• 한국통신학회논문지
• /
• 제26권11C호
• /
• pp.75-84
• /
• 2001

본 논문에서는 신경망을 이용한 실시간 고장 검출 및 진단(FDD : Fault Detection and Diagnosis) 시스템을 제안한다. 제안된 시스템은 공조 시스템(FDD : Air Handling Unit)에서 발생 가능한 여러 고장들을 검출하고 진단할 수 있다. 고장 검출 및 진단 기법으로 3층 구조의 전방향(feed-forward) 신경망을 사용하였고, 여기에 사용된 학습 방법은 역전파(back-propagation) 학습 알고리즘이다. 공조 시스템에 적용된 실시간 고장 검출 및 진단 시스템은 비주얼 C++와 비주얼 베이직을 사용하여 구현하였다. 제안된 고장 검출 및 진단 시스템을 실제 운전 중인 공조 시스템에 적용하여 실험하였고, 정확한 고장 검출 및 진단이 수행됨을 실험 결과로서 입증하였다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.615-618
• /
• 2019

Visual saliency detection is an important part in various vision-based applications. There are a myriad of techniques for saliency detection in color images. However, the number of methods for saliency detection in infrared images is inadequate. In this paper, we introduce a simple approach for pedestrian identification in infrared images using saliency. The input image is thresholded into several Boolean maps, an initial saliency map is then calculated as a weighted sum of created Boolean maps. The initial map is further refined by using thresholding, morphology operation, and Gaussian filter to produce the final, high-quality saliency map. The experiment showed that the proposed method produced high performance results when applied to real-life data.

• ETRI Journal
• /
• 제41권4호
• /
• pp.483-493
• /
• 2019

Considering the high dimensions of video sequences, it is often challenging to acquire a sufficient dataset to train the tracking models. From this perspective, we propose to revisit the idea of hand-crafted feature learning to avoid such a requirement from a dataset. The proposed tracking approach is composed of two phases, detection and tracking, according to how severely the appearance of a target changes. The detection phase addresses severe and rapid variations by learning a new appearance model that classifies the pixels into foreground (or target) and background. We further combine the raw pixel features of the color intensity and spatial location with convolutional feature activations for robust target representation. The tracking phase tracks a target by searching for frame regions where the best pixel-level agreement to the model learned from the detection phase is achieved. Our two-phase approach results in efficient and accurate tracking, outperforming recent methods in various challenging cases of target appearance changes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권3호
• /
• pp.1159-1181
• /
• 2016

This study introduces an image-based 2D-to-3D conversion system that provides significant stereoscopic visual effects for humans. The linear and atmospheric perspective cues that compensate each other are employed to estimate depth information. Rather than retrieving a precise depth value for pixels from the depth cues, a direction angle of the image is estimated and then the depth gradient, in accordance with the direction angle, is integrated with superpixels to obtain the depth map. However, stereoscopic effects of synthesized views obtained from this depth map are limited and dissatisfy viewers. To obtain impressive visual effects, the viewer's main focus is considered, and thus salient object detection is performed to explore the significance region for visual attention. Then, the depth map is refined by locally modifying the depth values within the significance region. The refinement process not only maintains global depth consistency by correcting non-uniform depth values but also enhances the visual stereoscopic effect. Experimental results show that in subjective evaluation, the subjectively evaluated degree of satisfaction with the proposed method is approximately 7% greater than both existing commercial conversion software and state-of-the-art approach.

• Journal of the Optical Society of Korea
• /
• 제16권2호
• /
• pp.145-150
• /
• 2012

We present a display-based visual stimulator for psychophysical and electrophysiological visual sensitivity measurements. The stimulator offers various psychophysical visual stimuli and transfers the signals from external devices along with the stimulation signals to an electrophysiological recorder. As an experimental demonstration, we perform a visual sensitivity experiment in the mesopic vision range by using the display-based stimulator. The intensity of the steady-state visual evoked potential is observed to correlate with the luminance of the flickering visual stimulation. For the psychophysically determined detection thresholds, we determine the mesopic luminance, showing agreement with the perceived brightness within the uncertainty of the luminance measurement.

• 전자공학회논문지
• /
• 제51권5호
• /
• pp.137-151
• /
• 2014

본 논문에서는 일반적인 자연 영상에서 관심 객체를 자동으로 검출하기 위한 방법을 제안한다. 영상에서의 관심 객체는 사람에 따라서 주관적으로 판단되며, 일반적으로 사람의 시각은 관심 객체에 초점이 맞춰지게 된다. 관심 객체의 자동 검출을 위한 첫 번째 단계로서 사람의 시각 인지기반의 돌출 맵을 이용하여 관심 객체의 후보 영역을 검출한다. 검출된 후보영역은 객체에 대한 대략적인 위치 정보를 가지고 있지만 관심 객체를 정확하게 분할하지 못하는 문제점이 존재한다. 따라서 두 번째 단계에서 영상의 색상과 에지를 고려한 그래프 기반의 영상 분할 기법과 객체 영역의 세선화(skeletonization)를 결합함으로써 정확한 객체 영역을 자동으로 검출한다. 본 논문에서는 제안하는 방법과 기존 방법들의 성능을 비교하기 위해서 정확률(precision), 재현율(recall) 그리고 정밀도(accuracy)를 계산하였다. 그 결과, 제안하는 방법은 미 검출(under detection) 및 과검출(over detection)에 대한 문제점을 줄임으로써 기존 방법보다 더 향상된 결과를 보인다.

• Journal of Microbiology and Biotechnology
• /
• 제31권5호
• /
• pp.705-709
• /
• 2021

Porphyromonas gingivalis (P. gingivalis) is a major bacterial pathogen that causes periodontitis, a chronic inflammatory disease of tissues around the teeth. Periodontitis is known to be related to other diseases, such as oral cancer, Alzheimer's disease, and rheumatism. Thus, a precise and sensitive test to detect P. gingivalis is necessary for the early diagnosis of periodontitis. The objective of this study was to optimize a rapid visual detection system for P. gingivalis. First, we performed a visual membrane immunoassay using 3,3',5,5'-tetramethylbenzidine (TMB; blue) and coating and detection antibodies that could bind to the host laboratory strain, ATCC 33277. Antibodies against the P. gingivalis surface adhesion molecules RgpB (arginine proteinase) and Kgp (lysine proteinase) were determined to be the most specific coating and detection antibodies, respectively. Using these two selected antibodies, the streptavidin-horseradish peroxidase (HRP) reaction was performed using a nitrocellulose membrane and visualized with a detection range of 10³-10⁵ bacterial cells/ml following incubation for 15 min. These selected conditions were applied to test other oral bacteria, and the results showed that P. gingivalis could be detected without cross-reactivity to other bacteria, including Streptococcus mutans and Escherichia fergusonii. Furthermore, three clinical strains of P. gingivalis, KCOM 2880, KCOM 2803, and KCOM 3190, were also recognized using this optimized enzyme immunoassay (EIA) system. To conclude, we established optimized conditions for P. gingivalis detection with specificity, accuracy, and sensitivity. These results could be utilized to manufacture economical and rapid detection kits for P. gingivalis.

• 대한인간공학회지
• /
• 제36권3호
• /
• pp.255-265
• /
• 2017

Objective: This study aims to survey visual search performance models to assess and predict individual's visual tasks in everyday life and industrial sites. Background: Visual search is one of the most frequently performed and critical activities in everyday life and works. Visual search performance models are needed when designing or assessing the visual tasks. Method: This study was mainly based on survey of literatures related to ergonomics relevant journals and web surfing. In the survey, the keywords of visual search, visual search performance, visual search model, etc. were used. Results: On the basis of the purposes, developing methods and results of the models, this study categorized visual search performance models into six groups: probability-based models, SATO models, visual lobe-based models, computer vision models, neutral network-based models and detection time models. Major models by the categories were presented with their advantages and disadvantages. More models adopted the accuracy among two factors of accuracy and speed characterizing visual tasks as dependent variables. Conclusion: This study reviewed and summarized various visual search performance models. Application: The results would be used as a reference or tool when assessing the visual tasks.

• 대한치과의사협회지
• /
• 제49권8호
• /
• pp.461-471
• /
• 2011

The detection of carious lesions is a key point to apply appropriate preventive measures or operative treatment of dental caries. A laser fluorescence device DIAGNOdent$^{(R)}$ (KaVo, Biberach, Germany) has also been shown to be of additional clinical value in the detection of initial caries. This report focus on the DIAGNOdent$^{(R)}$ for caries detection. DIAGNOdent$^{(R)}$ irradiate visible red light at a wavelength of 655 nm to elicit near-infrared fluorescence from caries lesion. This device is known as a reproducible method for caries detection, with good sensitivity and specificity especially for caries detection on occlusal and accessible smooth surfaces. DIAGNOdent$^{(R)}$ tended to be more sensitive method of detecting occlusal dentinal caries, however, showed more false-positive diagnoses than the visual inspection. So Clinician should not use the device as a clinician's primary diagnostic method and it is recommended that the device should be used in the decision-making process in relation to the diagnosis of caries as a second opinion in cases of doubt after visual inspection. The trend of modern dentistry would be a preventive approach rather than invasive treatment of the disease. This is possible only with early detection and respective preventive measures, DIAGNOdent$^{(R)}$ can help the changes.

• 전자공학회논문지
• /
• 제51권6호
• /
• pp.132-142
• /
• 2014

근래에 고령운전자의 증가와 다양한 차량용 멀티미디어 기기의 등장으로 운전 중 운전자의 시각적 주의 결핍 및 분산되어 교통신호등 오인식으로 인해 교통사고가 증가하고 있는 상황이다. 이를 보완하기 위해 일반적인 교통신호등 검출연구들은 색상 임계치, 템플릿 매칭, 학습기 기반 등의 방안이 제시 되었으나 색상 임계치의 경우 시내 도로와 같이 복잡한 배경과 주위 환경변화에 강인하지 못하고, 야간 시간대의 경우 템플릿 및 학습기 기반의 검출방안의 경우 그 인식도가 떨어지는 문제점이 존재한다. 따라서 제안한 방안에서는 교통신호등의 구조적인 형태 정보(모양, 밝기, 대비, 색상 등)을 기반 한 시각적 주의 영역과 spot-lights 영역 검출을 통해 복잡한 시내 도로 환경에서 교통신호등을 검출하는 방안을 제안한다. 교통신호등은 운전자의 시인성을 높일 수 있는 위치에 설치되고 또한 구조적인 고유한 형태와 색상을 지니고 있는 특징들을 이용하여 교통신호등을 검출한다. 제안한 방안에서는 입력된 칼라영상에서 특징정보들 간의 다차원 가우시안 파라미드 영상들을 생성하고 각 영상들 간의 대비차이 계산하여 현저하게 두드러진 영역들을 검출하고, 밝기 영상에서 주위 영역과 현저하게 밝은 spot-lights 영역들을 검출한다. 그리고 검출된 두 영역들의 모양과 색상 분석을 통해 교통신호등을 검출한다. 제안한 방법을 다양한 시간대와 시내 도로에서 실험한 결과, 교통신호등 검출률은 83.2%이고 프레임 당 처리 시간은 0.68초이다. 이것을 통해 사후판독 기능이 차량 영상기록장치에 결합한 안전운전 지원시스템으로 제안한 방안이 유용하게 적용될 수 있음을 알 수 있다.