• 한국측량학회지
• /
• 제39권6호
• /
• pp.599-607
• /
• 2021

스트리트뷰(Street-view) 영상은 도로의 특정 위치를 중심으로 한 전방위 영상을 제공하며, 보행 환경에 대한 다양한 장애물 정보를 포함한다. 보행자용 길안내 서비스에 활용하기 위한 보행 네트워크(Pedestrian network) 데이터는 교통약자를 비롯한 보행자의 이동 편의성을 보장하기 위하여 보행 장애물에 대한 최신 정보를 반영해야 한다. 본 연구에서는 스트리트뷰 영상과 딥러닝 기반의 객체탐지 알고리즘을 활용하여 서울 전역에 위치한 주요 보행 장애물인 볼라드(Bollard)를 학습하였다. 또한, 탐지된 볼라드 정보와 보행 네트워크 간의 공간매칭을 통해 횡단보도 노드를 대상으로 볼라드의 유무와 개수 정보를 장애물 속성으로 입력하고, 동시에 누락된 횡단보도 정보를 갱신하기 위한 프로세스를 정의하였다. 스트리트뷰 영상으로 학습된 모델은 보행 상황에서 스마트폰으로 촬영한 사진에 대해서도 적용이 가능하며, 향후 스트리트뷰 영상에 포함된 다양한 보행 장애물에 대한 추가 학습을 통해 효율적인 보행 장애 정보 갱신이 가능할 것으로 기대된다.

• 인터넷정보학회논문지
• /
• 제24권6호
• /
• pp.81-89
• /
• 2023

현대사회에서 시각장애인들은 도보, 승강기, 횡단보도 등 일반적인 환경에서 보행을 하는데 어려움이 있다. 시각장애인의 불편 해소를 위한 연구로 영상이나 음성을 이용한 연구가 있으며, 이런 연구는 고비용의 웨어러블 장치, 고성능 CCTV, 음성 센서 등을 사용하여 실생활에 적용하는 데는 한계가 있다. 본 논문에서 시각장애인이 보행 중에 안전한 이동을 위해서 스마트폰에 포함된 저비용의 영상 센서를 활용하여 주변 도보 공간을 인지하는 인공지능 융합 알고리즘을 제안한다. 제안된 알고리즘은 이동 중인 사람 탐지를 위해서 모션 캡처 알고리즘과 장애물 탐지를 위한 객체 탐지 알고리즘을 융합하여 개발하였다. 모션 캡처 알고리즘으로 mediapipe을 사용하여 이동 중에 있는 주변 보행자들을 모델링 및 탐지하였다. 객체 탐지 알고리즘을 사용했으며 도보 중에 발생하는 다양한 장애물을 모델링 하였다. 실험을 통하여 인공지능 융합 알고리즘을 검증했으며, 정확도 0.92, 정밀도 0.91, 재현율 0.99. F1 score 0.95로 결과를 얻어서 알고리즘의 성능을 확인하였다. 본 연구로 보행 중에 발생하는 볼라드, 공유 킥보드, 자동차 등의 주변 장애물 및 이동 중인 보행자 회피하여 시각장애인들의 통행에 도움을 줄 수 있다.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2016년도 제50회 동계 정기학술대회 초록집
• /
• pp.371.2-371.2
• /
• 2016

Graphene electronics is one of the promising technologies for the next generation electronic devices due to the outstanding properties such as conductivity, high carrier mobility, mechanical, and optical properties along with extended applications using 2 dimensional heterostructures. However, large contact resistance between metal and graphene is one of the major obstacles for commercial application of graphene electronics. In order to achieve low contact resistance, numerous researches have been conducted such as gentle plasma treatment, ultraviolet ozone (UVO) treatment, annealing treatment, and one-dimensional graphene edge contact. In this report, we suggest a fabrication method of one-dimensional graphene metal edge contact without using graphene exfoliation. Graphene is grown on Cu foil by low pressure chemical vapor deposition. Then, the graphene is transferred on $SiO_2/Si$ wafer. The patterning of graphene channel and metal electrode is done by photolithography. $O_2$ plasma is applied to etch out the exposed graphene and then Ti/Au is deposited. As a result, the one-dimensional edge contact geometry is built between metal and graphene. The contact resistance of the fabricated one-dimensional metal-graphene edge contact is compared with the contact resistance of vertically stacked conventional metal-graphene contact.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume I
• /
• pp.417-420
• /
• 2006

In these days, mobile application dealing with information contents on mobile or handheld devices such as mobile communicator, PDA or WAP device face the most important industrial needs. The motivation of this study is the design and implementation of mobile application using high resolution satellite imagery, large-sized image data set. Although major advantages of mobile devices are portability and mobility to users, limited system resources such as small-sized memory, slow CPU, low power and small screen size are the main obstacles to developers who should handle a large volume of geo-based 3D model. Related to this, the previous works have been concentrated on GIS-based location awareness services on mobile; however, the mobile 3D terrain model, which aims at this study, with the source data of DEM (Digital Elevation Model) and high resolution satellite imagery is not considered yet, in the other mobile systems. The main functions of 3D graphic processing or pixel pipeline in this prototype are implemented with OpenGL|ES (Embedded System) standard API (Application Programming Interface) released by Khronos group. In the developing stage, experiments to investigate optimal operation environment and good performance are carried out: TIN-based vertex generation with regular elevation data, image tiling, and image-vertex texturing, text processing of Unicode type and ASCII type.

• 대한기관식도과학회지
• /
• 제2권2호
• /
• pp.194-199
• /
• 1996

Laser therapy is becoming an accepted procedure for tissue coagulation and ablation and is especially useful in treating tumors. The laser energy is applied to the tissue of interest through various delivery systems which are introduced percutaneously, via blood vessels, through body openings, or during surgical exposure of the tissue. One of the major obstacles to effective application of lasers has been the lack of reliable method to determine the extent of tissue involvement in real time. Several methods have been proposed for monitoring the tissue response and controlling the laser in real time during laser therapy. Among them, magnetic resonance imaging(MRI) has been introduced to monitor laser-tissue interactions because laser irradiation induces changes not only in the thermal motions of the hydrogen protons within the tissue but also in the distribution and mobility of water and lipids. The buttocks of New Zealand rabbits were treated by KTP and $CO_2$laser(power : 10 watts, exposure time:10 seconds). m images were taken at immediately after lasering, 1 week later, 2 weeks later, and at the same time, tissues were harvested for histopathologic study. We analyzed MR images and histopathologic findigs of laser-treated tissues. The MR images taken immediately after laser treatment showed 3 layer pattern and which was correlated with histopathologic changes. We suggest MRI may become a useful monitoring tools for laser-tissue interaction.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2005년도 춘계 종합학술대회 논문집
• /
• pp.491-495
• /
• 2005

가정의 정보가전기기의 소형화, 네트워크화에 따라 사용자에게 네트워크의 유연성, 이동성, 사용의 편리성을 제공해 주는 무선 홈네트워크에 대한 요구가 증대되고 있다. 그러나, 기존 무선 홈네트워크 시스템은 가정 내 장애물에 의한 음영 지역이 존재하며, 정적이고 제한된 서비스만이 가능하다. 본 논문에서는 이러한 무선 홈 네트워크 시스템의 문제점을 해결하기 위한 방법으로 Home Robot을 이용한 무선환경의 홈 네트워크 시스템을 제안한다.

• 제어로봇시스템학회논문지
• /
• 제17권4호
• /
• pp.313-320
• /
• 2011

Multi-axle driving vehicles that are used in special environments require high driving performance, steering performance, and stability. Among these vehicles, 6WS/6WD vehicles with middle wheels have structural safety by distributing the load and reducing the pitch angle during rapid acceleration and braking. 6WS/6WD vehicles are favored for military use in off road operations because of their high maneuverability and mobility on extreme terrains and obstacles. 6WD vehicles that using in-wheel motor can generate the independent wheel torque without other mechanical parts. Conventional vehicles, however, cannot generate an opposite driving force at each side wheel. Using an independent steering and driving system, six-wheel vehicles can show better performance than conventional vehicles. Using of independent steering and driving system, the 6 wheel vehicle can improve a performance better than conventional vehicle. This vehicle enhances the maneuverability under low speed and the stability at high speed. This paper describes an independent 6WS/6WD vehicle, consists of three parts; Vehicle Model, Control Algorithm for 6WS/6WD and Simulation. First, vehicle model is application of TruckSim software for 6WS and 6WD. Second, control algorithm describes the optimum tire force distribution method in view of energy saving. Last is simulation and verification.

• 제어로봇시스템학회논문지
• /
• 제13권2호
• /
• pp.114-120
• /
• 2007

This paper introduces a mobile robotic system being developed for urban search and rescue. In order to search human victims in narrow spaces, we developed two types of serially linked mobile robots, named KAEROT-Centipede and KAEROT-SnakeTV1, that can climb over large vertical steps or travel inside narrow vertical pipes. To send such mobile robots to the disaster areas coping with large obstacles, we also developed a assistant mobile robot, named KAEROT-QuadTrack, that has 4 articulated track modules. This paper describes the mechanical structure and control architecture of the serially linked mobile robots and the supporting configuration for torque reduction of the assistant mobile robot during spinning motion that usually requires large driving torque. The experimental results show that such robotic systems have good mobility over the various terrains in disaster areas.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1195-1200
• /
• 2007

It is desirable that the guard robot should be small-sized and light-weighted to increase its portability. In addition, it should be able to overcome a relatively high obstacle to cope with different situations. The jumping robot can reach a higher place more rapidly than other locomotion methods. This research proposes the jumping mechanism based on the conical spring for a small robot. Both the clutch mechanism and conical spring are incorporated into the jumping mechanism. In the clutch mechanism, the spring can be immediately compressed and released by one actuator with the planetary gear train and one-way clutch. The robot equipped with the jumping mechanism can overcome the obstacles which are higher than its height. In this paper, the characteristic of the conical spring for the jumping robot is determined and the small-sized, lightweight jumping mechanism is developed. The validity of the jumping mechanism was verified by various experiments. It is shown that the robot using this mechanism can provide good mobility in the rough terrain.

• 한국콘텐츠학회논문지
• /
• 제20권8호
• /
• pp.637-644
• /
• 2020

VANET (Vehicular Ad Hoc Networks)은 차량 간, 차량과 인프라 간의 네트워크이다. 높은 이동성, 이동 제한, 장애물에 의한 신호 방해와 같은 VANET 고유의 특성은 안정적인 VANET 서비스 제공을 어렵게 한다. 이를 해결하기 위해, 본 논문에서는 기존 버스 기반 클러스터링을 개선한, 차량 종류 기반 우선순위 클러스터 방법을 제시한다. 제안 알고리즘은 차량 종류, 예상 통신 수명, 주변 노드 링크 차수를 바탕으로 우선순위, 링크 품질, 연결성을 평가해 클러스터를 구성한다. 차량의 종류를 바탕으로 미리 결정된 우선순위를 활용함으로써 클러스터 헤드 선택을 단순화하고 클러스터 커버리지를 높이고자 한다. 제안 알고리즘은 커넥티드카 환경에서 안정적인 서비스를 제공하는데 기여함으로써 다양한 서비스 활성화의 기반이 될 것으로 기대된다.