Acoustic Sensor-Based Multiple Object Tracking with Visual Information Association. (23rd August 2010)

• Record Type: Journal Article
• Authors: Lee Lee, Jinseok Jinseok; Hong Hong, Sangjin Sangjin; Moon Moon, Nammee Nammee; Oh Oh, Seong-Jun Seong-Jun
• Other Names: Kellermann Kellermann Walter Walter Academic Editor.
• Is Part Of: EURASIP journal on advances in signal processing. Volume 2010(2010)
• Publication Date: 2010-08-23
• Subjects: Signal processing -- Periodicals; Traitement du signal; Signal processing; Periodicals; 621.3822
• DOI: 10.1155/2010/591340
• Languages: English
• ISSNs: 1687-6172

Abstract

Abstract : Object tracking by an acoustic sensor based on particle filtering is extended for the tracking of multiple objects. In order to overcome the inherent limitation of the acoustic sensor for the simultaneous multiple object tracking, support from the visual sensor is considered. Cooperation from the visual sensor, however, is better to be minimized, as the visual sensor's operation requires much higher computational resources than the acoustic sensor-based estimation, especially when the visual sensor is not dedicated to object tracking and deployed for other applications. The acoustic sensor mainly tracks multiple objects, and the visual sensor supports the tracking task only when the acoustic sensor has a difficulty. Several techniques based on particle filtering are used for multiple object tracking by the acoustic sensor, and the limitations of the acoustic sensor are discussed to identify the need for the visual sensor cooperation. Performance of the triggering-based cooperation by the two visual sensors is evaluated and compared with a periodic cooperation in a real environment.