Neural dual extended kalman filtering: Applications in speech enhancement and monaural blind signal separation. In: IEEE Workshop on Neural Networks for Signal Processing, pp. 466–475 (1997)Google Scholar