Akitoshi Itai

Footstep classification using simple speech recognition technique

The characteristics of human footsteps are determined by the gait, the footwear and the floor. Accurate footstep analysis would be useful in various applications, home security service, surveillance and understanding of human action since the gait expresses personality, age and gender. The feasibility of a footstep classification has been confirmed by using the acoustic feature parameter[1], however, almost of conventional approaches are focused on the statistical features and pattern recognitions. In the speech recognition, a feature string is stretched and compressed in the time domain. The dynamic programming is used to accomplish this task, and is an effective method of absorbing time domain fluctuations. In the footstep classification, footstep sound (i.e. an impact sound and a fricative sound) is expanded and contracted in the time domain the same as speeches. This paper applies the DTW and cepstra to the footstep classification. Result shows that the proposed method is useful to the footstep recognition problems.

Global Noise Estimation Based on Tensor Product Expansion with Absolute Error

This paper proposes a novel signal estimation method that uses a tensor product expansion. When a bivariable function, which is expressed by two-dimensional matrix, is subjected to conventional tensor product expansion, two single variable functions are calculated by minimizing the mean square error between the input vector and its outer product. A tensor product expansion is useful for feature extraction and signal compression, however, it is difficult to separate global noise from other signals. This paper shows that global noise, which is observed in almost all input signals, can be estimated by using a tensor product expansion where absolute error is used as the error function.

Personal Identification Using Footstep Detection in In-Door Environment

Footsteps, with different shoes of heels, sneakers, leathers or even bare footed, will appear in different grounds of concrete, wood, etc. If a footstep is discriminable, the application to various fields can be considered. In this paper, the feature extraction of a footstep is investigated. We focus on the recognizing a certain kind of footstep waveforms under the restricted condition. We propose a new methodology using the feature parameter such as the peak frequency set by the mel-cepstrum analysis, the walking intervals and the similarity of spectrum envelope. It is shown for personal identification that the performance of the proposed method is effective.

Footstep Recognition with Psyco-acoustics Parameter

The characteristics of a footstep are determined by the gait, the footwear and the floor. Accurate footstep analysis would be useful in various applications, home security service, surveillance and understanding of human action since the gait expresses personality, age and gender. The feasibility of personal identification has been confirmed by using the feature parameter of footsteps (Shoji et al., 2004), however, the recognition rate of this method decreases as the number of subjects increases. This paper applies psycho-acoustics parameter to feature extraction. Results show that the parameter proposed herein yields effective and practical personal identification

Sound Localization of Approaching Vehicles Using Uniform Microphone Array

Due to recent trends in society, enhanced car safety is strongly required. As one piece of environmental traffic information, the direction of approaching vehicles can be estimated from an analysis of sound sources. This gives information of approaching vehicles to drivers at intersections when visibility is poor. To prevent traffic accidents, it is necessary to detect the direction of approaching vehicles more accurately and rapidly. This paper describes a scheme that uses a uniform linear microphone array with four microphones to estimate the direction of approaching vehicles. We employ a correlation method to realize sound source localization and we propose a direction estimation method with cubic spline interpolation in Carter, G. C. and Abraham, P. B. (1980). Trials show that the proposed scheme offers good performance.

Footstep classification using wavelet decomposition

The characteristics of human footsteps are determined by the gait, the footwear and the floor. Accurate footstep analysis would be useful in various applications, home security service, surveillance and understanding of human action since the gait expresses personality, age and gender. The feasibility of personal identification has been confirmed by using the feature parameter of footsteps, however, it is necessary to use more effective parameters since the recognition rate of this method decreases as the number of subjects increases. In audio classification, Fourier and wavelet transform were used to extract the feature of audio signals. The feasibility of a footstep classification using Fourier and wavelet parameters were confirmed previously. In this paper, we focused on the wavelet parameter which consists of subband power, time-brightness and time-width. Previous work shows that the feature extraction using wavelet transform is effective for footstep categorizations, however, an optimal frame length for feature extraction and the relationship between a recognition rate and the length of feature parameters are not discussed in that paper. This paper provides two dominant results; the frame window size, which yield the good accuracy for footstep classification, is 4096; the feature parameter based on wavelet parameters can be reduced to 2/3 with equivalent recognition rate. Results show that the parameter applied herein yields effective and practical footstep classification.

Personal Identification Using Footstep Based on Wavelets

The characteristics of a footstep are determined by the gait, the footwear and the floor. Accurate footstep analysis would be useful in various applications, home security service, surveillance and understanding of human action since the gait expresses personality, age and gender. The feasibility of personal identification has been confirmed by using the feature parameter of footsteps, however, it is necessary to use more effective parameters since the recognition rate of this method decreases as the number of subjects increases. In this paper, wavelet transform is applied to feature extraction from footsteps. In audio classification, Fourier and wavelet transform are used to extract the feature of audio signals. Results show that the parameter proposed herein yields effective and practical personal identification

Spectrum based feature extraction using spectrum intensity ratio for SSVEP detection

Recent years, a Steady-State Visual Evoked Potential (SSVEP) is used as a basis for Brain Computer Interface (BCI)[1]. Various feature extraction and classification techniques are proposed to achieve BCI based on SSVEP. The feature extraction of SSVEP is developed in the frequency domain regardless of the limitation in flickering frequency of visual stimulus caused by hardware architecture. We introduce here the feature extraction using a spectrum intensity ratio. Results show that the detection ratio reaches 84% by using a spectrum intensity ratio with unsupervised classification. It also indicates the SSVEP is enhanced by proposed feature extraction with second harmonic.

Approaching vehicle detection using linear microphone array

Due to recent trends in society, enhanced car safety is strongly required. To prevent traffic accidents, it is necessary to detect the direction of approaching vehicles in T-intersection accurately and rapidly. This paper describes a scheme that uses a linear microphone array with four microphones to estimate the approaching vehicles. We employ a cross-correlation method to realize sound source localization and propose a direction estimation scheme based on the weighted sum of interpolated cross-correlation. Trials show that the proposed scheme offers good performance.

A study on using linear microphone array-based acoustic sensing to detect approaching vehicles

Due to recent trends in society, enhanced car safety is strongly required. To prevent traffic accidents, it is important to estimate the direction of approaching vehicles at intersections. Conventional research employs the cross correlation of a 4-microphone array to detect a single approaching vehicles, the detection of multiple vehicles has not yet been attempted. This paper describes a technique that uses a linear microphone array with four microphones to detect two approaching vehicles simultaneously. Field trials show that the proposed scheme offers accurate direction estimation of two approaching vehicles.