• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.155-161
• /
• 2021

Recently, researches for military purposes such as precision tracking and mission completion using UAVs have been actively conducted. In particular, if the posture information of the leading UAV is estimated and the mission UAV uses this information to follow in stealth and complete its mission, the speed of the posture information estimation of the guide UAV must be processed in real time. Until recently, research has been conducted to accurately estimate the posture information of the leading UAV using image processing and Kalman filters, but there has been a problem in processing speed due to the sequential processing of the processing process. Therefore, in this study we propose a way to improve processing speed by applying methods that the image processing area is limited to the ROI area including the object, not the entire area, and the continuous processing is distributed to OpenMP-based multi-threads and processed in parallel with thread synchronization to estimate attitude information. Based on the experimental results, it was confirmed that real-time processing is possible by improving the processing speed by more than 45% compared to the basic processing, and thus the possibility of completing the mission can be increased by improving the tracking and estimating speed of the mission UAV.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.3-9
• /
• 2017

Recently, in 3rd Generation Partnership Project(3GPP), there is a study of the Long Term Evolution(LTE) based vehicle communication which has been actively conducted to provide a transport efficiency, telematics and infortainment. Because the vehicle communication is closely related to the safety, it requires a reliable communication. Because vehicle speed is very fast, unlike the movement of the user, radio channel is rapidly changed and generate a number of problems such as transmission quality degradation. Therefore, we have to continuously updates the channel estimates. There are five types of conventional channel estimation scheme. Least Square(LS) is obtained by pilot symbol which is known to transmitter and receiver. Decision Directed Channel Estimation(DDCE) scheme uses the data signal for channel estimation. Constructed Data Pilot(CDP) scheme uses the correlation characteristic between adjacent two data symbols. Spectral Temporal Averaging(STA) scheme uses the frequency-time domain average of the channel. Smoothing scheme reduces the peak error value of data decision. In this paper, we propose the novel channel estimation scheme in LTE based Vehicle-to-Vehicle(V2V) environment. In our Hybrid Reliable Channel Estimation(HRCE) scheme, DDCE and Smoothing schemes are combined and finally the Linear Minimum Mean Square Error(LMMSE) scheme is applied to minimize the channel estimation error. Therefore it is possible to detect the reliable data. In simulation results, overall performance can be improved in terms of Normalized Mean Square Error(NMSE) and Bit Error Rate(BER).

• Phonetics and Speech Sciences
• /
• v.15 no.4
• /
• pp.91-100
• /
• 2023

Reverberation time (T60) is a typical acoustic parameter that provides information about reverberation. Since the impacts of reverberation vary depending on the frequency bands even in the same space, frequency-dependent (FD) T60, which offers detailed insights into the acoustic environments, can be useful. However, most conventional blind T60 estimation methods, which estimate the T60 from speech signals, focus on fullband T60 estimation, and a few blind FDT60 estimation methods commonly show poor performance in the low-frequency bands. This paper introduces a modified approach based on Attentive pooling based Weighted Sum of Spectral Decay Rates (AWSSDR), previously proposed for blind T60 estimation, by extending its target from fullband T60 to FDT60. The experimental results show that the proposed method outperforms conventional blind FDT60 estimation methods on the acoustic characterization of environments (ACE) challenge evaluation dataset. Notably, it consistently exhibits excellent estimation performance in all frequency bands. This demonstrates that the mechanism of the AWSSDR method is valuable for blind FDT60 estimation because it reflects the FD variations in the impact of reverberation, aggregating information about FDT60 from the speech signal by processing the spectral decay rates associated with the physical properties of reverberation in each frequency band.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10c
• /
• pp.166-170
• /
• 2006

본 논문은 스트림 형태로 발생하는 이동객체의 위치정보에 대해 과거 시점의 위치정보 추정 방법을 제안한다. 기존 이동객체의 위치 추정에 대한 연구는 메모리 량의 제한이 없는 상태에서 이미 저장된 과거 데이터를 이용하여 임의의 과거 시점 위치를 추정하는 방법이다. 그러나 스트림 환경에서는 위치정보가 무한하게 발생하기 때문에 모든 위치정보를 저장 및 관리할 수 없다. 따라서 본 논문에서는 스트림 형태로 발생하는 위치정보에 대하여 제한된 메모리를 사용하여 임의의 과거시점 위치를 추정하는 방법을 제안한다. 이를 위하여, 실제위치, 무제약 추정위치, 제약 추정위치의 세가지 위치 개념을 정형적으로 정의하고, 다항식을 이용하여 이들 위치를 추정하는 체계적인 방법을 제안한다.

• Proceedings of the KIPE Conference
• /
• 2010.07a
• /
• pp.418-419
• /
• 2010

본 논문에서는 스크리닝에 기반한 리튬이온 배터리 팩의 state of charge (SOC) 추정방법을 연구하였다. 전기화학적 특성이 서로 유사한 셀들을 미리 선별하는 스크리닝 방법을 통해 직렬, 병렬, 직/병렬팩이 구성될 때, 이러한 팩의 전기화학적 등가회로 모델은 단위 셀 대비 일정한 경향성을 보이는 용량, open circuit voltage (OCV) 등의 파라미터 정보를 토대로 기존 단위 셀 모델과 동일한 모델 구축이 가능하다. 이를 통하여 extended kalman filter (EKF)를 이용한 배터리 팩의 SOC 추정이 가능함을 보인다.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.507-508
• /
• 2007

확률적(stochastic) RFID 충돌방지 알고리즘은 둘 이상의 태그가 리더기의 인식범위 내에 있을 경우 태그들이 동시에 리더기의 질의에 응답함으로서 발생하는 충돌을 확률적으로 감소시켜, 정확하고 빠르게 다수의 태그를 인식하기 위한 알고리즘이다. 본 논문에서는 확률적 충돌방지 알고리즘 중 하나인 dynamic framed ALOHA를 기반으로 새로운 태그 수 추정 방법을 이용한 RFID 충돌 방지 알고리즘을 제안하였다.

• Proceedings of the KIPE Conference
• /
• 2019.07a
• /
• pp.47-49
• /
• 2019

본 논문은 노화로 인하여 감소하는 전기자동차용 배터리의 전류 용량을 실시간으로 추정하는 SOH (State-of-health) 알고리즘을 제안한다. 제안하는 알고리즘은 노화에 따른 OCV (Open circuit voltage) 곡선의 변화 경향을 분석하고, 저주파 통과 필터를 이용하여 추정된 OCV를 기반으로 전류 용량 및 SOH를 산출한다. 알고리즘을 검증하기 위하여 전기자동차용 배터리를 이용한 실험 및 시뮬레이션을 진행한다.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.460-464
• /
• 2019

번역 품질 예측은 기계번역 시스템이 생성한 번역문의 품질을 정답 번역문을 참고하지 않고 예측하는 과정으로, 번역문의 사후 교정을 위한 번역 오류 검출의 역할을 담당하는 중요한 연구이다. 본 논문은 문장 수준의 번역 품질 예측 문제를 HTER 구간의 분류 문제로 간주하여, 번역 품질 말뭉치의 HTER 분포 불균형으로 인한 성능 제약을 완화하기 위해 인조 사후 교정 말뭉치를 이용하는 방법을 제안하였다. 결과적으로 HTER 분포를 균등하게 조정한 학습 말뭉치가 그렇지 않은 쪽에 비해 번역 품질 예측에 더 효과적인 것을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.4
• /
• pp.36-42
• /
• 1996

In this paper, we have proposed the robust estimation of HMM parameters which is based on CDDN(codeword dependent distance normalization)and codeword weighting by distance. The proposed method has used a distance normalization based on the characteristics of a codeword dependent distribution and have computed fuzzy contributions of codeword to a input vector with a fuzzy objective function. From experimental results, we have shown the effectiveness of the proposed method in that the correction rate of the proposed method is improved 4.5% over the conventional FVQ based method. Especially, the application of distance weighting to smoothing of output probability is improved the performance of 2.5% compared to distance based codeword weighting.

• Journal of Internet Computing and Services
• /
• v.19 no.6
• /
• pp.41-51
• /
• 2018

Recently, in the field of video surveillance, deep learning based learning method is applied to intelligent video surveillance system, and various events such as crime, fire, and abnormal phenomenon can be robustly detected. However, since occlusion occurs due to the loss of 3d information generated by projecting the 3d real-world in 2d image, it is need to consider the occlusion problem in order to accurately detect the object and to estimate the pose. Therefore, in this paper, we detect moving objects by solving the occlusion problem of object detection process by adding depth information to existing RGB information. Then, using the convolution neural network in the detected region, the positions of the 14 keypoints of the human joint region can be predicted. Finally, in order to solve the self-occlusion problem occurring in the pose estimation process, the method for 3d human pose estimation is described by extending the range of estimation to the 3d space using the predicted result of 2d keypoint and the deep neural network. In the future, the result of 2d and 3d pose estimation of this research can be used as easy data for future human behavior recognition and contribute to the development of industrial technology.