Algorithmes de Reconnaissance Non Coopérative de Cibles et implémentation sur GPU
Résumé
In this paper, first, we present the problem of Non Cooperative Target Recognition (NCTR) as a supervised classification problem. Then, we use a very simple method of K Nearest Neighbors (KNN) to do this classification. We explore and compare the performances of this algorithm based on the choice of the distances and the representation spaces of the data. KNN algorithm will be executed initially on CPU with Matlab and then on GPU using MEX functions of Matlab. Time computing and memory transfert time will be taken into account to evaluate the benefit of such an implementation.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...