@InProceedings{MeloMenoSchw:2015:FaRoOp,
               author = "Melo, Victor Hugo Cunha de and Menotti, David and Schwartz, 
                         William Robson",
          affiliation = "{Universidade Federal de Minas Gerais} and {Universidade Federal 
                         de Ouro Preto} and {Universidade Federal de Minas Gerais}",
                title = "Fast and robust optimization approaches for pedestrian detection",
            booktitle = "Proceedings...",
                 year = "2015",
               editor = "Segundo, Maur{\'{\i}}cio Pamplona and Faria, Fabio Augusto",
         organization = "Conference on Graphics, Patterns and Images, 28. (SIBGRAPI)",
            publisher = "Sociedade Brasileira de Computa{\c{c}}{\~a}o",
              address = "Porto Alegre",
             keywords = "Pedestrian detection, random filtering, location regression, 
                         cascade of rejection, partial least squares.",
             abstract = "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.",
  conference-location = "Salvador, BA, Brazil",
      conference-year = "26-29 Aug. 2015",
             language = "en",
                  ibi = "8JMKD3MGPBW34M/3K2N5CH",
                  url = "http://urlib.net/ibi/8JMKD3MGPBW34M/3K2N5CH",
           targetfile = "2015-WTD-VictorMelo.submitted.pdf",
        urlaccessdate = "2024, May 05"
}