• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• pp.91-94
• /
• 2022

자율주행 자동차 개발 연구가 활발히 진행됨에 따라 객체 검출기의 성능이 중요하게 되었다. 딥러닝 기술의 발전하면서 객체 검출기의 성능도 큰 발전을 이루었다. 그에 따라 도로 위 차량 검출기의 성능도 발전하고 있으나 평상시 낮 도로상황에서 잘 동작하던 모델은 안개가 끼거나 밤 상황이 되면 제대로 동작하지 못하는 문제를 가지고 있다. 이유는 딥러닝 모델이 학습할 때 사용한 데이터셋의 정보에 따라 특정 도메인에 편향된 특성을 학습하기 때문이다. 따라서, 본 논문에서는 객체 검출 신경망에 도메인 판별기를 적용하여 이와 같은 도메인 이동 문제를 극복하는 모델을 제안한다. 모델의 성능을 Cityscapes 데이터셋과 Foggy Cityscapes 데이터셋을 사용하여 평가한 결과, 기존의 특정 도메인에서 학습한 모델보다 제안하는 모델의 검출 성능이 개선된다는 것을 확인하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.29 no.1
• /
• pp.76-81
• /
• 2010

In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the second-order conditional maximum a posteriori (CMAP). In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the current observation and the speech activity decisions in the pervious two frames. Experimental results show that the proposed approach yields better results compared to the statistical model-based and the CMAP-based VAD using the LR test.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.465-469
• /
• 1998

가변 전송율 음성 부호화기를 위한 음성 검출기를 통계적 모델을 적용하여 설계한다. 제안된 음성 검출기는 음성 파라미터를 decision-directed 방식으로 추정함으로써 LRT를 이용하여 동작 특성이 우수한 판정 규칙을 유도한다. 또한 음성 발생 사건들을 1차의 Markov process 로 모델링 함으로써 과거의 관찰들을 현재 프레임의 음성 검출 과정에서 고려할 수 있는 행오버 알고리즘을 개발한다. 개발된 음성 검출기는 고려된 실험환경에서 ITU-T 표준인 G.729 Annex B 음성 검출기보다 맹 우수한 성능을 나타내었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.4B
• /
• pp.245-256
• /
• 2003

2-D OCDMA is considered to be a viable technical solution for optical LANs, and a considerable amount of research effort has been devoted to various 2-D OCDMA techniques. In this paper, we propose two new interference model for 2-D OCDMA LANs employing unipolar random codes, and derive maximum-likelihood detectors based on these interference models. The BER performance of the maximum likelihood detectors and that of other existing detectors are compared through extensive computer simulation. In addition, the complexity of high-speed implementation of the detectors is assessed, and as a result, we found that the AND detector and the maximum-likelihood detectors for the pulse-binomial and the pulse-Poisson model offer the best trade-off between the BER performance and the facility of high-speed implementation.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.397-402
• /
• 2007

In this paper, we apply a support vector machine(SVM) that incorporates an optimized nonlinear decision rule over different sets of feature vectors to improve the performance of statistical model-based voice activity detection(VAD). Conventional method performs VAD through setting up statistical models for each case of speech absence and presence assumption and comparing the geometric mean of the likelihood ratio (LR) for the individual frequency band extracted from input signal with the given threshold. We propose a novel VAD technique based on SVM by treating the LRs computed in each frequency bin as the elements of feature vector to minimize classification error probability instead of the conventional decision rule using geometric mean. As a result of experiments, the performance of SVM-based VAD using the proposed feature has shown better results compared with those of reported VADs in various noise environments.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.39 no.2
• /
• pp.144-152
• /
• 2011

This paper presents a new scheme for fault detection and isolation in the satellite system. The purpose of this paper is to develop a fault detection, isolation and diagnosis algorithm based on the bank of interacting multiple model (IMM) filter for both total and partial faults in a satellite attitude control system (ACS). In this paper, IMM are utilized for detection and diagnosis of anticipated actuator faults in a satellite ACS. Other fault detection, isolation (FDI) schemes using conventional IMM are compared with the proposed FDI scheme. The FDI procedure is developed in two stages. In the first stage, 11 EKFs actuator fault models are designed to detect wherever actuator faults occur. In the second stage of the FDI scheme, two filters are designed to identify the fault type which is either the total or partial fault. An important feature of the proposed FDI scheme can decrease fault isolation time and figure out not only fault detection and isolation but also fault type identification.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.5
• /
• pp.194-198
• /
• 2007

In this paper, we apply a discriminative weight training to a statistical model-based voice activity detection(VAD). In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratios(LRs) based on a minimum classification error(MCE) method which is different from the previous works in that different weights are assigned to each frequency bin which is considered more realistic. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LR test.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.8 no.3
• /
• pp.145-150
• /
• 2014

In this paper, we propose a novel scheme to improve the performance of a voice activity detection(VAD) which is based on the deep belief networks(DBN) with the likelihood ratio(LR). The proposed algorithm applies the DBN learning method which is trained in order to minimize the probability of detection error instead of the conventional decision rule using geometric mean. Experimental results show that the proposed algorithm yields better results compared to the conventional VAD algorithm in various noise environments.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.7
• /
• pp.372-378
• /
• 2008

Voice activity detectors (VAD) are important in wireless communication and speech signal processing, In the conventional VAD methods, an expression for the likelihood ratio test (LRT) based on statistical models is derived in discrete Fourier transform (DFT) domain, Then, speech or noise is decided by comparing the value of the expression with a threshold, This paper presents a new statistical VAD method based on a signal subspace approach, The probabilistic principal component analysis (PPCA) is employed to obtain a signal subspace model that incorporates probabilistic model of noisy signal to the signal subspace method, The proposed approach provides a novel decision rule based on LRT in the signal subspace domain, Experimental results show that the proposed signal subspace model based VAD method outperforms those based on the widely used Gaussian distribution in DFT domain.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.100-106
• /
• 2008

In this paper we apply a discriminative weight training employing power spectral flatness measure (PSFM) to a statistical model-based voice activity detection (VAD) in various noise environments. In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratio test (LRT) based on a minimum classification error (MCE) method which is different from the previous works in th at different weights are assigned to each frequency bin and noise environments depending on PSFM. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LRT.