Track classification within wireless sensor network
Autor: | Jean Dezert, Robin Doumerc, Julien Moras, Loic Canevet, Benjamin Pannetier |
---|---|
Rok vydání: | 2017 |
Předmět: |
020301 aerospace & aeronautics
business.industry Computer science Real-time computing 02 engineering and technology Fuzzy logic 0203 mechanical engineering 0202 electrical engineering electronic engineering information engineering Wireless 020201 artificial intelligence & image processing Computer vision Artificial intelligence business Wireless sensor network Classifier (UML) |
Zdroj: | SPIE Proceedings. |
ISSN: | 0277-786X |
DOI: | 10.1117/12.2267990 |
Popis: | In this paper, we present our study on track classification by taking into account environmental information and target estimated states. The tracker uses several motion model adapted to different target dynamics (pedestrian, ground vehicle and SUAV, i.e. small unmanned aerial vehicle) and works in centralized architecture. The main idea is to explore both: classification given by heterogeneous sensors and classification obtained with our fusion module. The fusion module, presented in his paper, provides a class on each track according to track location, velocity and associated uncertainty. To model the likelihood on each class, a fuzzy approach is used considering constraints on target capability to move in the environment. Then the evidential reasoning approach based on Dempster-Shafer Theory (DST) is used to perform a time integration of this classifier output. The fusion rules are tested and compared on real data obtained with our wireless sensor network.In order to handle realistic ground target tracking scenarios, we use an autonomous smart computer deposited in the surveillance area. After the calibration step of the heterogeneous sensor network, our system is able to handle real data from a wireless ground sensor network. The performance of this system is evaluated in a real exercise for intelligence operation (“hunter hunt” scenario). |
Databáze: | OpenAIRE |
Externí odkaz: |