A real time algorithm for people tracking using contextual reasoning |
| |
| Authors: | Rosario Di Lascio Pasquale Foggia Gennaro Percannella Alessia Saggese Mario Vento |
| |
| Affiliation: | 1. A.I.Tech s.r.l., A Spin-off Company of the University of Salerno, Italy;2. Department of Information Engineering, Electrical Engineering and Applied Mathematics, University of Salerno, Italy;1. Department of Electrical and Computer Engineering, UAB, Birmingham, AL 35294, USA;2. Harper Laboratories, LLC, Atlanta, GA 30318, USA;1. School of Computer Science and Technology, Tianjin University, Tianjin, China;2. School of Computer Science, Carnegie Mellon University, United States;3. Department of Information Engineering and Computer Science, University of Trento, Italy;4. Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin 300072, China;5. State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;1. Institut Mines-Telecom, Telecom ParisTech – CNRS LTCI – Paris, France;2. CMLA, ENS Cachan, CNRS, PRES UniverSud, France |
| |
| Abstract: | In this paper we present a real-time tracking algorithm that is able to deal with complex occlusions involving a plurality of moving objects simultaneously. The rationale is grounded on a suitable representation and exploitation of the recent history of each single moving object being tracked. The object history is encoded using a state, and the transitions among the states are described through a Finite State Automata (FSA). In presence of complex situations the tracking is properly solved by making the FSA’s of the involved objects interact with each other. This is the way for basing the tracking decisions not only on the information present in the current frame, but also on conditions that have been observed more stably over a longer time span. The object history can be used to reliably discern the occurrence of the most common problems affecting object detection, making this method particularly robust in complex scenarios. An experimental evaluation of the proposed approach has been made on two publicly available datasets, the ISSIA Soccer Dataset and the PETS 2010 database. |
| |
| Keywords: | Video surveillance Real-time object tracking Finite State Automata |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
