2013 - 2015
Public selection of scientific, technological and innovation research projects, aimed at the development of Sport in its different dimensions). Due to the large number of people present in sports facilities that host competitions with large audiences, such as stadiums or gymnasiums, there are several problems that are difficult to deal with efficiently when the entire analysis process is carried out manually, such as the detection of conflicts occurring in the stands and the identification and location of the individuals involved or the delimitation of regions of the stands or group of individuals who must be monitored with greater attention due to their improper behavior. In order to assist in the monitoring and, consequently, the safety of fans present at sports competitions, this project aims to employ computer vision techniques to automate the resolution of the above problems in order to provide relevant information to those responsible for monitoring fans in sports facilities with the aim of increasing precision and efficiency in decision making. In this way, security agents will only receive video segments containing situations classified as of interest from the point of view of environmental monitoring and surveillance, which may require some type of human intervention. In order to obtain the necessary information for the satisfactory execution of the monitoring system, the project will focus on obtaining robust solutions through the use of accurate visual characteristic descriptors in order to reduce the propagation of errors in detection, recognition problems and re-identification of people and recognition of their actions, as well as the development of efficient methodologies that will enable the processing of large amounts of visual data.