Joint audio-video object localization using a recursive multi-state multi-sensor estimator
Strobel N, Spors S, Rabenstein R (2000)
Publication Status: Published
Publication Type: Conference contribution, Conference Contribution
Publication year: 2000
Publisher: IEEE
City/Town: Piscataway, NJ, United States
Book Volume: 4
Pages Range: 2397-2400
Event location: Istanbul
URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=0033677156&origin=inward
Abstract
Object localization based on audio and video information is important for the analysis of dynamic scenes such as video conferences or traffic situations. In this paper, we view the dynamic audio-video object localization problem as a joint recursive estimation problem. It is solved using a decentralized Kalman filter fusing both audio and video position estimates. To better take into account different object maneuvers, multiple state-space equations are also incorporated. The result is a recursive multi-state multi-sensor estimator. Experiments show that it yields significantly improved joint position estimates compared to results achieved by using either an audio or a video system only.
Authors with CRIS profile
Involved external institutions
Germany (DE)How to cite
APA:
Strobel, N., Spors, S., & Rabenstein, R. (2000). Joint audio-video object localization using a recursive multi-state multi-sensor estimator. In Proceedings of the 2000 IEEE Interntional Conference on Acoustics, Speech, and Signal Processing (pp. 2397-2400). Istanbul, TR: Piscataway, NJ, United States: IEEE.
MLA:
Strobel, Norbert, Sascha Spors, and Rudolf Rabenstein. "Joint audio-video object localization using a recursive multi-state multi-sensor estimator." Proceedings of the 2000 IEEE Interntional Conference on Acoustics, Speech, and Signal Processing, Istanbul Piscataway, NJ, United States: IEEE, 2000. 2397-2400.
BibTeX: Download