%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2016/09.12.15.44
%2 sid.inpe.br/sibgrapi/2016/09.12.15.44.56
%T Um Estudo sobre Redes Neurais Convolucionais e sua Aplicação em Detecção de Pedestres
%D 2016
%A Vargas, Ana Caroline Gomes,
%A Paes, Aline,
%A Vasconcelos, Cristina Nader,
%@affiliation UFF
%@affiliation UFF
%@affiliation UFF
%E Aliaga, Daniel G.,
%E Davis, Larry S.,
%E Farias, Ricardo C.,
%E Fernandes, Leandro A. F.,
%E Gibson, Stuart J.,
%E Giraldi, Gilson A.,
%E Gois, João Paulo,
%E Maciel, Anderson,
%E Menotti, David,
%E Miranda, Paulo A. V.,
%E Musse, Soraia,
%E Namikawa, Laercio,
%E Pamplona, Mauricio,
%E Papa, João Paulo,
%E Santos, Jefersson dos,
%E Schwartz, William Robson,
%E Thomaz, Carlos E.,
%B Conference on Graphics, Patterns and Images, 29 (SIBGRAPI)
%C São José dos Campos, SP, Brazil
%8 4-7 Oct. 2016
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Pedestrian Detection, Computer Vision, Machine Learning, CNN, SVM, HOG, Adaboost, Haar features.
%X This work addresses Deep Learning from the point of view of the Computer Vision area, drawing a parallel between the two areas, considering the pedestrian detection task. To achieve that, the experimental results of two classical Computer Vision approaches are compared to the results obtained from a Convolutional Neural Network, which is known for obtaining the state of the art to the problem of pedestrian detection.
%@language pt
%3 um-estudo-sobre.pdf