• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.1 no.1
• /
• pp.10-16
• /
• 2002

In this paper, a novel algorithm for segmentation of moving multiple vehicles in video sequences using logic operations is proposed. For the case of multiple vehicles in a scene, the proposed algorithm begins with a robust double-edge image derived from the difference between two successive frames using exclusive OR operation. After extracting only the edges of moving multiple vehicles using Laplacian filter, AND operation and dilation operation, the image is segmented into moving multiple vehicle image. The features of moving vehicles can be directly extracted from the segmented images. The proposed algorithm has no the two preprocessing steps, so it can reduce noises which are norm at in preprocessing of the original images. The algorithm is more simplified using logic operations. The proposed algorithm is evaluated on an outdoor video sequence with moving multiple vehicles in 90,000 frames of 30fps by a low-end video camera and produces promising results.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.2
• /
• pp.145-156
• /
• 2020

The climate change occurring all over the world increases the risk, specially in urban area, Accordingly, rainwater pumping station expansion is required than before. In order to increase the efficiency of the rainwater pumping station, the analysis of flow characteristics in the pump sump is needed for vortex control. Many efforts have been made to illuminate the vortex behavior using PIV, but any reliable results have not been obtained yet, because of the limitations in image capturing and dependency of measured velocity values on the interrogation area and time interval used for velocity calculation. In this study, therefore, experiments were carried out to find out the limitation of PIV and estimate the validation of the velocity values associated with the analysis parameters such as interrogation area, time interval, grid size. For the experimental condition used in this study, the limitation of PIV and the effects of parameters on the velocity estimation are presented.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.9-15
• /
• 2019

The purpose of present study is to assess the maximum width of the surface cracks using the histogram analysis of image processing techniques in concrete structures. For this purpose, the concrete crack image is acquired by the camera. The image is Grayscale coded and Binary coded. After Binary coded image is Dilate and Erode coded, the image is then recognized as separated objects by applying Labeling techniques. Over time, dust and stains may occur naturally on the surface of concrete. The crack image of concrete may include shadows and reflections by lighting depending on a surrounding conditions. In general, concrete cracks occur in a continuous pattern and noise of image appears in the form of shot noises. Bilateral Blurring and Adaptive Threshold apply to the Grayscale image to eliminate these effects. The remaining noises are removed by the object area ratio to the Labeled area. The maximum numbers of pixels and its positions in the crack objects without noises are calculated in x-direction and y-direction by Histogram analysis. The widths of the crack are estimated by trigonometric ratio at the positions of the pixels maximum numbers for the Labeled objects. Finally, the maximum crack width estimated by the proposed method is compared to the crack width measured with the crack gauge. The proposed method by the present study may increase the reliability for the estimation of maximum crack width using image processing techniques in concrete surface images.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.79-88
• /
• 2021

COVID-19 is putting the entire performance industry in a dire situation. One of the approaches to overcome this crisis is contactless performance business using video media. But, these contactless performance videos are now found to have their own issues. First, with the increasing demands for these videos, the need for higher-quality video products is also increasing. However, there are many organizations that cannot afford such an investment. Second, it is not possible to have the same unique experience of a live performance with the videos. 360-degree VR performance videos are now gaining attention as an alternative to cope with this issue. As such, the researcher reviewed the production of 360 VR performance videos in general based on the cases of the play and a children's story concert As a result, the researcher could confirm the three benefits of simulated 'live experience through a sense of reality', 'convenience of filming' and 'continuity of acting'. Also, the issues related to this approach including 'Lack of professional filming companies', 'Expensive viewing equipment', 'Absence of Platform' and 'Limitations of Camera Technology', among others have been identified, etc. Based on these findings, the researcher could propose strategies for improvement in order to utilize 360-degree VR performance videos.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.1
• /
• pp.123-128
• /
• 2015

In this study, experimented how to increase corresponding points which are obtained through stereo matching for dense 3D reconstruction. After extracting a snapshot image from the images acquired through stereo CCTVs, the matching points obtained using the SIFT matching and RANSAC procedure were gradually overlapped. In conclusion, it was confirmed that as images are overlapped, the number of matching points continues to grow.

• Journal of the Korean Society of Radiology
• /
• v.83 no.3
• /
• pp.453-472
• /
• 2022

Over the past decades, the immense clinical need for early detection methods and treatments for dementia has become a priority worldwide. The advances in PET biomarkers play increasingly important roles in understanding disease mechanisms by demonstrating the protein pathology underlying dementia in the brain. Amyloid-β and tau deposition in PET images are now key diagnostic biomarkers for the Alzheimer's disease continuum. The inclusion of biomarkers in the diagnostic criteria has achieved a paradigm shift in facilitating early differential diagnosis, predicting disease prognosis, and influencing clinical management. Furthermore, in vivo images showing pathology could become prognostic as well as surrogate biomarkers in therapeutic trials. In this review, we focus on recent developments in radiotracers for amyloid-β and tau PET imaging in Alzheimer's disease and other neurodegenerative diseases. Further, we introduce their potential application as future perspectives.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.670-672
• /
• 2000

본 논문에서는 단일광자방출 전산화단층촬영영상 (SPECT)을 이용하여 좌심실의 내.외벽의 운동을 분리하여 추적하는 방법을 제시한다. 좌심실의 운동은 크게 평행이동, 회전이동, 비강체 변형으로 나뉘어 분석된다. 운동 추적을 위해 사용된 역동적 변형 솔리드는 물체중심 변동 좌표계로써 특징점들의 모드형태벡터를 사용하고, 좌심실 역동성을 유한요소방법에 의해 시뮬레이션한다. 또한, 변형 모델에 대해 묵시적으로 표준화된 parameterization을 하지 않고, 의료영상으로부터 얻은 자료값을 직접 이용하기 위해 노드간 보간함수로써 3차원 가우시안 함수를 사용한다. 그리하여 보다 자연스러운 방식으로 연속적으로 변화하는 좌심실의 운동을 추적할 수 있다. 이러한 분리된 내.외벽 운동 분석은 운동 기능에 이상이 있는 심질환 분석을 보다 효과적으로 도울 수 있다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.43-45
• /
• 2012

본 논문은 목자판과 수면이 포함된 시차가 있는 연속적인 두 영상을 이용하여 수면위치를 탐색하는 방법과 그 적용성을 평가한 결과를 기술한다. 수위표 상단으로부터 특정 크기의 직사각형 검사영역을 설정하고 짧은 시차를 가진 두 영상의 동일한 위치의 검사영역에 대해 상관계수를 산정한다. 이렇게 함으로써 물의 흐름으로 픽셀 농도가 변화하는 수역과 픽셀 농도가 고정되어 있는 육역을 구분한다. 제안한 기법을 검증하기 위해 실험실에서 촬영한 사진을 분석하였다. 검사영역의 크기에 따라 상관계수 특성이 달라짐을 확인하였으며, 검사영역이 수위표 전체 폭에 걸쳐 있는 경우에 상관계수에 따른 수면특성이 뚜렷이 나타나 제안된 기법이 수면을 찾는데 활용될 수 있음을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.202-205
• /
• 2011

본 논문은 DNA 특성분석 기능을 수행하는 전기영동 장치와 분석결과 해석 기능을 수행하는 젤닥 장치를 통합한 장치를 제안하였다. 이들 두 기능을 독립적으로 수행하는 기존의 시스템은 바이오 전문가의 중간 개입 작업이 필요하며 경험치에 의존하는 검사의 부적황성, 높은 오염가능성, 긴 검사시간 등의 한계점을 가지고 있다. 기존 장비에서 독립적으로 수행하던 두 기능을 동시에 수행하도록 하여, 현 시스템의 한계점들을 개선 할 수 있는 장치를 제안하고 구현하였다. 한편 기존에는 완료된 최종 결과 영상 한 장만을 획득 할 수 있었던 것에 반해 특성분석 중에 결과 영상을 실시간으로 모니터링할 수 있어서 DNA 특성 분석의 성공 여부를 조기에 판단할 수 있었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.10a
• /
• pp.511-515
• /
• 1998

본 논문에서는 전경과 배경을 동시에 고려하는 이동 물체 추적 기법을 제안한다. 본 논문에서 제안하는 이동 물체 추적 기법은 카메라가 고정되지 않은 동적인 환경에서 연속적으로 촬영된 동영상으로부터 배경과 전경을 분리한 후 배경으로부터는 카메라의 동작을, 그리고 전경으로부터는 이동 물체를 추적한다. 배경에서는 영상의 움직임을 나타내는 동작 벡터를 추출하여 2차원 파라미터 동작 모델인 어파인 동작 모델에 적합시키고, 회귀분석법을 통해 어파인 동작 모델을 구성하는 파라미터를 추출하여 분석함으로써 다양한 카메라의 동작을 구한다. 전경에서는 칼라 정보를 이용하여 물체들의 모델을 생성하고 매 시점마다 모델을 수정하면서 이동 물체를 추적한다. 본 논문에서는 카메라의 동작 및 이동 물체의 추적 시 예측 알고리즘인 칼만 필터를 활용함으로써 보다 효율적이고 강건한 추적이 가능하다. 또한, 배경에서 추출된 카메라의 동작 정보를 전경에서 추출하는 이동 물체의 이동궤적 정보 계산 시 활용함으로써 보다 정확하게 장면을 분석할 수 있다.