Efficient Management of Multiple Agent Tracking through Observation Handling

J. Gonzàlez, D. Rowe, J. Andrade, and J.J. Villanueva (Spain)


Multiple Agent Tracking, Low Level Tracking, Agent De tection.


Non-supervised multiple-agent tracking is a complex task which demands a structured framework in order to accom plish it. Therefore, this proposal presents a system which is modular and hierarchically organised. It consists in sev eral levels, working in cascade, which are defined accord ing to the different functionalities to be performed. The goal of this work is to implement and experimentally ver ify a novel image-based algorithm which deals with serious segmentation difficulties, thereby being able to simultane ously perform a reliable tracking of several agents. As a result, agents’ trajectories are obtained, as well as quantita tive information about their state at any time, such as their speed or size.

Important Links:

Go Back