author = "Nazar{\'e} Jr., Antonio Carlos and Ferreira, Renato Antonio Celso 
                         and Schwartz, William Robson",
          affiliation = "{Universidade Federal de Minas Gerais} and {Universidade Federal 
                         de Minas Gerais} and {Universidade Federal de Minas Gerais}",
                title = "A Scalable and Versatile Framework for Smart Video Surveillance",
            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 = "Smart~Surveillance~Framework, Surveillance Systems, Computer 
                         Vision, Video Analysis, Video Surveillance.",
             abstract = "The large amount of visual data generated by surveillance cameras 
                         is usually analyzed manually, a challenging task which is labor 
                         intensive and prone to errors. Therefore, automatic approaches 
                         must be employed to enable the proper processing of the visual 
                         data. The main goal of automated surveillance systems is to 
                         analyze the scene focusing on the detection and recognition of 
                         suspicious activities. However, these systems are rarely tackled 
                         in a scalable manner. With that in mind, this Masters thesis 
                         proposed a framework for scalable video analysis called Smart 
                         Surveillance Framework (SSF) to allow researchers to implement 
                         their solutions to the surveillance problems as a sequence of 
                         processing modules that communicate through a shared memory. The 
                         framework provides useful features to the researchers, such as 
                         memory management to allow handling large amounts of data, 
                         communication control among execution modules, predefined data 
                         structures specifically designed for the surveillance environment 
                         and management of multiple data input. Our experimental results 
                         evaluate important aspects of the Smart Surveillance Framework 
                         (SSF) and demonstrate the scalability of the framework, the lower 
                         overhead caused by the communication between the modules and the 
                         shared memory and the high performance of our feature extraction 
  conference-location = "Salvador",
      conference-year = "Aug. 26-29, 2015",
             language = "en",
                  ibi = "8JMKD3MGPBW34M/3K2MKA8",
                  url = "",
           targetfile = "article.pdf",
        urlaccessdate = "2021, Dec. 04"