Motion Detection Using Cellular Neural Network
Cellular Neural Networks have been recently used for motion detection. Their main advantage lies in the comparative nature of each processor within its local neighborhood. The function of each processor is dependent on the choice of the control and feedback templates. In this paper a new set of templates is introduced. These templates allow the CNN processor to detect object motion in any direction, as well as estimating the motion distance. Experimental results are also introduced to test and verity the accuracy of these templates.
KeywordsMotion Detection Cellular Neural Network Black Pixel Shadow Detector Detect Object Motion
Unable to display preview. Download preview PDF.
- L. O. Chua and T. Roska, „The CNN Paradigm“, IEEE Transactions on Circuits and Systems-I, vol.CAS-40, pp. 147–156, March 1993.Google Scholar
- Peter Kinget, Michel Steyaert, “A Programmable Cellular Neural Network CMOS Chip for High Speed Image Processing”, IEEE Trans. on Solid State Circuits, Vol. 30, No. 3, pp. 205–243, March 1995.Google Scholar
- Cs. Rekeczky, A. Ushida, and T. Roska, “Rotation Invariant Detection of Moving and Standing Objects Using Analogic Cellular Neural Network Algorithms Based on Ring-Codes”, IEICE Transactions on Fundamentals and Information Sciences, Vol. E78-A, No. 10, pp. 1316–1330, October 1995.Google Scholar