An analog CNN algorithm is proposed for detection of moving objects in high-resolution gray-scale images, with multiple moving objects and with moderate a priori information on the scene. The algorithm is based on simple 3×3 templates followed by a clustering operation on the moving pixels. The effectiveness of the proposed algorithm is shown using some real-life indoor and outdoor images.
Costantini, G., Casali, D., Carota, M. (2005). Moving Objects Detection based on CNNs and Clustering. ??????? it.cilea.surplus.oa.citation.tipologie.CitationProceedings.prensentedAt ??????? 9th WSEAS International Conference on CIRCUITS (ICC 2005).
Moving Objects Detection based on CNNs and Clustering
COSTANTINI, GIOVANNI;
2005-01-01
Abstract
An analog CNN algorithm is proposed for detection of moving objects in high-resolution gray-scale images, with multiple moving objects and with moderate a priori information on the scene. The algorithm is based on simple 3×3 templates followed by a clustering operation on the moving pixels. The effectiveness of the proposed algorithm is shown using some real-life indoor and outdoor images.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
