• 전기전자학회논문지
• /
• 제24권1호
• /
• pp.147-153
• /
• 2020

기존의 차선 검출 방법들은 곡률과 날씨 변화가 큰 도로 환경에서 검출률이 낮다. 확률적 허프 변환을 이용한 방법은 에지와 직선의 각도를 이용해서 차선을 검출함으로 곡선과 악천후일 때 검출률이 낮다. 슬라이딩 윈도우 방법은 윈도우로 이미지를 분할해서 검출하기 때문에 곡선 형태의 차선도 검출하지만 어파인 변환을 사용하기 때문에 도로의 경사율에 영향을 받는다. 본 논문에서는 다양한 외부 환경에서도 차선을 강인하게 검출하고 장애물을 회피하기 위한 딥러닝 기반의 주행 보조 시스템을 제안한다. VGG-16기반의 SegNet으로 입력 영상을 의미론적으로 분할해서 차선을 검출한다. 검출한 차선과의 이격거리를 계산하고 안전범위를 산출해서 차량이 차선의 중앙을 주행하도록 제어한다. 또한, 전방의 미확인 물체와 충돌이 예상되면 운전자에게 경보를 주고 Adaptive-MPC로 차량을 제어해서 충돌을 회피하는 알고리즘도 제안한다. CARLA로 시뮬레이션한 결과 제안한 알고리즘은 곡률이 큰 차선과 다양한 환경에서도 강인하게 차선을 검출하고 전방의 안전범위를 계산하여 충돌을 회피하는 것을 볼 수 있다.

• 인터넷정보학회논문지
• /
• 제24권1호
• /
• pp.39-47
• /
• 2023

The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.

• Journal of Communications and Networks
• /
• 제1권3호
• /
• pp.145-152
• /
• 1999

A new switch architecture is presented to enhance out-put queuing in photonic packet switches. Its appkication is for a packet switching enviroment based on the optical transport of fixed length packets. This architecture consists of a couple of cas-cading switching elements with output queuing, whose buffer ca-pacity is limited by photonic technology. The introduction of a suitable buffer management allows a very good and balanced ex-ploitation of the available optical memories, realized with fiber de-lay lines. In particular, packet loss performance is here evaluated showing the improvement with respect to the single switch and a way to design large optical switches is shown in order to meet broadband network requirements.

• Child Studies in Asia-Pacific Contexts
• /
• 제1권1호
• /
• pp.39-49
• /
• 2011

This study compared parents' and teachers' feeding practices with young children. Parents and teachers of children aged 0-3 years were recruited at 24 child care centers to complete surveys regarding their demographic characteristics, parenting styles, and feeding practices with young children. Respondents included 106 parents and 102 teachers. Participants' feeding beliefs and values were found to be related to their parenting style classifications (i.e., Authoritative, Authoritarian, or Permissive), ethnicity, income, and other demographic characteristics. Findings indicate the need for teachers and parents to begin communicating about their longterm goals for a child's development as soon as the child enters care. Understanding the goals and variation of feeding practices used at home and at school can help teachers and parents begin to construct a shared vision for care.

• Macromolecular Research
• /
• 제14권6호
• /
• pp.588-595
• /
• 2006

The morphology, structure and melting behaviour of cold-crystallized isotactic polystyrene (iPS) were studied by differential scanning calorimetry (DSC), wide angle X-ray diffraction (WAXD) and small angle X-ray scattering (SAXS). The polymer was found to crystallize according to the dual-lamellar stack model. The two populations of lamellae, along with a melting-recrystallization phenomenon, determined the appearance of multiple melting peaks in DSC traces. The annealing peak was attributed to the relaxation of a rigid amorphous phase, rather than to the melting of crystalline material.

• Journal of Communications and Networks
• /
• 제14권6호
• /
• pp.710-718
• /
• 2012

The implementation of a common control channel is one of the most challenging issues in cognitive radio networks, since a fully reliable control channel cannot be created without reserving bandwidth specifically for this purpose. In this paper, we investigate a promising solution that exploits the ultra wide band (UWB) technology to let cognitive radio nodes discover each other and exchange control information for establishing a communication link. The contribution of this paper is threefold: (i) We define the communication protocol needed to let cognitive radio nodes discover each other and exchange control information for link set up, (ii) we overcome the gap in coverage, which typically exists between UWB and long-medium range technologies, by using multi-hop communication, (iii) we evaluate the performance of our approach by adopting an accurate channel model and show its benefits with respect to an in-band signaling solution.

• 지적과 국토정보
• /
• 제51권1호
• /
• pp.39-51
• /
• 2021

최근 자율주행에서 도로, 차로, 교차로, 도로 표지, 도로 시설물 등을 효과적으로 표현하기 위한 표준화된 정밀도로지도의 데이터 모델링과 더불어 실질적인 적용을 위한 관심이 크게 증가하고 있다. 현재 ISO 22726-1, ISO 14296, HERE HD Live map, NDS open lane model, OpenDRIVE, NGII HD map 등의 다양한 국제 표준 또는 산업계 표준 모델들이 활용되고 있으나, 이들 간의 모델링 방식에서 큰 차이가 존재하여 다양한 표준의 정밀도로지도를 융합하여 활용하는데 많은 어려움이 존재한다. 이에 본 연구에서는 자율주행에서 다양한 정밀도로지도 표준 모델들의 효율적인 융합 활용을 지원하기 위하여 정밀도로지도 모델 간의 변환 방안을 제안하고자 한다. 구체적으로, 국내에서 접근이 용이한 국토지리정보원 정밀도로지도 모델과 산업계에서 활발히 이용되고 있는 OpenDRIVE 모델 간의 변환 방안을 제안하고자 한다. 제안된 방안은 NGII HD map의 각 레이어와 OpenDRIVE의 객체 간 단순 변환을 수행하는 방안, OpenDRIVE에 신규 객체를 생성하는 방안, 그리고 선형 변환 및 데이터 융합을 이용하여 NGII HD map 데이터를 OpenDRIVE 객체로 변환하는 방안으로 구성된다. 끝으로 NGII HD map에서 OpenDRIVE로 변환된 결과 데이터에 대하여 Carla 시뮬레이터를 이용한 가시화를 통하여 검증을 수행하였다. 이러한 NGII HD map 모델의 변환 방안은 향후 자율주행에서 NGII HD map의 활용도를 높이는데 크게 기여할 수 있을 것으로 기대된다.

• 한국항행학회논문지
• /
• 제27권1호
• /
• pp.36-42
• /
• 2023

자율주행 차량의 개발은 현재 각종 기업체와 연구소에서 활발하게 이뤄지고 있다. 특정 산업뿐만 아니라 일상생활 속 상용화에 대한 기대감 역시 높아진 상태이다. 자율주행 차량을 위한 시뮬레이터는 안정성 및 비용을 고려했을 때, 알고리즘 개발 및 수행에 있어서 필수 요소이다. 이러한 필요 속에서 다양한 시뮬레이터 및 시뮬레이터용 플랫폼들이 등장하고 있지만, 현실 세계의 다양한 기상 환경 요소를 반영한 시뮬레이션에 대한 연구는 아직 미흡한 편이다. 본 논문은 기상 환경을 고려할 수 있는 자율주행 차량용 교통 시뮬레이션을 제안하였다. 설정할 수 있는 기상 환경을 크게 4가지로 분류하였고, 이를 적용할 수 있는 개선된 충돌 방지 알고리즘을 제시한다. 시뮬레이션 개발은 자율주행을 위한 개발 도구 CARLA의 Python API를 통해 이루어졌고, 기존 충돌 알고리즘과의 수행 결과를 비교하였다. 이를 통해 실생활의 다양한 기상 환경 요소를 반영할 수 있는 고도화된 자율주행 차량용 시뮬레이션 개발을 위한 개선점을 제안하고자 하였다.

• Imaging Science in Dentistry
• /
• 제44권1호
• /
• pp.1-6
• /
• 2014

Professionals performing radiographic examinations are responsible for maintaining optimal image quality for accurate diagnoses. These professionals must competently execute techniques such as film manipulation and processing to minimize patient exposure to radiation. Improper performance by the professional and/or patient may result in a radiographic image of unsatisfactory quality that can also lead to a misdiagnosis and the development of an inadequate treatment plan. Currently, the most commonly performed extraoral examination is panoramic radiography. The invention of panoramic radiography has resulted in improvements in image quality with decreased exposure to radiation and at a low cost. However, this technique requires careful, accurate positioning of the patient's teeth and surrounding maxillofacial bone structure within the focal trough. Therefore, we reviewed the literature for the most common types of positioning errors in panoramic radiography to suggest the correct techniques. We would also discuss how to determine if the most common positioning errors occurred in panoramic radiography, such as in the positioning of the patient's head, tongue, chin, or body.

• 산경연구논집
• /
• 제6권3호
• /
• pp.27-33
• /
• 2015

Purpose - This paper's aim is to analyze the technological information in patent databanks as a strategy in prospecting for new technologies. Research design, data, and methodology - We detail the major free electronic database sources for patent information, the patent documents, the patent document structures, INID codes (Internationally Agreed Numbers for the Identification of Data), indexation, references, and classification notions. Additionally, we review and analyze information on the activities of the Center of Dissemination Documentation and Technological Information (CEDIN) from the National Institute of Intellectual Property (INPI) of Brazil for the period 2000 to 2011. Results - The research shows that the technological information contained in the patents could provide a wide range of functionality within companies and universities. Conclusions - In recent years, (CEDIN), a specialist in intellectual property, has been serving internal and external users by providing guidance on the basis of patents and other literature, but the number of users served is still small. In order to familiarize more potential users of such technological information, task forces should be created among INPI, universities, and companies.