• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.635-640
• /
• 2021

In this paper, we describe a parking space identification system that can automatically identify empty parking lot spaces from a parking lot photo. This system is based on a deep learning technique, and the accuracy of the identification result is good by learning various existing parking lot images. It could be applied to the existing parking management system. This system was also developed as a smartphone application for easy testing. Therefore, if you take a picture of a parking lot through a smartphone camera, the captured image is automatically recognized and an empty parking space can be automatically identified.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.6
• /
• pp.541-547
• /
• 2017

Climate change has become the main cause of the exacerbation in natural disasters. Social Overhead Capital(SOC) structure needs to be checked for displacement and crack periodically to prevent damage and the collapse caused by natural disaster and ensure the safety. For efficient structure maintenance, the optical image technology is applied to the Structure Health Monitoring(SHM). However, optical image is sensitive to environmental factors. So it is necessary to verify its validity. In this paper, the accuracy of estimating the vertical displacement was verified with respect to environmental condition such as natural light, measurement distance, and the number of image sheets. The result of experiments showed that the effect of natural light on accuracy of estimating vertical displacement was the greatest of all. The measurement angle which was affected by the change in measurement distance was also important to check the vertical displacement. These findings will be taken into account by applying appropriate environmental condition to minimize errors when the bridge was measured by camera. It will also enable the application of optical images to the SHM.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.3
• /
• pp.665-671
• /
• 2013

Even though a dual lens stereoscopic camera allows for convenient stereoscopic photography, the necessity for the research comes up, since the dual lens stereoscopic camera can cause visual discomfort during zoom-in due to the fixed convergence point. We propose a method based on which a convergence point can be adjusted to prevent visual discomfort during zoom-in for a dual lens stereoscopic camera. First, the relational model is classified into nine kinds and defined, depending on locations of focus, object, and convergence point. And then, the method to minimize visual discomfort is suggested by adjusting convergence point on the given model. We also implement the suggested methods with anaglyph computer graphic and demonstrate the superiority of them.

• Journal of Broadcast Engineering
• /
• v.23 no.2
• /
• pp.283-292
• /
• 2018

Devices capable of capturing and displaying high dynamic range (HDR) images with significantly increased brightness range compared to low dynamic range (LDR) images have been developed and various methods for efficiently converting the brightness range of an image have been developed. In this paper, we propose a reverse tone mapping method using a guided filter to efficiently convert LDR images into HDR images. After obtaining brightness enhancement function (BEF) using a guided filter, we can reconstruct HDR image from one LDR image. In addition, when the image is too bright or dark, the proposed method maximizes the image quality of the reconstructed HDR image by estimating and adjusting the exposure value before expanding the brightness range of images. Computer simulations show that the proposed method produces HDR images of superior quality compared with the conventional methods.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.375-378
• /
• 2019

최근 딥러닝과 머신러닝 기법이 소프트웨어의 성능 향상에 도움이 되는 것이 입증됨에 따라, 의료 영상 진단 보조 소프트웨어를 개발하기 위한 시도가 활발해 지고 있다. 그 중 캡슐내시경은 소장 소화기관을 관찰할 수 있는 초소형 의료기기로, 기존의 내시경 검사와 다르게 이물감이 느껴지지 않고 의료보험 적용으로 최근 들어 널리 이용되고 있다. 일반적으로 캡슐 내시경은 8 시간 동안 소화기간을 촬영하며, 한 번의 검사 결과로 생성된 동영상 데이터 셋은 수 만장의 이미지를 포함하기 때문에, 방대한 양의 이미지들을 효율적으로 관리하기 위한 체계가 필요하다. 특히, 방대한 양의 캡슐내시경 이미지를 학습하는 경우, 수 만장의 이미지 속에서 유의미한 특징(촬영정보, 의사소견, 환자정보, 병변의 위치 및 크기 등)을 추출해내야 하므로 학습 데이터 레이블링을 위한 정보를 정확히 추출해야 하는 작업이 요구된다. 따라서 본 논문에서는 캡슐내시경 영상을 학습할 때, 학습 데이터 레이블 정보를 체계적으로 구축할 수 있게 하는 레이블 정보 추출 기법을 제안하고자 한다. 제안하는 기법은 병원에서 14년간 수집된 총 340명의 캡슐내시경 데이터(약 1,700 만장의 이미지)를 토대로 영상데이터를 구조적으로 분석하여 유의미한 정보를 추출하고 노이즈 데이터를 제거한 뒤, 빅데이터 저장소에 적재할 수 있음을 보였다.

• Conservation Science in Museum
• /
• v.24
• /
• pp.75-80
• /
• 2020

X-ray computed tomography (X-ray CT), which is often applied to the investigation of the interior structures of cultural properties, is very useful for studying production methods used in lacquerware that would otherwise be difficult to observe with the naked eye. Lacquerware inlaid with mother-of-pearl is an important subject in the study of traditional Korean craft. However, it can be a challenge to specify the production methods used in the framework of a lacquerware item unless the object has been structurally damaged. Studies of lacquerware inlaid with mother-of-pearl have thus far focused on the techniques of lacquering and of inlaying the mother-of-pearl. Production methods for the framework of lacquerware has received little academic attention. This study conducted X-ray CT on a lacquerware item from the Joseon period to reveal the materials and woodworking techniques used for the framework. The study revealed that softwood was used for the framework, and the post (gidungmok) and apron (soemok) were joined using a three-way miter joint (sambang yeongwi jjaim). Other pieces were joined with nails.

• Korean Journal of Heritage: History & Science
• /
• v.50 no.3
• /
• pp.64-87
• /
• 2017

Dahoe is a traditional braid in Joseon Dynasty. There are many Dahoe artifacts, which can give us a glimpse of the costume, culture, and life of that era. The study of Dahoe is necessary in various fields, but it is difficult because this manufacturing technique has been passed down from hand to hand. Few studies have been done so far. This research examines the manufacturing technique of KwangDahoe which is passed down by Maedeupjang (Decorative Knotting) and is generally used for knotting and/or tying objects. The main characteristic of TieKwangDahoe, made through the same method as WonDahoe, is the square hole in the middle. It was impossibile to remake the original braid because there is no confirmed number of the strand. Especially it is very difficult to do conservation and restoration on serious degradation state of the fiber. Therefore, it is necessary to analyze the non-destructive manufacturing techniques method for Dahoe and assess their applicability. First, we analyzed the artifacts' manufacturing technique based on the database of the Dahoe's manufacturing technique. In order to do that, we undertook schematization, restoration, morphological analyzation of the Dahoe. And then, X-ray CT scans were performed to improve the reliability of the DB. These results of scanning were interpreted based on the manufacturing technique. The selected Tie-KwangDahoe on the sword for the study are artifacts including artistic value and symbolism in Joseon Dynasty. Based on the analysis of the manufacturing technique, we found that both artifacts were made of 20-strand braid of single cross according to the length-scale measure. It was manufactured using 8-strand on left-right side, 12-strand on front-back side by the braiding manufacturing technique method Finally, this research suggests non-destructive analysis method of Dahoe's manufacturing technique is based on the database and the analysis results. I hope this research can be useful in various professional fields of Dahoe in the future. Moreover, I hope this can be of any help in preserving Korean cultural heritage.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.4
• /
• pp.123-133
• /
• 2005

This study has made photographing respectively by changing the converging angle by use of d7 $metric^5$ that is a measurement digital camera. And also in order to minimize the errors happened at the relative orientation, we have sorted out the round target that the relative orientation is automatically on the programming and have calculated RMSE by carrying out the bundle adjustment. We think that such a study could be used as very important basic data necessary in deriving the optimal photographic conditions by the close-range digital photogrammetry and in judging such a degree.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.4
• /
• pp.91-98
• /
• 2017

Electrical impedance tomography is a nondestructive imaging technique to reconstruct unknown conductivity distribution based on applied current data and measured voltage data through an array of electrodes attached on the periphery of a domain. In this paper, an inverse method based on truncated singular value decomposition is proposed to solve the inverse problem with the generalized Tikhonov regularization and to reconstruct the conductivity distribution. In order to reduce the inverse computational time, truncated singular value decomposition is applied to the inverse term after the generalized regularization matrix is taken out from the inverse matrix term. Numerical experiments and phantom experiments have been performed to verify the performance of the proposed method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.1 s.35
• /
• pp.75-83
• /
• 2006

Satellite imagery is generally used for investigating the damage from natural disaster for wide area and remotely piloted vehicle or aerial photos are used for the local damage. But for more detailed information such as damages of public facilities, these methods are inadequate and so in this case field surveying has been carried out. We tried to estimate the damage of public facilities faster and more accurately using photogrammetric method. We developed a digital stereo camera system by fixing two digital cameras on a frame, and with this system the photos of actually damaged areas were collected. The damages were estimated from these stereo photos. Then the estimated data was compared with field surveying data in order to verify our system.