Improved Adaptivity and Robustness in Decentralised Multi-Camera Networks

Lukas Esterle, Bernhard Rinner Peter R. Lewis, and Xin Yao
In Proceedings of the Sixth ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC 2012), pp 1-6. IEEE Press, 2012.

In this paper we present increased adaptivity and robustness in distributed object tracking by multi-camera networks using a socio-economic mechanism for learning the vision graph. To build-up the vision graph within a distributed smart-camera network, we use an ant-colony inspired mechanism, which exchanges responsibility for tracking objects using Vickrey auctions. Employing the learnt vision graph allows the system to optimise its communication. Since distributed smart camera networks are prone to uncertainties in individual cameras, such as failures or changes in extrinsic parameters, the vision graph should be sufficiently robust to enable seamless tracking and optimised communication. To better reflect real smart-camera platforms and networks, we consider that communication and handover are not instantaneous, and that cameras may be added, removed or their properties changed during runtime. Using our dynamic socio-economic approach, the network is able to continue tracking objects well, despite these uncertainties, and in some cases with improved performance. This demonstrates the adaptivity and robustness of our approach.

@InProceedings{esterle_2012,
title = "Improved Adaptivity and Robustness in Decentralised Multi-Camera Networks",
booktitle = "Proceedings of the Sixth International Conference on Distributed Smart Cameras (ICDSC 2012)",
author = "Lukas Esterle and Bernhard Rinner and Peter R. Lewis and Xin Yao",
location = "Hong Kong"
year = "2012",
publisher = "IEEE Press",
pages = "1--6"
}