Detection and Localization of 3D Audio-Visual Objects Using Unsupervised Clustering

Vasil Khalidov 1 Florence Forbes 1 Miles Hansard 2 Elise Arnaud 2 Radu Horaud 2
1 MISTIS - Modelling and Inference of Complex and Structured Stochastic Systems
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
2 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This paper addresses the issues of detecting and localizing objects in a scene that are both seen and heard. We explain the benefits of a human-like configuration of sensors (binaural and binocular) for gathering auditory and visual observations. It is shown that the detection and localization problem can be recast as the task of clustering the audio-visual observations into coherent groups. We propose a probabilistic generative model that captures the relations between audio and visual observations. This model maps the data into a common audio-visual 3D representation via a pair of mixture models. Inference is performed by a version of the expectationmaximization algorithm, which is formally derived, and which provides cooperative estimates of both the auditory activity and the 3D position of each object. We describe several experiments with single- and multiple-speaker detection and localization, in the presence of other audio sources.
Complete list of metadatas


https://hal.inria.fr/inria-00373148
Contributor : Elise Arnaud <>
Submitted on : Friday, April 3, 2009 - 2:41:31 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:41 AM
Long-term archiving on : Thursday, June 10, 2010 - 7:40:53 PM

Identifiers

Citation

Vasil Khalidov, Florence Forbes, Miles Hansard, Elise Arnaud, Radu Horaud. Detection and Localization of 3D Audio-Visual Objects Using Unsupervised Clustering. ICMI 2008 - ACM/IEEE International Conference on Multimodal Interfaces, Oct 2008, Chania, Greece. pp.217-224, ⟨10.1145/1452392.1452438⟩. ⟨inria-00373148⟩

Share

Metrics

Record views

692

Files downloads

411