만성간질환(Chronic diffuse hepatopathy)의 진단은 간경화, 간부전, 간암으로 인한 사망률과 유병율을 감소 시키는 중요한 임상과제 중 하나이다. 이에 본 연구에서는 초음파진단 영상을 바탕으로 간탄력도검사(Fibro scan)를 통해 지방간, 만성간질환을 예측할 수 있는 기준을 알아보고자 하였다. 280명의 환자를 대상으로 혈청학적 검사, 간탄력도 검사 측정값(kPa)을 분석하였으며 ROC 곡선분석을 이용하여 지방간 및 만성간질 환을 예측을 위한 간탄력도 측정값의 cut-off value를 결정하였다. 혈청학적 검사에서 Bililubin, PT(prothromb in time)은 질병예측에 관련성이 없었으며(p=0.243, p=0.115), 혈당과 중성지방수치는 지방간에서 의미 있는 차이를 보이며 높게 나타났다(p<0.05). 간탄력도 측정값은 정상 대조군, 지방간, 만성간질환 순으로 높게 측 정되었으며 만성간질환 예측을 위한 cut-off value는 10.3 kPa(AUC 0.98, Sensitivity 94.94%, Specificity 94.9 3%)로 결정하였다. 따라서 정량적인 평가로 만성간질환 환자의 진단에 일차적인 도구로 활용될 것으로 사 료된다.

최근 들어 한국의 영상산업은 급속히 발전해왔으며 성장속도와 추세가 가장 강한 산업으로 부상 되고 있다. 한국영상산업의 성장은 정치, 경제에도 유리하게 촉진한다. 중국이 지리적으로 한국과 가까운 나라로서 한국의 영상산업의 급성장을 보고 많은 소중한 경험을 배울 수 있을 것이라고 생각한다. 이 논문은 한국의 영상산업 급성장의 원인에 대한 분석을 통하여 중국의 영상산업에 대해 살펴보고 중국의 영상산업 발전에 유용한 의견과 제안을 연구해 보았다.

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x–axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.

This work shows how to create an algorithm and implementation for motion and image matching between a vehicle simulator and Unity 3D based virtual object. The motion information of the virtual vehicle is transmitted to the real simulator via a RS232 communication protocol, and the motion is controlled based on the inverse kinematics solution of the platform adopting rotary-type six actuators driving system. Wash-out filters to implement the effective motion of the motion platform are adopted, and thereby reduce the dizziness and increase the realistic sense of motion. Furthermore, the simulator system is successfully designed aiming to reducing size and cost with adaptation of rotary-type six actuators, real driving environment via VR (Virtual Reality), and control schemes which employ a synchronization between 6 motors and 3rd order motion profiles. By providing relatively big sense of motion particularly in impact and straight motions mainly causing simulator sickness, dizziness is remarkably reduced, thereby enhancing the sense of realistic motion.

본 연구는 IP 카세트를 이용하는 이동촬영 장비의 세균오염도를 조사하여 이동촬영으로 인한 병원 감염을 예방하고 감염교육의 기초자료를 제공하고자 실시하였다. 결과는 IP Cassette 1번에서 CNS, VRE가 검출되었다. 2번에서는 CNS, 3번에서는 CNS, Pseudomonas aeruginosa, 4번에서는 CNS, 5번에서는 CNS, Bacillussp., 6번에서는 Enterococcus faecium이 검출되었다. 영상판독기에서는 Enterococcus faecium, Bacillus sp., 장비 이동 손잡이에서 Acinetobacter baumannii, 조작버튼에서는 Bacillus sp., 조사야 조절 손잡이에서는 CNS, Bacillus sp., X-선 발생 스위치에서는 Acinetobacter baumannii, 바코드기 에서는 CNS가 검출되었다. IP Cassette 이동테이블에서는 Bacillus sp. Acinetobacter baumannii, 납 앞치마에서는 CNS, Bacillus sp.가 검출되었다. 방사선사가 촬영 중 착용한 의료용 장갑에서는 Acinetobacter baumannii, CNS가 검출 되었다. 따라서 IP Cassette는 사용 후에는 반드시 소독하고 재사용하며, 영상판독기, IP 이동테이블은 오염된 IP Cassette를 통해 세균이 전파될 수 있으므로 사용 후에는 소독을 실시해야 한다. 환자와 직접 접촉하는 의료용 장갑도 1회 사용 후 교체하고 촬영 시 접촉이 많은 X-발생 스위치, 납 앞치마도 철저히 소독하여 이동촬영으로 인한 감염을 예방하여야 한다.

본 연구는 영상의 노이즈 감소를 위한 복합필터 제안과 간 초음파영상에서 노이즈 제거를 통한 영상품질의 향상으로 정확한 영상 해석에 도움을 주고자 하였다. 실험은 ATS-539 다목적용 초음파팬텀을 이용하여 Gaussian blurring filter, Sharpening filter, Median filter의 조합으로 상위 7개의 복합필터를 선정하고 이를 간 초음파영상에 적용하였다. 그 결과 상위 7개 복합필터 적용하였을 때 SNR, CNR, MSR 값이 모두 증가하는 것으로 나타났다. 이 중 복합필터 1과 2가 가장 높은 값을 나타내었다. 또한 PSNR 30 dB이상, SSIM 1에 가까운 결과값을 나타내어 영상의 손실률이 적음을 알 수 있었다. 따라서 본 연구에서 제안한 복합필터의 적절한 적용은 정확한 영상의 판독과 해석에 도움을 줄 수 있을 것이다.

Recently, there has been frequent shortage of expansion joint in expressway bridges. When that happens, maintenance budgets will be overloaded and not effective, so it is not easy to come up with a solution. In this study, we introduce a bridge inspection system that combines laser image sensing technology and automatic control technology, which have been recently applied in various fields. And this system was developed to measure bridge extension joints while traveling more than 80km/h.

With the introduction of the one-tolling and smart-tolling, Vehicle number recognition technology of ITS imaging equipment that was used to prevent the escape and tolling evasion will play an important role in the collection system. Korea Highway Corporation will prepare a ITSK-00088 Performance Assessment to improve the license plate recognition. and there are a number of efforts to improve the accuracy of vehicle number recognition. But even if the ITS equipment had passed the performance assessment, it is in a situation which does not achieve the target value due to physical and environmental factors. we propose a method for acquiring the additional information(color, type, pattern) including plate number of the vehicle in order to improve the recognition rate of the vehicle number. Through that link the vehicle additional information, vehicle specifications DB, image analysis system, the goal is to build a system that can be identified for the misrecognized and unrecognized vehicle.

We designed and implemented automatic pavement damage detector using an image processing algorithm on driving condition. The experimental results show that the detector is able to successfully monitor and detect pavement damages

The internal displacement of the corrugated steel plate structure reduces structural stability. In this study, we developed a smart checking system to evaluate the stability of the corrugated steel plate culvert structure by laser scanning and image mapping. It is expected that output data can be used in inspecting deformation rates between designs and measured 3D shapes. Also, it can solve the problems in current visual inspection and systemize the inspection tasks scientifically.

To monitor structural responses and detect serious events, an image-based health monitoring technology for existing bridges has been developed. The image-based system allows users to connect and remotely control cameras in real-time. The developed system was successfully tested and verified in the test bed bridges. This paper presents the application examples of it.

The purpose of this study is to analyze the accuracy of cultivated crop database in agricultural farm business using UAV(Unmanned Aerial Vehicle) and field survey over Daesso-myeon, Umsung-gun, Chungbuk. When comparing with agricultural farm business and cadastral maps, Daeso-myeon crop field shows 29.8%(2,030 parcels out of 6,822 parcels) is either mismatched or missing. It covers almost 19.3%(3.4km2 of 17.6km2) of total farmland. In order to solve these problems, it is necessary to prepare a multifaceted plan including cadastral map. Comparative analysis of the cultivated crop registered in the agricultural farm business and the field survey agreed only in 3,622 parcels in total 6,822 parcels whereas 3200 parcels disagree. Among these disagreed parcels 2,030(29.8%) have been confirmed as unregistered farm business entity. Accuracy of cultivated crop registered in agricultural farm business agreed in 75.6% cases. Especially the paddy field registration is more accurate that other crops. These discrepancies can lead to false payment in agricultural farm business. For exploration and analysis of regional resources, UAV images can be used together with farm business management database and cadastral map to get a clearer grasp over on-site resources and conditions.

Scientific analysis and inter-Korean cooperation are needed to reduce North Korea’s environmental pollution and deforestation. Many efforts to reduce North Korea’s environmental issue have a fundamental weakness because they are generally influenced by internal and political conditions. To overcome such a weakness, two approaches may be effective; the first is to use new technology such as Google Earth and the second is to build collaborative governance that is invulnerable to political conditions. This study focuses on building collaborative governance models based on Google Earth data investigation, a previous research’s release of Google Earth database, and literature review of North Korea’s environmental issues. This research’s results are as follows. First, North Korea’s industrial regions suffer from environmental pollution and many other regions experience severe deforestation according to Google Earth-based spatial images. Second, we can discern environmental pollution such as air pollution, water pollution, soil pollution, and deforestation using Google Earth-based spatial image. In reality, we are able to identify deforestation and partially soil pollution with Google Earth-based spatial image. Third, there are different environmental problems among North Korea’s local regions. South Korea has to prepare and plan various collaborative governance models depending on North Korea’s local needs on environmental problems.

두부 CT에서 피폭선량을 줄이기 위해서 저관전압 사용이 요구된다. 그러나 노이즈가 증가하는 현상이 발생해서 2차 데이터 가공 시 오류를 초래할 수 있다. 본 연구에서는 저관전압을 사용하고 노이즈를 줄일 수 있는 방법을 제시하였다. 실험 결과 100kVp 에서 노이즈 값이 높게 나타났고, 140kVp에서 가장 낮게 나타났다. 100kVp에서 선량이 낮게 나타났고, 140kVp에서 선량이 높게 기록되었다. 역치값에 따른 웨이블릿의 적용 결과 웨이블릿 Th30에서 노이즈값은 4.51로 감소하였다.(50% 감소) 100kVp, 회전시간 0.5 sec (선량: 40.64 mGy)파라미터 조건과 웨이블릿 Th 30을 사용하면 65.3%의 피폭선량 감소가 가능하였다. 연구에서 제시한 방법을 두부CT영상에 적용한다면 환자의 안전과 정확한 정보를 해석하는데 도움을 줄 것이라고 판단한다.

Recently, there has been frequent shortage of expansion joint in expressway bridges. When that happens, maintenance budgets will be overloaded and not effective, so it is not easy to come up with a solution. In this study, we introduce a bridge inspection system that combines laser image sensing technology and automatic control technology, which have been recently applied in various fields. And this system was developed to measure bridge extension joints while traveling more than 80km/h.

With the introduction of the one-tolling and smart-tolling, Vehicle number recognition technology of ITS imaging equipment that was used to prevent the escape and tolling evasion will play an important role in the collection system. Korea Highway Corporation will prepare a ITSK-00088 Performance Assessment to improve the license plate recognition. and there are a number of efforts to improve the accuracy of vehicle number recognition. But even if the ITS equipment had passed the performance assessment, it is in a situation which does not achieve the target value due to physical and environmental factors. we propose a method for acquiring the additional information(color, type, pattern) including plate number of the vehicle in order to improve the recognition rate of the vehicle number. Through that link the vehicle additional information, vehicle specifications DB, image analysis system, the goal is to build a system that can be identified for the misrecognized and unrecognized vehicle.

We designed and implemented automatic pavement damage detector using an image processing algorithm on driving condition. The experimental results show that the detector is able to successfully monitor and detect pavement damages.

The internal displacement of the corrugated steel plate structure reduces structural stability. In this study, we developed a smart checking system to evaluate the stability of the corrugated steel plate culvert structure by laser scanning and image mapping. It is expected that output data can be used in inspecting deformation rates between designs and measured 3D shapes. Also, it can solve the problems in current visual inspection and systemize the inspection tasks scientifically.

To monitor structural responses and detect serious events, an image-based health monitoring technology for existing bridges has been developed. The image-based system allows users to connect and remotely control cameras in real-time. The developed system was successfully tested and verified in the test bed bridges. This paper presents the application examples of it.

This study estimated sunshine duration in South Korea using cloud detection images; the 2 class and 5 class images of Communication, Ocean and Meteorological Satellite (COMS). The images were preprocessed and then compared with the observed sunshine duration from the Automated Synoptic Observing System (ASOS). Based on the result of comparing yearly and monthly sunshine duration, the results of the 5 class were better than the results of the 2 class. In the case of comparing daily sunshine duration, the results of the 5 class also showed relatively better outcome than the 2 class images. The simulation performance of the sunshine duration observed by ASOS and the sunshine duration calculated by COMS were evaluated using Kling-Gupta Efficiency (KGE) technique. The 5 class data showed relatively high efficiency. RMSEs were relatively lower in the 5 class than the 2 class image in all years (2011-2014). Therefore, the 5 class data among the COMS satellite images could provide meaningful information at the points where there is no observation of sunshine duration.