%0 Conference Proceedings
%T Fast and robust optimization approaches for pedestrian detection
%D 2015
%A Melo, Victor Hugo Cunha de,
%A Menotti, David,
%A Schwartz, William Robson,
%@affiliation Universidade Federal de Minas Gerais
%@affiliation Universidade Federal de Ouro Preto
%@affiliation Universidade Federal de Minas Gerais
%E Segundo, Maurício Pamplona,
%E Faria, Fabio Augusto,
%B Conference on Graphics, Patterns and Images, 28 (SIBGRAPI)
%C Salvador
%8 Aug. 26-29, 2015
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Pedestrian detection, random filtering, location regression, cascade of rejection, partial least squares.
%X The large number of surveillance cameras available nowadays in strategic points of large cities aims to provide a safe environment. However, the huge amount of visual data provided by the cameras prevents its manual processing, requiring the application of automated methods. Among such methods, pedestrian detection plays an important role in reducing the amount of data. However, the currently available methods are unable to process such large amount of data in real time. Therefore, there is a need for the development of optimization techniques. Towards accomplishing the goal of reducing costs for pedestrian detection, this Masters thesis proposed two optimization approaches. Our first approach proposes a novel optimization that performs a random filtering in the image to select a small number of detection windows, allowing a reduction in the computational cost. Our results show that accurate results can be achieved even when a large number of detection windows are discarded. The second approach consists of a cascade of rejection based on Partial Least Squares (PLS) combined with the propagation of latent variables through the stages. Our results show that the method reduces the computational cost by increasing the number of rejected background samples in earlier stages of the cascade.
%@language en
%3 2015-WTD-VictorMelo.submitted.pdf