• 한국정보통신학회논문지
• /
• 제26권5호
• /
• pp.668-674
• /
• 2022

시각 정보를 이용한 기계 학습 기술은 주변 상황 인지, 결함 감지, 보안 그리고 사용자 분석과 같이 산업, 서비스 분야에서 활용성이 높아졌다. 그 중 CCTV 영상 분석을 통한 사용자 분석은 시각 정보를 잘 활용하는 실용적인 부분이라고 할 수 있다. 또한 이러한 임베디드 환경에서의 실용성을 높이기 위한 신경 회로망 경량화에 대한 연구가 지속되고 있다. 본 논문에서는 디스플레이형 자판기인 키오스크에서 활용할 수 있는 사람 및 얼굴 검출과 사용자의 나이 및 성별 분류 시스템을 제안한다. 제안하는 모델은 MobileNet, YOLOv2, 생략 연결을 기반으로 설계되었으며, 검출과 분류 망을 개별적으로 학습한 뒤 결합한 2-stage 구조를 띈다. 또한 주의 집중 기법을 사용하여 시스템의 성능을 향상시키고자 하였다. 제안하는 시스템에 대한 구동과 성능 평가는 소형 그래픽 처리 유닛인 Nvidia Jetson Nano에서 진행하였다.

• 대한건축학회논문집:계획계
• /
• 제34권1호
• /
• pp.95-102
• /
• 2018

Public spaces in the cities are social and economic resources to maintain sustainable urban revitalization. As an importance of public spaces is getting increased, many cities focus on public space management and introduce their own management system. NYC Plaza Program is one of the public space management systems in USA and it was designed in order to transform underused roads and streets into pedestrian public spaces throughout the New York City. Plaza management system works with private organizations' participation as NYC Department of Transportation empowers selected private organizations to the right of management and assists their efforts. In this study, we focused on how the plazas are managed by private sectors and seek to find out characteristics of types of management methods based on landuse(residential, commercial and openspace) status around plazas. We analyzed 61 plazas that generated by NYC Plaza Program with three major conditions of management system including organization, fund and activities. There are three major findings from the analysis. 1)In most residential surrounded plazas, resident-initiative organizations manage small scaled fund and activities meanwhile public agencies support their management. 2)BID is a dominant tool in the commercial surrounded plazas. BID provides with secured fund, mid-sized activities and a broad network with commercial facilities. 3)Openspace-surrounded types are usually using supports of exiting organizations and fund system.

• 한국디지털건축인테리어학회논문집
• /
• 제13권4호
• /
• pp.95-108
• /
• 2013

The purpose of this study is to analyze and to grasp Peter Calthorpe's urbanism through the process that is compared with various developments of urban design field for the preservation of global environment. From this study, Peter Calthorpe's urbanism for global environment is comprehended according to design stages. As a design goal, He seeks a green urbanism that puts emphasis on land use and transportation. As a urban planning, he devises urban footprint for the tool of evaluation and urban planning, and proposes five place types toward mixed-use development, and advocates Transect for eco-friendly land use. As a urban design, he devises urban network model for transportation network based on accessibility, and devises TOD and TOC model for preventing urban sprawl and mitigating carbon emissions, and advocates TND model for pedestrian-friendly space and community life. He makes importance of urban design. Because he thinks that integrative solution is required to global environment and urban design of integrative characteristic is suitable to preserve global environment. The results of this study are summarized as the followings: First, type classification of urbanism for the preservation of global environment and grasping purposes, methods, characteristics according to the types. Second, grasping characteristics and location of Peter Calthorpe's urbanism as a green urbanism. Third, proposing the direction of improvement for our urban planning and design.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 추계종합학술대회
• /
• pp.950-953
• /
• 2007

본 논문에서는 인간과 환경사이의 물리적 또는 심리적 인터액션을 통한 인간중심의 적절한 서비스를 제공하는 공간지능화(iSpace: Intelligent Space) 구현하고자 네트웍 센서 인식공간을 소개하고 있다. 영상 데이터 처리 및 정보 네트웍 기능을 갖는 다수의 컬러 CCD 카메라를 iSpace 공간에 분산 배치하였다. iSpace내의 정보획득을 위한 네트웍 센서를 분산 지능형 네트웍 디바이스(DIND: Distributed Intelligent Network Devices)라고 명명하고 있으며, 각 DIND는 일종의 클라이언트 역할을 수행하도록 하였으며, DIND는 카메라 센서를 이용하는 이른바 카메라 네트워크를 구성한 것으로 이를 통해 실내 환경을 인식하고 모델링 하며 공간 내 거주자의 의도를 인식하기 위한 시스템을 구축하였다.

• 한국지능시스템학회논문지
• /
• 제21권4호
• /
• pp.475-480
• /
• 2011

본 논문에서는 충돌 위험도 판단 시스템을 제안한다. 먼저 칼만 필터를 이용하여 보행자의 정보를 예측하고, 몬테 카르롤로 모의 실험과 신경 회로망을 이용해 충돌 확률을 계산한다. 그리고 과거의 충돌 확률 정보를 이용하여 충돌확률을 예측한다. Belief 충돌 예측 방법은 현재뿐만 아니라, 과거의 필터링 정보를 모두 이용하여 충돌 확률을 에측한다. 마지막으로 컴퓨터 시뮬레이션으로 제안된 알고리즘의 성능을 확인한다.

• 한국안전학회지
• /
• 제35권5호
• /
• pp.74-85
• /
• 2020

Smart phone zombie or Smombie means pedestrians who walk without attention to their surroundings because they are focused upon their smart phone. Because the traffic accidents and injuries caused by Smombie have been increased rapidly in recent years, the social attention and policies are needed to prevent it. This study was conducted to analyze Smombie's current status and some solutions used before and to propose new improved method through the latest ICT trend. In this study, we did the field survey to check Smombies at several places in Seoul through people counting, and found that a lot of pedestrians still use the smart phone while walking. And we analyzed many case studies about some solutions to prevent Smombies previously. The case studies include legal regulations, government policies, smart phone app services and facilities that are used before. We studied them through internet searches and reference studies and we also checked the current operating situation as visiting several places that the solutions actually has been operated. Therefore, we found there are some limitations in previous solutions in terms of effectiveness and management. To consider new solution that can be expected to overcome the limitations, we analyzed the latest ICT trends focused on features to utilize the Smombie prevention, especially video recognition and digital signage. In these days, video recognition has been developed rapidly with assistance of AI technology and it can recognize the specific pedestrian's characteristics such as holding smart phone as well as hair style, clothes, backpack and etc. On the other hands, the digital signage is the convergence device that includes big display, network connection and various IoT sensors. It can be used as public media in many places for public services as well as advertising. Through these analysis results, we show the requirements and the user scenario for the improved method to prevent Smombie. Finally, we propose to develop R&D technology to recognize Smombie exactly as pedestrian attributes and to spread creative contents to increase pedestrian's interest and engagement for Smombie prevention through digital signage.

• 로봇학회논문지
• /
• 제2권1호
• /
• pp.21-28
• /
• 2007

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. And the article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguity conditions. We propose to track the moving objects by generating hypotheses not in the image plan but on the top-view reconstruction of the scene. Comparative results on real video sequences show the advantage of our method for multi-object tracking. Also, the method is applied to the intelligent environment and its performance is verified by the experiments.

• 한국멀티미디어학회논문지
• /
• 제12권1호
• /
• pp.97-106
• /
• 2009

무선 근거리 통신망 환경의 측위 전략은 정확도는 떨어지지만 측위를 위한 특수 장비가 필요 없다는 점에서 매력이 있다. 본 논문은 무선 근거리 통신망 환경에서 옥내 이동 물체의 제적을 의사 결정 트리기법을 이용한 측위 방법으로 측정하고, 측정치가 실제 궤적과 다르지 않음을 통계적으로 검정함으로써 이렇게 얻은 궤적을 실제 응용 시스템 개발에 사용하여도 좋다는 이론적 근거를 제공한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.46-51
• /
• 2005

Intelligent Space(ISpace) is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human following by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. And the article presents the integration of color distributions into particle filtering. Particle filters provide a robust tracking framework under ambiguity conditions. We propose to track the moving objects by generating hypotheses not in the image plan but on the top-view reconstruction of the scene. Comparative results on real video sequences show the advantage of our method for multi-object tracking. Simulations are carried out to evaluate the proposed performance. Also, the method is applied to the intelligent environment and its performance is verified by the experiments.

• 경영과학
• /
• 제33권1호
• /
• pp.49-58
• /
• 2016

Focusing on the drastic increase of smart devices, machine generated data expansion is a general phenomenon in network services and IoT (Internet of Things). Especially, built-in multi sensors in a smart device are used for collection of user status and moving data. Combining the internal sensor data and environmental information, we can determine landmarks that decide a pedestrian's locations. We use an ANOVA method to analyze data acquired from multi sensors and propose a landmark classification algorithm. We expect that the proposed algorithm can achieve higher accuracy of indoor-outdoor positioning system for pedestrians.