BIS3-3 ; Object tracking is useful in applications like computer-aided medical diagnosis, video editing, visual surveillance etc. Commonly used approaches usually involve the use of filter (e.g. Kalman filter) to predict the location of the object in next image frame. Such approaches actually borrow ideas from signal theory and are limited to applications where dynamic model is known. In this paper, a flexible and reliable estimation algorithm using wavelet network (or wavenet) is proposed to build an object tracking system. This system simulates the perception of motion that occurs in primates. Neural-based filters will be used for color, shape and motion analysis. Experimental results show that object can be tracked accurately without fixing any dynamic model compare with commonly used Kalman filter. ; postprint ; The Brain Inspired Cognitive Systems (BICS 2004), Stirling, Scotland, U.K., 29 August-1 September 2004. In Proceedings of the Brain Inspired Cognitive Systems, 2004, p. 1-7
Neurally inspired object tracking system
2004-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DDC: | 629 |
A Neurally-Based Auto-Lock-On Target-Tracking Sight Controller for Airborne Fire Control System
British Library Online Contents | 1992
|Neurally-augmented immunity-based detection and identification of aircraft sub-system failures
Online Contents | 2014
|British Library Conference Proceedings | 1992
|MANIAC: A Next Generation Neurally Based Autonomous Road Follower
British Library Conference Proceedings | 1993
|ATP as Neurally Released Modulator of Human Airway Ion Transport
British Library Conference Proceedings | 1994
|