Title :
Collision prediction via the CNN Universal Machine
Author :
Gál, V. ; Roska, T.
Author_Institution :
Comput. & Autom. Inst., Hungarian Acad. of Sci., Budapest, Hungary
Abstract :
We present an analogic CNN algorithm that estimates the time to an impending collision between an approaching object and the observer. Calculation is based on a context insensitive method, which is well known in neurobiology, using only two specific cues of the expanding two-dimensional image of the looming object
Keywords :
analogue processing circuits; cellular neural nets; image processing; neural chips; physiological models; visual perception; CNN Universal Machine; analogic CNN algorithm; collision prediction; context insensitive method; expanding two-dimensional image; Animals; Cellular neural networks; Detectors; Equations; Geometrical optics; Image edge detection; Object detection; Optical arrays; Pixel; Turing machines;
Conference_Titel :
Cellular Neural Networks and Their Applications, 2000. (CNNA 2000). Proceedings of the 2000 6th IEEE International Workshop on
Conference_Location :
Catania
Print_ISBN :
0-7803-6344-2
DOI :
10.1109/CNNA.2000.876829
