This document encloses analysis of portions of extraction module as composed by Difference of Gaussian Interest Point Detector (DoG), Scale Invariant Feature Transform (SIFT) and Compressed Histogram of Gradients (ChoG) algorithms. With reference to TMuC, the Keypoint Selection, the Vector Quantization, and the Entropy Encoding were not considered in this analysis. The analysis, altought not fully completed, was mainly focused on the memory requirements and the feasibility of the system.
Memory analysis of Interest Point Detector and Compact Descriptor algorithms
VIGLIAR, MARIO;LICCIARDO, GIAN DOMENICO;Ettore Napoli;
2012-01-01
Abstract
This document encloses analysis of portions of extraction module as composed by Difference of Gaussian Interest Point Detector (DoG), Scale Invariant Feature Transform (SIFT) and Compressed Histogram of Gradients (ChoG) algorithms. With reference to TMuC, the Keypoint Selection, the Vector Quantization, and the Entropy Encoding were not considered in this analysis. The analysis, altought not fully completed, was mainly focused on the memory requirements and the feasibility of the system.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.