Share This Author
Robust speech interface based on audio and video information fusion for humanoid HRP-2
- Isao Hara, F. Asano, Kiyoshi Yamamoto
- Computer Science, PhysicsIEEE/RSJ International Conference on Intelligent…
- 28 September 2004
In this method, audio information and video information are fused by a Bayesian network to enable the detection of speech events and the information of detected speech events is utilized in sound separation using adaptive beam forming.
Motion segmentation based on factorization method and discriminant criterion
- N. Ichimura
- Computer ScienceProceedings of the Seventh IEEE International…
A motion segmentation algorithm based on factorization method and discriminant criterion and it is proposed that this grouping is robust against noise and outliers because features with no useful information are automatically rejected.
Maneuvering target tracking by using particle filter
- N. Ikoma, N. Ichimura, T. Higuchi, H. Maeda
- Computer Science, EngineeringProceedings Joint 9th IFSA World Congress and…
- 25 July 2001
This research uses a state-space representation to track a maneuvering target and proposes the use of heavy-tailed non-Gaussian distribution for the system noise to follow abrupt changes in the target's motion due to sudden operations of the acceleration pedal, braking and steering.
A robust and efficient motion segmentation based on orthogonal projection matrix of shape space
- N. Ichimura
- Engineering, Computer ScienceProceedings IEEE Conference on Computer Vision…
- 13 June 2000
A novel algorithm for motion segmentation that uses the fact that shape of an object with homogeneous motion is represented as 4 dimensional linear space is proposed and is robust for data with noise and outliers.
R&D of versatile 3D vision system VVV
- F. Tomita, T. Yoshimi, Y. Ishiyama
- Computer ScienceSMC'98 Conference Proceedings. IEEE…
- 11 October 1998
An advanced 3D vision system VVV (Versatile Volumetric Vision) which can be used for many purposes in many fields; robotics, medical and welfare, CAD, VR, etc.
Detection and Separation of Speech Event Using Audio and Video Information Fusion and Its Application to Robust Speech Interface
A method of detecting speech events in a multiple-sound-source condition using audio and video information is proposed and a maximum likelihood adaptive beamformer is employed as a preprocessor of the speech recognizer to separate the speech signal from environmental noise.
An Application of a Particle Filter to Bayesian Multiple Sound Source Tracking with Audio and Video Information Fusion
A particle filter is applied to the problem of detecting and tracking multiple sound sources by Bayesian inference using combined audio and video information and the computational cost is reduced significantly compared to exactBayesian inference, while maintaining the quality of estimation.
Stochastic filtering for motion trajectory in image sequences using a Monte Carlo filter with estimation of hyper-parameters
- N. Ichimura
- EngineeringObject recognition supported by user interaction…
- 1 August 2002
Experimental results using synthetic data show that the proposed method can estimate appropriate hyper-parameters for tracking motion and reducing the effect of outliers.
Motion segmentation using feature selection and subspace method based on shape space
- N. Ichimura
- Computer ScienceProceedings 15th International Conference on…
- 3 September 2000
An algorithm using feature selection and subspace method is proposed to solve the combinatorial problem of motion segmentation using feature correspondences and the result can be solved without optimization.
Detection and separation of speech segment using audio and video information fusion
For detecting speech events, sound localization using a microphone array and human tracking by stereo vision is combined by a Bayesian network and a maximum likelihood adaptive beamformer is constructed.