Collision prediction via the CNN Universal Machine

V. Gal, T. Roska

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Cellular neural networks (CNN) algorithm was used to estimate the time to an impending collision between an approaching object and the observer. Context insensitive method was used for the calculations. The simulated results show that the accuracy of estimation depends on the size of the array of the CNN cells and sampling rate at which CNN-UN can process the calculation. According to the calculations performed in the laboratory the characteristics of the real 64×64 CNN-UM enable the process between the two frames to be completed in 27 msecs.

Original languageEnglish
Pages105-110
Number of pages6
Publication statusPublished - Dec 11 2000
EventProceedings of the 2000 6th IEEE International Workshop on Cellular Neural Network and their Applications (CNNA 2000) - Catania, Italy
Duration: May 23 2000May 25 2000

Other

OtherProceedings of the 2000 6th IEEE International Workshop on Cellular Neural Network and their Applications (CNNA 2000)
CityCatania, Italy
Period5/23/005/25/00

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'Collision prediction via the CNN Universal Machine'. Together they form a unique fingerprint.

  • Cite this

    Gal, V., & Roska, T. (2000). Collision prediction via the CNN Universal Machine. 105-110. Paper presented at Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Network and their Applications (CNNA 2000), Catania, Italy, .