• Spatial Information Research
• /
• v.19 no.1
• /
• pp.51-59
• /
• 2011

We produced true ortho images after interpolating occlusion areas and relief displacement of building as well as producing ortho-images to use backward image of ADS which is a aerial digital camera of line type. Also, I was able to produce high quality ortho-images using a small mount of Ground Control Points(GCP) relatively to compare to frame type camera from the evaluation of horizontal position accuracy using ground check points, photo control points for the verification of ortho-images and true-ortho images. Also, I was able to verify the effectiveness in interpolating occlusion areas cause the length overlap was 100% when producing true-ortho images of line type camera.

• Journal of Cadastre & Land InformatiX
• /
• v.50 no.2
• /
• pp.69-79
• /
• 2020

TRecently, smart cities that solve various problems in cities based on IoT technology are in the spotlight. In particular, cases of BIM application for smooth management of construction and maintenance are increasing, and spatial information is converted into 3D data through convergence technology and used for safety diagnosis. The purpose of this study is to create and combine point clouds of a multi-story building by using a ground laser scanner and a handheld LiDAR SLAM among UAV and LiDAR equipment, supplementing the Occluded area and disadvantages of each technology, examine the effectiveness of indoor and outdoor reverse design by observing shape reproduction and accuracy. As a result of the review, it was confirmed that the coordinate accuracy of the data was improved by creating and combining the indoor and outdoor point clouds of the multi-story building using three technologies. In particular, by supplementing the shortcomings of each technology, the completeness of the shape reproduction of the building was improved, the Occluded area and boundary were clearly distinguished, and the effectiveness of reverse engineering was verified.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.06a
• /
• pp.202-205
• /
• 2008

건물이 밀집된 도심지역을 촬영한 두 시기 항공영상에 화소기반 변화탐지 기법인 영상대차(Image Differencing), 영상중첩 분석(Image Overlay)기법을 적용하여 넓은 대도심지역의 효율적인 변화탐지 가능성을 살펴보았다. 영상대차(Image Differencing) 기법은 알고리즘이 간단하고 정량적인 분석이 가능한 결과를 얻을 수 있다는 장점이 있으나 고층건물밀집지역을 보여주고 있는 고해상도 항공영상의 적용과정에서는 폐색영역, 그림자 등으로 인해 정확한 변화탐지 결과를 보여주지 못했다. 영상중첩 분석(Image Overlay)기법은 한 번에 두 개 또는 세 개의 영상을 비교 분석할 수 있다는 장점이 있으나 직관적인 분석만을 제공하고 정량적인 분석이 불가능하였다. 현재의 화소기반 영상변화탐지 기술수준으로는 고해상도 공간영상에 대한 신뢰도 높은 변화탐지 분석결과를 얻을 수 없다는 것을 확인하였다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.15 no.4
• /
• pp.401-413
• /
• 2013

Slurry shield tunnelling ensures stability by pressurizing the tunnel face with the slurry contained in the chamber. It resists water and earth pressure in order to prevent the failure in the tunnel face during tunnel excavation. If the ground is relatively coarse, slurry can not clog the tunnel face and excessive slurry infiltration will occur. In this case chemical compounds or additives should be added to the slurry in order to improve the clogging phenomena at the tunnel face. In this study, the effect of the carbon dioxide gas as an additive to the slurry instead of chemical compounds on the capability of enhancing the clogging in the tunnel face is investigated. Bubbles arising from the carbonate-added slurry are trapped in the soil voids enhancing the clogging capability. This effect is studied in this paper by performing laboratory model tests simulating in-situ conditions, and by adopting the fine particle clogging theory. Tunnel face stability analysis was also performed and it was found that the effective size ($D_{10}$) of soils which can guarantee tunnel stability utilizing the carbonate-added slurry increased from 1.0 mm up to 2.6 mm. Moreover, Stability analysis showed that the tunnel face is stable if the ${\lambda}$(deposition coefficient) value is greater than $0.007sec^{-1}$.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.21 no.2
• /
• pp.243-256
• /
• 2019

Formation of filter cake with little slurry penetration into the tunnel face ground is an essential factor to successfully apply the slurry shield tunnel boring machine (TBM) for tunnelling work. However, when the bentonite slurry is in contact with seawater, it is not easy to guarantee the filter cake formation due to decrease of the swelling volume and viscosity of the slurry. In this study, in order to evaluate the effect of the seawater on the applicability of the slurry shield TBM method, the slurry injection tests were carried out with the variation of seawater percentage contained in the slurry samples as well as the variation of soil types. And then, the effect of these two factors on the slurry clogging phenomena was theoretically and experimentally figure out. As a result, it was found that the value of the slurry clogging criteria (SCC) indicating the applicability of the slurry shield TBM significantly decreases up to 67% as the percentage of seawater increases from 0% up to 20%. In addition, it was found to be necessary to take into account both the characteristics of slurry and soil types together when judging the applicability of the slurry shield TBM method by assessing the slurry penetration characteristics that will occur during tunnelling work.

• 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.

• Smart Media Journal
• /
• v.2 no.4
• /
• pp.27-33
• /
• 2013

Multi-view video system provides both realistic 3D feelings and free-view navigation. But it is hard to transmit too huge data, so we send only two or three view images and generate intermediate view image using depth information. In this paper, we propose high quality multi-view image generation method from stereoscopic images. Since the stereo matching method does not provide accurate disparity values for all the pixels, especially at the occlusion area, we propose an occlusion handling method using the background pixels at first. We also apply a joint bilateral filtering to enhance the disparity map at the object boundary since it can affect the quality of synthesized images significantly. Finally, we can generate virtual view images at intermediate view positions using confidence map to reduce bad pixel and hole's error. Experimental results show the proposed method performs better than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.12
• /
• pp.2146-2152
• /
• 2008

In In this paper, we proposed a new JPEG2000 codec using multiresolution-based rendering (MRBR) technique for video compression of 3-dimensional digital cinema. We introduced discrete wavelet transform (DWT) for stereoscopic image and stereo matching technique in the wavelet domain. The disparity was extracted using stereo matching and transmitted with the reference (left) image. Since the generated right image was degraded by the occlusion lesion, the residual image which is generated from difference between the original right image and the generated one was transmitted at the same tine. The disparity data was extracted using the dynamic programming method in the disparity domain. There is high correlation between the higher and lower subbands. Therefore we decreased the calculation amount and enhanced accuracy by restricting the search window and applying the disparity information generated from higher subband.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.23-26
• /
• 2020

본 논문에서는 CCTV를 통해 얻은 영상에서 얼굴을 인식하여 자동으로 출석 여부를 체크하는 시스템을 소개한다. 이 시스템은 CNN을 바탕으로 RetinaFace 모델을 사용하여 얼굴을 탐지하고, 탐지된 얼굴을 ArcFace 모델로 R⁵¹²의 목표 공간으로 임베딩한다. 기존 데이터베이스에 등록된 얼굴과 CCTV를 통해 얻은 얼굴들의 임베딩 벡터 사이의 Angular Cosine Distance를 측정하여 동일 인물인지 판단하는 매칭 알고리즘을 제안한다. 실험을 통해 두 모델을 동시에 사용할 최적의 환경을 파악하고, 마스크 착용으로 얼굴의 하단부가 가려지는 폐색 문제에 더욱 효과적으로 대응하여 매칭 성능을 높이는 방법을 제안한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.3
• /
• pp.303-309
• /
• 2011

Situation awareness services which increasingly expand their influence in everyday life can be classified into location-based service and social network service. Their quality of service (QoS) can be differed based on the location accuracy of smart phones and accuracy of directional recognition technology. This study was conducted to analyze GPS, digital compass, radio communication, and geospatial web information which can provide a clue in using the situation aware services based on lab experiments and surveys. According to the result of lab experiment on accuracy of determining location / direction with smart phones, owing to inherent lack of indoor accuracy in determining position and direction, as well as errors in spatial data used as platform, it was found that devices were not provided with sufficiently accurate data when using the situation aware services indoors compared to outdoors. To enhance accuracy of determining indoor positions, there are several methods including location metering based on Wi-Fi, which had several problems compared with GPS used in outdoor environment. Thus, it was determined that more study would be necessary to solve these issues.