Omni-Directional Surveillance for Unmanned Water Vehicles - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2008

Omni-Directional Surveillance for Unmanned Water Vehicles


This paper proposes a framework for automatic maritime visual surveillance using an unmanned water vehicle (UWV). The UWV is equipped with a GPS, an e-compass and a high resolution omni-camera. A fast algorithm is proposed to automatically calibrate the moving omni-camera in real time. Moreover, a saliency based visual attention method is used for target detection. Targets are tracked using adaptively selected discriminative features and mean shift. Target locations are then geo-registered to a map, and displayed on a situational awareness console. Experiments on real data in a system deployment demonstrate the effectiveness of the maritime surveillance framework.
Fichier principal
Vignette du fichier
VS2008-Oral-1b.pdf (961.99 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00321929 , version 1 (16-09-2008)


  • HAL Id : inria-00321929 , version 1


Haiying Liu, Omar Javed, Geoff Taylor, Xiaochun Cao, Niels Haering. Omni-Directional Surveillance for Unmanned Water Vehicles. The Eighth International Workshop on Visual Surveillance - VS2008, Graeme Jones and Tieniu Tan and Steve Maybank and Dimitrios Makris, Oct 2008, Marseille, France. ⟨inria-00321929⟩


170 View
223 Download


Gmail Facebook X LinkedIn More