• 한국자동차공학회논문집
• /
• 제25권2호
• /
• pp.219-226
• /
• 2017

This paper addresses the effective and quantitative image DB construction for the development of front looking camera systems. The automotive industry has expanded the capability of front camera solutions that will help ADAS(Advanced Driver Assistance System) applications targeting Euro NCAP function requirements. These safety functions include AEB(Autonomous Emergency Braking), TSR(Traffic Signal Recognition), LDW(Lane Departure Warning) and FCW(Forward Collision Warning). In order to guarantee real road safety performance, the driving image DB logged under various real road conditions should be used to train core object classifiers and verify the function performance of the camera system. However, the driving image DB would entail an invalid and time consuming task without proper guidelines. The standard working procedures and design factors required for each step to build an effective image DB for reliable automotive front looking camera systems are proposed.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2020년도 추계학술발표대회
• /
• pp.814-817
• /
• 2020

The number of single-person households is increasing every year, and there are also high concerns about the crime and safety of single-person households. In particular, crimes targeting women are increasing. Although home surveillance camera applications, which are mostly used by single-person households, only provide intrusion detection functions, this service utilizes AI image recognition technologies such as face recognition and object detection to provide theft, violence, stranger and intrusion detection. Users can receive security-related notifications, relieve their anxiety, and prevent crimes through this service.

• 산업진흥연구
• /
• 제5권3호
• /
• pp.53-60
• /
• 2020

본 연구는 하인즈 코헛의 자기(Self)이론을 기반으로, 자기대상(Selfobject) 기능을 상실한 내담자의 치료적 활성화를 위해 상담자의 전이대상 역할을 기술하였다. 본 연구에서 인간은 평생을 통해서 자기대상이 필요함을 확인하는 계기가 되었다고 할 수 있다. 다음으로는 변형적 내재화 과정을 언급하면 유아는 자기대상을 통한 최적의 좌절로 인하여 부모의 한계를 체험하면서 환상의 세계에서 현실로 돌아오게 된다. 전이대상으로 상담자 역할은 내담자가 응집적 자기를 확립하여, 적절한 자기대상을 선용하도록 하여야 한다. 그리고 내담자의 과대주의와 과시주의를 공감하고 상담자는 이상화 대상이 되어서 내담자가 인정받고 동일시할 수 있는 기회를 주어야 한다. 상담자는 상담 과정에서 내담자에게 최적의 좌절을 제공할 수 있다. 이때 상담자는 자신의 실수를 인정할 때 내담자는 상담자를 현실적으로 바라보게 되고 건강한 자기를 구축하여 변형적 내면화를 이룩하게 된다. 상담을 통해서 내담자에게 응집적 자기가 형성되면 타인을 공감하고 건강한 인간관계를 형성할 수 있다. 그러면 자신의 감정을 통제할 수 있고 비전을 가지게 된다. 그리고 내담자는 삶을 살아가면서 일생동안 적절한 대상과 관계를 맺으면서 살아갈 수밖에 없다고 인식하게 된다.

• 정보보호학회논문지
• /
• 제33권6호
• /
• pp.907-917
• /
• 2023

최근 자율주행 자동차는 운전자 지원 시스템에 딥러닝 기술을 적용하여 운전자에게 편의성을 제공하고 있지만, 딥러닝 기술이 적대적 회피 공격(adversarial evasion attacks)에 취약함이 밝혀졌다. 본 논문에서는 객체 인식 알고리즘인 YOLOv5(You Only Look Once)를 대상으로 MI-FGSM (Momentum Iterative-Fast Gradient Sign Method)를 포함한 5가지 적대적 회피 공격을 수행하였으며 객체 탐지 성능을 mAP(mean Average Precision)로 측정하였다. 특히, 본 논문에서는 모폴로지 연산을 적용하여 적대적 공격으로부터 노이즈를 제거하고 경계선을 추출하여 YOLO가 객체를 정상적 탐지할 수 있는 방안을 제안하고 이를 실험을 통해 그 성능을 분석하였다. 실험 결과, 적대적 공격을 수행했을 때 YOLO의 mAP가 최소 7.9%까지 떨어져 YOLO가 객체를 정확하게 탐지하지 못하는 것을 87.3%까지 성능을 개선하였다.

• 대한방사선치료학회지
• /
• 제20권2호
• /
• pp.83-89
• /
• 2008

목 적: 두경부 암 환자 치료 시 표적 및 주변 장기(Target 및 Structure)를 확인하는 방법으로 MVCBCT, KVCBCT, CT On-rail System, Ultrasound 등이 이용된다. 이 중 MVCBCT의 경우는 뼈를 이용한 표적 및 주변 장기의 확인에는 유용하나, 연부조직으로 구성된 표적 및 주변 장기의 확인에는 어려움이 있다. 이에 본 연구에서는 CT On-rail System을 이용하여 두경부 암 환자의 이하선의 움직임에 대한 파악과 체적의 변화에 따른 선량의 변화를 연구해 보고자 한다. 대상 및 방법: 본원에서 두경부 암으로 치료받는 환자 5명을 대상으로 하였다. 선택된 환자는 시멘스사 ARTISTE CT Vision (CT On-rail System)을 이용하여 주당 3회씩 CT 스캔을 시행하였다. CT 스캔 후 이하선의 움직임을 치료 계획시의 영상과 비교하여 이동된 좌표를 얻었으며, 이하선의 체적을 확인하기 위하여 획득한 CT영상을 치료계획 시스템(RTP System)에 전송하여 변화된 체적에 따른 선량분포의 차이를 확인하였다. 결 과: 이하선의 움직임에 의한 표적 좌표의 변화는 X: -0.4~0.4 cm, Y: -0.4~0.3 cm, Z: -0.3~0.3 cm이었다. GTV의 체적은 평균 7.11%/week로 감소되었으며 이하선의 체적과 선량의 변화는 평균적으로 좌측 이하선의 체적은 평균 4.81%/week, 우측 이하선의 체적은 2.91%/week, 선량은 좌측 이하선의 선량은 3.66%/week, 우측 이하선 선량은 2.01%/week 감소하였다. 결 론: CT On-rail System에서 얻어진 영상을 이용하여 표적 및 주변 장기를 확인한 결과 MVCBCT를 이용한 영상에 비해 연부조직의 관찰에 우수함을 알 수 있었다. 또한, 획득한 영상으로 재 치료계획(Replanning)을 한 후 선량의 재분포를 획득한 결과 단순한 움직임의 보정뿐 아니라 체적의 변화를 고려한 정확한 선량분포를 얻을 수 있었으며, 이렇게 보정된 선량의 전달은 Adaptive Targeting Radiotherapy가 가능할 수 있다고 사료된다. 향후 선량의 전달까지 걸리는 시간을 단축할 수 있는 Real Time Adaptive Targeting Radiotherapy가 구축되어야 할 것으로 사료된다.

• 대한안전경영과학회지
• /
• 제17권4호
• /
• pp.105-112
• /
• 2015

Sawmilling industry remained a high risk with the average 4.73% of industrial accidents in 2010-2012 that was eight times that of general manufacturing. Sawmilling industry had 200 industrial accidents victim in average. Manufacturing process in sawmill industry contained dangerous machinery such as conveyors, roller, saw ( band saw, circular saw) etc. It may be effective to figure out the type of industrial accidents occurred in the past and extend risk assessment which can predict hazard such as near miss when implementing exposure or potential dangers in sawmill industry. This study conducted research on the actual condition on the place of industrial accident occurrence, detailed work and contact object when injured, and injured part targeting 643 businesses which had industrial accidents in 2010-2012. As the results, RPN of general sawmill industry was the highest 'ganglip saw' with 36,157. RPN of the following order were 'moving truck' with 25,454, 'special machining operations' with 22,283. Also, probability of general sawmill industry was a lots within 1 year, while risk appeared a lots within 5 years. So, risk assessment shall be needed to emphasis on accident prevention of sawmill industry. And additional work will be needed on the risk assessment in hazard prevention work of supervisors.

• 대한안전경영과학회지
• /
• 제17권4호
• /
• pp.87-96
• /
• 2015

This study analyzed the safety management efficiency through input-oriented BCC Model using DEA by making of Models, in which this study selected the number of staff affiliated with the construction site, number of staff members on the construction team, and number of safety personnel as Input Factor, along with the number of disaster victims and zero-accident accomplished hours as output elements, targeting 40-or-so apartment building construction sites which are being built by 3 domestic construction companies. As a result of efficiency, it was 0.643, the number of efficient DMU was 4. In the aspect of returns to scale, 21 construction sites(52.5%) found to be in a state of increasing returns while 14 construction sites(35%) was in a state of Decreasing returns. The reason for inefficiency was found to lie in technical factors in case of 30 construction sites(75%). Lastly, inefficient DMU is in need of 38.9 % and 66% reduction in site personnel and safety personnel. Based on study results, the 29 construction sites accounting for 72.5% of DMU for safety management efficiency evaluation object turned out to do inefficient safety management that doesn't fit the size of each company.

• 농촌지도와개발
• /
• 제23권3호
• /
• pp.233-242
• /
• 2016

This study aimed to analyze educational satisfaction and the relationship between learning transfer and learning persistence shown after actual education targeting students who participated in the agricultural education and training. Conclusions based on the study results can be suggested as follows. First, of the factors related to learning persistence, satisfaction of educational contents turned out to be a statistically significant factor with a positive effect in the agricultural education and training. Students participating in the agricultural education and training have a conspicuous object to learn for improving ability which is necessary for and applicable to agriculture. Second, of the three factors related to learning transfer in the agricultural education and training, satisfaction of educational contents, educational facilities and satisfaction of environment turned out to have a positive effect. Third, results show that satisfaction of instructors does not affect both learning persistence and learning transfer. Lastly, in case of education and training for field practice, this study is suggesting the necessity of research by accessing in a concrete and detailed manner such as learning contents, instructors, educational facilities and satisfaction of environment from the comprehensive concept of educational satisfaction in the directivity of study related to satisfaction.

• 대한안전경영과학회지
• /
• 제5권4호
• /
• pp.97-106
• /
• 2003

At present, tendency of ERP(Enterprise Resource Planning) enterprises is that many ERP enterprises from abroad are rushing into capture of small and medium enterprises at home actively. SAP Korea and Korean Oracle have already showed their new product targeting domestic market of small or medium standing enterprise, and more, even MS(Micro Soft) also rushes into this market in earnest. The domestic business circle of ERP should prepare countermeasure by raising the perfection of product and having good command of minute marketing strategy to survive from aggressive strategy of SMB market. In addition, about the computerization of main affairs of business, ordering developing process was general that developing staffs analysed the affairs of each department that needed computerization and construct according to the operation process by using different tools, but condition is changing that businesses themselves are purchasing business application package from expert soft program enterprise and construct. Therefore, in this study, I try to grasp the problem of management, and define a new process that can help for more efficient management by making it an object producing and management module of enterprise 'K' that is one of domestic small and medium enterprise and that is operating ERP at present. As well, through the analysis of affair related producing, we are aiming to prepare for establishment of target, its range, and making the standard of result evaluation.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1396-1406
• /
• 2018

Lane detection is a key function in developing autonomous vehicle technology. In this paper, we propose a lane marker detection algorithm robust to environmental variation targeting low cost embedded computing devices. The proposed algorithm consists of two phases: initialization phase which is slow but has relatively higher accuracy; and the tracking phase which is fast and has the reliable performance in a limited condition. The initialization phase detects lane markers using a set of filters utilizing the various features of lane markers. The tracking phase uses Kalman filter to accelerate the lane marker detection processing. In a tracking phase, we measure the reliability of the detection results and switch it to initialization phase if the confidence level becomes below a threshold. By combining the initialization and tracking phases we achieved high accuracy and acceptable computing speed even under a low cost computing resources in which we cannot use the computing intensive algorithm such as deep learning approach. Experimental results show that the detection accuracy is about 95% on average and the processing speed is about 20 frames per second with Raspberry Pi 3 which is low cost device.