Premium
Analogic CNN algorithm for estimating position and size of moving objects
Author(s) -
Costantini Giovanni,
Casali Daniele,
Perfetti Renzo
Publication year - 2004
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/cta.293
Subject(s) - computer science , computer vision , artificial intelligence , position (finance) , algorithm , simple (philosophy) , selection (genetic algorithm) , template , scale (ratio) , separation (statistics) , computer graphics (images) , pattern recognition (psychology) , machine learning , programming language , philosophy , physics , finance , epistemology , quantum mechanics , economics
An analogic CNN algorithm is proposed for detection of multiple moving objects in high resolution, grey‐scale images taken from a fixed camera. The algorithm, based on simple 3 × 3 templates, can be implemented using CNN hardware, providing the real‐time operation required in surveillance and traffic control applications. Efficient separation of moving objects from the background is obtained through automatic threshold selection. The performance of the proposed method is shown using real‐life indoor and outdoor video sequences. Copyright © 2004 John Wiley & Sons, Ltd.