• 한국정보통신학회논문지
• /
• 제9권5호
• /
• pp.986-994
• /
• 2005

본 논문은 잡음 환경하에서 적응 가능한 음성구간검출를 구축하기 위하여 우도기반의 음성 특징 파라미터의 비선형 차원축소 방법을 제안한다. 제안하는 차원축소 방법은 음성/비음성 클래스에 대한 가우시아 확률 밀도 함수의 비선형적 우도값을 새로운 특징으로 취하는 방법이다. 음성구간검출기의 음성/비음성 결정은 우도비 검증(LRT)의 통계적 방법을 이용하며, 선형판별분석(LDA)에 의한 차원축소 결과와 성능을 비교한다. 실험 결과 제안된 차원 축소 방법으로 음성 특징 파라미터를 2차원으로 축소한 결과가 원래 특징백터의 차원에서의 결과와 대등한 성능을 확인하였다.

• International Journal of Control, Automation, and Systems
• /
• 제4권6호
• /
• pp.736-747
• /
• 2006

Simultaneous Localization and Map Building(SLAM) is one of the fundamental problems in robot navigation. The Extended Kalman Filter(EKF), which is widely adopted in SLAM approaches, requires extensive computation. The conventional particle filter also needs intense computation to cover a high dimensional state space with particles. This paper proposes an efficient SLAM method based on the recursive unscented Kalman filtering in an environment including a large number of landmarks. The posterior probability distributions of the robot pose and the landmark locations are represented by their marginal Gaussian probability distributions. In particular, the posterior probability distribution of the robot pose is calculated recursively. Each landmark location is updated with the recursively updated robot pose. The proposed method reduces filtering dimensions and computational complexity significantly, and has produced very encouraging results for navigation experiments with noisy multiple simultaneous observations.

• 한국컴퓨터정보학회논문지
• /
• 제6권2호
• /
• pp.41-47
• /
• 2001

본 연구에서는 카메라로부터 입력되는 영상열에서 사람과 같은 유동적인 이동 물체를 신뢰성 있게 판별하는 방법을 제안한다. 실시간 처리가 요구되는 시스템으로 빠른 수행속도와 적은 계산망, 신뢰성 있는 동작을 위해 입력영상과 참고영상에서 차영상을 구하고, 차영상의 히스토그램을 분석하여 여러개의 임계치을 결정한 후, 이를 사용하여 이동물체 영역을 신뢰성 있게 분리하고, 효율적으로 패턴을 분류할 수 있는 신경망을 이용하여 분리된 영역을 판별한다. 제안된 방법은 실제 상황에서 얻은 다양한 영상을 적용하여 실험하였으며, 4개층의 신경망을 적용하여 이동물체 검출 결과를 제시한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.1183-1186
• /
• 1998

Adaptive nois canceller can extract the noiseremoved spech in noisy speech signal by adapting the filter-coefficients to the background noise environment. A kind of LMS algorithm is one of the most popular adaptive algorithm for noise cancellation due to low complexity, good numerical property and the merit of easy implementation. However there is the matter of increasing misadjustment at voiced speech signal. Therefore the demanded speech signal may be extracted. In this paper, we propose a fast and noise robust wavelet packet adaptive noise canceller with NLMS-SUM method LMS combined algorithm. That is, we decompose the frequency of noisy speech signal at the base of the proposed analysis tree structure. NLMS algorithm in low frequency band can efficiently dliminate the effect of the low frequency noise and SUM method LMS algorithm at each high frequency band can remove the high frequency nosie. The proposed wavelet packet adaptive noise canceller is enhanced the more in SNR and according to Itakura-Satio(IS) distance, it is closer to the clean speech signal than any other previous adaptive noise canceller.

• The Journal of the Acoustical Society of Korea
• /
• 제22권3E호
• /
• pp.113-123
• /
• 2003

One of the most important problems in speech recognition is to detect the presence of speech in adverse environments. In other words, the accurate detection of speech boundary is critical to the performance of speech recognition. Furthermore the speech detection problem becomes severer when recognition systems are used over the telephone network, especially wireless network and noisy environment. Therefore this paper describes various speech detection algorithms for continuous digit recognition system used over wire/wireless telephone networks and we propose a algorithm in order to improve the robustness of speech detection using useful band selection under noisy telephone networks. In this paper, we compare some speech detection algorithms with the proposed one, and present experimental results done with various SNRs. The results show that the new algorithm outperforms the other speech detection methods.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.605-608
• /
• 1999

A conventional image coder, such as JPEG, requires not only DCT and quantization but also additional pre-filtering under noisy environment. Since the pre-filtering removes camera noise and improves coding efficiency dramatically, its efficient implementation has been an important issue. Based on well-known noise removal techniques in image processing fields, this paper introduces an efficient scheme by adapting a noise removal procedure to block-based image coders. By using two-dimensional DCT factorization, the proposed image coder has only a modified DCT and a VLC, and performs pre-filtering and quantization simultaneously in the modified DCT operation.

• 비파괴검사학회지
• /
• 제31권6호
• /
• pp.665-670
• /
• 2011

In this paper, a new approach to detect surface cracks from a noisy thermal image in the infrared thermography is presented using an holomorphic characteristic of temperature field in a thin plate under steady-state thermal condition. The holomorphic function for 2-D heat flow field in the plate was derived from Cauchy Riemann conditions to define a contour integral that varies according to the existence and strength of a singularity in the domain of integration. The contour integral at each point of thermal image eliminated the temperature variation due to heat conduction and suppressed the noise, so that its image emphasized and highlighted the singularity such as crack. This feature of holomorphic function was also investigated numerically using a simple thermal field in the thin plate satisfying the Laplace equation. The simulation results showed that the integral image selected and detected the crack embedded artificially in the plate very well in a noisy environment.

• 수산해양기술연구
• /
• 제30권2호
• /
• pp.125-131
• /
• 1994

This paper describes a method to measure the distortion level of loudspeaker using a LMS(Least Mean Square) adaptive filter. Conventional technique to measure the distortion level uses a band-pass filter with a sharp cut-off frequency characteristics. However. such the band-pass filter has a bed time response characteristics. On the other hand, the proposed method offers us an easy way to measure the specified harmonic distortion level with a small hardware. Moreover, our method is not affected by noise which has no correlation with the test signal, and the measurement can be carried out in a noisy environment. The effectiveness of the proposed method is confirmed by experiment using a loudspeaker in a noisy room.

• 한국음향학회지
• /
• 제1권1호
• /
• pp.45-53
• /
• 1982

A robust linear predictive coding method that can be used in noisy as well as quiet environment has been studied. In this method, noise autocorrelation coeffieients are first obtained and updated during nonspeech periods. Then, the effect of additive noise in the input speech is removed by subtracting values of the noise autocorrelation coefficients of corrupted speech in the course of computation of linear prediction coefficients. When signal-to-noise ratio of the input speech ranges from 0 to 10 dB, a performance improvement of about 5 dB can be gained by using this method. The proposed method is computationally very efficient and requires a small storage area.

• 한국통신학회논문지
• /
• 제21권10호
• /
• pp.2552-2562
• /
• 1996

In this paper, we propose a segmentation algorithm that can reliably separate moving objects from noisy background in the image sequance received from a camera at the fixed position. The proposed algorithm consists of three processes:generation of the difference image between the input image and the reference image, multilevel quantization of the difference image, and multistagemerging in the quantized image. The quantization process requantizes the difference image based on the multiple threshold values determined bythe histogram analysis. The merging starts from the seed region which created by using the highest threshold value and ends when termination conditions are met. the proposed method has been tested with various real imge sequances containing intruders. The test results show that the proposed algorithm can detect moving objects like intruders very effectively in the noisy environment.