Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Large-scale camera network topology estimation by lighting variation|
van den Hengel, A.
|Citation:||Lecture Notes in Artificial Intelligence, 2017 / Blanc-Talon, J., Penne, R., Philips, W., Popescu, D., Scheunders, P. (ed./s), vol.10617 LNCS, pp.455-467|
|Series/Report no.:||Lecture Notes in Computer Science; 10617|
|Conference Name:||18th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2017) (18 Sep 2017 - 21 Sep 2017 : Antwerp, Belgium)|
|Michael Zhu, Anthony Dick, Anton van den Hengel|
|Abstract:||This paper proposes a scalable and robust algorithm to find connections between cameras in a large surveillance network, based solely on lighting variation. We show how to detect regions that are affected by lighting changes within each camera view, with limited data. Then, we establish the light-overlap connections and show that our algorithm can scale to hundreds of camera while maintaining high accuracy. We demonstrate our method on a campus network of 100 real cameras and 500 simulated cameras, and evaluate its accuracy and scalability.|
|Keywords:||Large-scale intelligent video surveillance; topology estimation; light-overlap; lighting variation detection; segmentation|
|Rights:||©Springer International Publishing AG 2017|
|Appears in Collections:||Aurora harvest 8|
Australian Institute for Machine Learning publications
Computer Science publications
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.