Paper Info
Title
Joint audio-video object localization using a recursive multi-state multi-sensor estimator
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 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.
Year
DOI
Venue
2000
10.1109/ICASSP.2000.859324
Acoustics, Speech, and Signal Processing, 2000. ICASSP '00. Proceedings. 2000 IEEE International Conference
Keywords
Field
DocType
Kalman filters,audio signal processing,audio-visual systems,equations,motion estimation,multivariable systems,object detection,recursive estimation,sensor fusion,state-space methods,decentralized Kalman filter,dynamic scene analysis,joint audio-video object localization,multiple state-space equations,object maneuvers,position estimates,recursive estimation,recursive multi-state multi-sensor estimator,sensor fusion,traffic situation analysis,video conferences
Computer vision,Object detection,Computer science,Sensor fusion,Kalman filter,Video tracking,Artificial intelligence,Motion estimation,Audio signal processing,Recursion,Estimator
Conference
Volume
ISSN
ISBN
6
1520-6149
0-7803-6293-4
Citations 
PageRank 
References 
4
0.54
1
Authors
3
Name
Order
Citations
PageRank
Strobel, N.140.54
S. Spors2899.54
R. Rabenstein311915.00