Existing geometric and radiometric compensation methods for direct-projected augmented reality focus on static projection surfaces rather than dynamic surfaces (with varying geometry in time). We aim at providing an effective framework for projecting a sequence of augmented reality images onto dynamic surfaces without geometric and radiometric distortion. We present our design of a special pattern image for simultaneous geometric and radiometric compensation and evaluate two different techniques for embedding the pattern image into augmented reality images. The validity of the proposed method is examined through a variety of experiments with a mobile projector-camera system.

We present a mobile pointing and input system for mobile phones with minimal hardware parts that allows users who wear an eyeglass display to view and interact with a large virtual image. To use the mobile phone as a pointing and input device, a fiducial marker-based tracking system developed for augmented reality is adapted for our system. The brightness and shape of active marker could be changed according to the state of operating environment and/or the user's intentions in order to increase the detection rate of the marker.

In home environments, demands for a robot to serve a user are on the increase, such as cleaning rooms, bringing something to the user, and so on. To achieve these tasks, it is essential for developing a natural way of human-robot interaction (HRI). One of the most natural ways is that the robot approaches the user to do some tasks after recognizing the user's call and localizing its position. In this case, user localization becomes a key technology. In this paper, we propose a novel audio visual user localization system. It consists of a microphone array with eight sensors and a video camera. Estimating calling direction is achieved by the spectral subtraction of the spatial spectra. In particular, a novel beam forming method is proposed to suppress the nonstationary audio noises where they always occur in a real world. Furthermore, a robust method for face detection is proposed to double check the user based on an Adaboost classifier. It is improved to reduce the false alarms remarkably through a new postprocessing on face candidates. Successful results in a real home environment show its efficacy and feasibility. The implementation issues, limitations, and their possible solutions are also discussed.

An effective human-robot interaction is essential for wide penetration of mobile home robots into the market. The ability to track human in the home environment is one of fundamental functions of home robots. In this paper, we introduce a prototype of Samsung home robot (SHR) developed by Samsung Advanced Institute of Technology (SAIT) and present a scheme of tracking user movement utilizing a structured light range sensor. The structured light range sensor is considered to be cost-effective and robust for a wide range of environment; however, its low resolution of range data tends to extract wrong features for the human tracking, such as table legs, trash cans, door-edges, etc. To compromise this weakness, we have developed an algorithm that excludes those features that do not come from human legs. Efficacy and robustness of this proposed system were examined through experiments in the real home environment.

Describes a pattern classification approach for detecting frontal-view faces via learning a decision boundary. The classification can be achieved either by explicit estimation of density functions of two classes, face and non-face or by direct learning of a classification function (decision boundary). The latter is a more effective approach, when the number of training available examples is small, compared to the dimensionality of image space. The proposed method consists of a implicit modeling of both face and near-face classes using Independent Component Analysis (ICA), and a subsequent classification stage based on the decision boundary estimation using Support Vector Machine (SVM). Multiple nonlinear SVMs are trained for local subspaces, considering the general non-Gaussian and multi-modal characteristic of face space. This parallelization of SVMs reduces computational cost of on-line classification, since the locally trained SVM has small number of support vectors compared to the SVM trained on entire data space. We showed that the proposed algorithm is superior to the simple combination of ICA and SVM, both in accuracy and computational burden.

Sinusoidal speech coders have been widely studied for low bit rate coding around 4 kbit/s. However, the estimation error of the sinusoidal model parameters would seriously degrade the speech quality. In general, the estimation errors are caused by the effects of various types of speech signal or background noise. In this paper we propose a sinusoidal speech coder with robust parameter determination methods. They consist of spectro-temporal autocorrelation method for robust pitch determination, frequency shifting method for robust voicing level measurement, and residual-spectrum magnitude coding method for spectral magnitude compensation. From the experimental results, we can find the robustnesses of the proposed techniques. In addition, informal listening test of the synthesized speech confirms the effectiveness of the incorporated schemes.

This paper proposes a new 4 kbit/s speech coder based on CELP structure with 45 ms total codec delay. The coder is mainly featured by the renewal codebook of the excitation signal and the linked split-vector quantizer of line spectrum pair parameters which enable the coder to get high quality speech at low bit rate. In addition, techniques of formant enhancement in the spectral envelop and harmonic recovery in the transient region are also introduced to reduce buzzy and hoarse sounds, respectively. From the intensive listening test with intermediated response system (IRS) speech, we obtained a comparable subjective quality to 32 kbit/s ADPCM (ITU Recommendation G.726) under a nominal speech input level of -26 dB overload.

In speech coding, several vector quantization (VQ) methods for the LPC (linear predictive coding) parameters have been developed. Because LPC parameters are too dynamic to quantize directly, the LSFs (line spectrum frequencies) are used instead. In this study, we propose the linked split-vector quantizer (LSVQ) where the lower and the upper codebook are selected according to the preselected middle codevector. Using the ordering property of LSFs, LSVQ links three codebooks for the efficient use of the codebook space. Compared with the conventional split-vector quantizer (SVQ), LSVQ increases the usage of codebook space by 10.84%, and shows lower spectral distortion at 23 bits/frame than the SVQ at 24 bits/frame.