• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.44-49
• /
• 2016

This paper proposed the method to improve performance of a pixel, which has low accuracy, by applying image segmentation methods based on color and multi-threshold of brightness. Stereo matching is the process to find the corresponding point on the right image with the point on the left image. For this process, distance(depth) information in stereo images is calculated. However, in the case of a region which has textureless, stereo matching has low accuracy and bad pixels occur on the disparity map. In the proposed method, the relationship between adjacent pixels is considered for compensating bad pixels. Generally, the object has similar color and brightness. Therefore, by considering the relationship between regions based on segmented regions by means of color and multi-threshold of brightness respectively, the region which is considered as parts of same object is re-segmented. According to relationship information of segmented sets of pixels, bad pixels in the disparity map are compensated efficiently. By applying the proposed method, the results show a decrease of nearly 28% in the number of bad pixels of the image applied the method which is established.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.630-637
• /
• 2003

This paper proposed a new watermarking algorithm using chaotic sequence instead of conventional M-sequence for protecting copyright to the author. Robustness and security is very important for watermarking process. We use multi-threshold value according to the human visual system for improving robustness of watermarking to each subband images coefficient differently after wavelet transform. And then, we embedded watermark image to original image by multi-watermark weights which are made by random sequence generator. We detect watermark image from the difference data which is made from each wavelet subband images. We also simulate the efficiency from the various possible attacks. Chaotic sequence is better than M-sequence, because the one is very easy to make sequence and the chaotic sequence is changed easy according to the initial value. So, the chaotic sequence has the better security than the conventional M-sequence.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.834-838
• /
• 1992

Tracking performance depends on the quantity of the measurement data. In the Kalman-Bucy filter and other trackers, this dependence is well understood in terms of the measurement noise covariance matrix, which specifies the uncertainty in the value of measurement inputs. In this paper, we derived approximated error covariance matrix to evaluate the dependence of target detection probability and false alarm probability in the presence of uncertainty of measurement origin.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.580-582
• /
• 2001

본 논문에서는 인간 시각 시스템 모델을 기반으로 디지털 멀티미디어 영상 정보의 소유권을 보호하기 위하여 시각적으로 보이지 않는 강건한 워터마크를 내장하는 알고리즘을 제안한다. 알고리즘을 제안한다. 입력영상을 웨이블릿변환을 사용하여 3단계 분해한 다음 각 부대역에 대해서 적응적인 다중 임계값을 적용하여, 보다 강건한 워터마킹삽입 알고리즘을 제안한다. 최저주파수 LL3영역을 제외한 각 부대역은 영상의 정보가 다소 적으므로, 삽입 후 영상정보에 대해 손실을 줄일 수 있다. 실험결과, 본 논문에서 제안한 방법은 영상의 화질이 우수했으며, 외부의 공격에도 강인성이 뛰어 나고, 검출된 워터마크의 시각적인 높음을 알 수 있다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 2004.11a
• /
• pp.331-331
• /
• 2004

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.536-543
• /
• 2023

Speaker diarization, which labels for "who spoken when?" in speech with multiple speakers, has been studied on a deep neural network-based end-to-end method for labeling on speech overlap and optimization of speaker diarization models. Most deep neural network-based end-to-end speaker diarization systems perform multi-label classification problem that predicts the labels of all speakers spoken in each frame of speech. However, the performance of the multi-label-based model varies greatly depending on what the threshold is set to. In this paper, it is studied a speaker diarization system using single-label classification so that speaker diarization can be performed without thresholds. The proposed model estimate labels from the output of the model by converting speaker labels into a single label. To consider speaker label permutations in the training, the proposed model is used a combination of Permutation Invariant Training (PIT) loss and cross-entropy loss. In addition, how to add the residual connection structures to model is studied for effective learning of speaker diarization models with deep structures. The experiment used the Librispech database to generate and use simulated noise data for two speakers. When compared with the proposed method and baseline model using the Diarization Error Rate (DER) performance the proposed method can be labeling without threshold, and it has improved performance by about 20.7 %.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12B
• /
• pp.1703-1711
• /
• 2001

광시스템에서 발생할 수 있는 비선형 현상 중 하나인 유도 브릴루앙 산란은 낮은 입력 파워 레벨에서도 발생할 수 있기 때문에 광전송 시스템에 큰 영향을 주는 현상이다. 그러므로 고출력의 신호를 광섬유에 입사시켜 광전송 시스템의 전송 거리를 길게 하기 위해서는 광섬유에서 발생하는 유도 브릴루앙 산란에 대한 고려가 필요하다. 특히 현재 광통신에 사용되고 있는 파장 분할 다중방식(WDM) 광전송 시스템에서는 채널 간격이 좁으므로 유도 브릴루앙 산란의 영향을 고려해야만 한다. 브릴루앙 이득 스펙트럼은 브릴루앙 주파수 천이, 부릴루앙 선폭과 이득계수에 대한 정보뿐만 아니라 브릴루앙 임계값에 대한 정보를 포함한다. 이러한 유도 브릴루앙 산란 신호를 1550nm 파장대에서 실험적으로 확인하였으며 실험으로 관측한 SBS 신호를 이론적으로 계산된 값과 비교하였다. 실험으로 구한 신호 주파수는 10.8825GHz로서 이론상의 값 10.9GHz와 일치하였으며 브릴루앙 이득 스펙트럼을 측정한 결과 1.5436 $\times$ $10^{-ll}$m/w의 브릴루앙 이득 계수 $g_{0}$을 얻었다.다.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.344-346
• /
• 2022

본 논문에서 거푸집의 가장취약 부분인 접합부위에 로드센서를 부착하여 실시간 콘크리트 측압을 측정 할 수 있으며, 관리자는 모니터링을 통하여 확인 할 수 있도록 하며 LORA의 저전력 장거리 통신망을 사용하는 디바이스를 개발하여 로드센서에 측정한 값을 데이터변경, 웹 기반의 클라우드 서비스로 발송하여 PC 및 Mobile로 확인 할 수 있는 시스템을 구축하였다. 여러가지 센서로부터 데이터를 수신하여 모바일로 송신해 주는 무선송수신기의 개발을 원하고 있으며, 하중센서, 경사도센서, 풍향센서 등 다중 데이터값을 수신할 수 있어야 한다. 이렇게 구성된 센서와 데이터의 수신을 통해서 콘크리트 타설시 발생하는 측압을 측정하고 공사기간 동안 별도의 전원 공급 없이 작동이 유지될 수 있는 시스템을 구축하였다. 수요자가 Application과 호환이 이루어져야 하며 또한 MEMS센서를 이용하여 상태를 모니터링 하고 임계값을 지정하여 이상 신호 발생시 위험상황에 대해서 인공지능기법을 이용하여 관리자에게 알림을 주어 효과적으로 사용할 수 있는 시스템을 개발하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.5A
• /
• pp.267-275
• /
• 2003

In UMTS terminal modem uses 3 step search procedure for initial cell search, which comprises 1) slot synchronization, 2) code group identification and frame synchronization, and 3) scrambling-code identification. The performance of initial cell search procedure depends on search parameters like observation time and threshold. The purpose of this paper is to get the optimal observation time and threshold of each step for minimum mean acquisition time. In this paper we induce mean detection time of each step and mean acquisition timefrom the model of 3 step search procedure using state diagram. Also we propose initial cell search algorithm which utilize window search method against initial oscillator error, and select an appropriate observation time and threshold of each step by the analysis of simulation and induced result. It is shown that the mean acquisition time in multipath fading channel can be shorter than 500ms by using the determined observation time and threshold of each step.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.12B
• /
• pp.1083-1096
• /
• 2008

This paper proposes an energy-aware path management scheme, so-called the TBP(Threshold based Back-Pressure) algorithm, which is designed for lifetime extension of the energy-constrained wireless sensor networks. With the goal of fair energy consumptions, we extensively utilize the available paths between the source and the sink nodes. The traffic distribution feature of the TBP algorithm operates in two scales; the local and the whole routing area. The threshold and the back-pressure signal are introduced for implementing those operations. It is noticeable that the TBP algorithm maintains the scalability by defining both the threshold and the back-pressure signal to have their meanings locally confined to one hop only. Throughout several experiments, we observe that the TBP algorithm enhances the network-wide energy distribution. which implies the extension of the network lifetime. Additionally, both the delay and the throughput outcomes show remarkable improvements. This shows that the energy-aware path control scheme holds the effects of the congestion control.