Detail výsledku
Distributed Visual Sensor Network Fusion
Zendulka Jaroslav, doc. Ing., CSc., UIFS (FIT)
The poster deals with a framework fordistributed visual sensor network metadata management system. It is assumedthat data coming from many cameras is annotated using computer vision modulesto produce metadata representing moving objects in their states. The data issupposed to be noisy, uncertain and some states might be missing. Firstly, hereis described the spatio-temporal data cleaning using Kalman filter. Secondly,it copes with many visual sensors fusion and persistent object tracking within alarge area. Thirdly, it describes the data and architecture model.
Visual sensor, distributednetwork, metadata management, moving objects, spatio-temporal data,Kalman filter, sensor fusion, object tracking, large area surveillancesystem.
Visual sensor, distributed network, metadata management, moving objects, spatio-temporal data, Kalman filter, sensor fusion, object tracking, large area surveillance system.
@misc{BUT192634,
author="Petr {Chmelař} and Jaroslav {Zendulka}",
title="Distributed Visual Sensor Network Fusion",
booktitle="4th Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms",
year="2007",
pages="2",
address="Brno",
note="Abstract"
}