A proposal for local and global human activities identification
Castillo Montoya, José Carlos
Fernández Caballero, Antonio
Rodríguez Sánchez, José María
MetadataShow full item record
There are a number of solutions to automate the monotonous task of looking at a monitor to find suspicious behaviors in video surveillance scenarios. Detecting strange objects and intruders, or tracking people and objects, is essential for surveillance and safety in crowded environments. The present work deals with the idea of jointly modeling simple and complex behaviors to report local and global human activities in natural scenes. In order to validate our proposal we have performed some tests with some CAVIAR test cases. In this paper we show some relevant results for some study cases related to visual surveillance, namely ?speed detection?, ?position and direction analysis?, and ?possible cashpoint holdup detection?.