Recognition and localization of relevant human behavior in videos
conference paper
Ground surveillance is normally performed by human assets, since it requires visual intelligence. However, especially for military operations, this can be dangerous and is very resource intensive. Therefore, unmanned autonomous visual-intelligence systems are desired. In this paper, we present an improved system that can recognize actions of a human and interactions between multiple humans. Central to the new system is our agent-based architecture. The system is trained on thousands of videos and evaluated on realistic persistent surveillance data in the DARPA Mind’s Eye program, with hours of videos of challenging scenes. The results show that our system is able to track the people, detect and localize events, and discriminate between different behaviors, and it performs 3.4 times better than our previous system.
TNO Identifier
471229
Publisher
SPIE
Article nr.
871110
Source title
Sensors, and Command, Control, Communications, and Intelligence (C3I) Technologies for Homeland Security and Homeland Defense XII, 29 april 2013, Batimore, MD, USA
Place of publication
Bellingham, WA