Online Audio-Visual Multi-Source Tracking and Separation: A Labeled Random Finite Set Approach
The dissertation proposes an online solution for separating an unknown and time-varying number of moving sources using audio and visual data. The random finite set framework is used for the modeling and fusion of audio and visual data. This enables an online tracking algorithm to estimate the source...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
Curtin University
2021
|
| Online Access: | http://hdl.handle.net/20.500.11937/89300 |
| Summary: | The dissertation proposes an online solution for separating an unknown and time-varying number of moving sources using audio and visual data. The random finite set framework is used for the modeling and fusion of audio and visual data. This enables an online tracking algorithm to estimate the source positions and identities for each time point. With this information, a set of beamformers can be designed to separate each desired source and suppress the interfering sources. |
|---|