• Smart Media Journal
• /
• v.12 no.11
• /
• pp.57-66
• /
• 2023

In this paper, we present a study on an AI-based system utilizing the CCTV system within city buses to predict the intentions of boarding and alighting passengers, with the aim of preventing accidents. The proposed system employs the YOLOv7 Pose model to detect passengers, while utilizing an LSTM model to predict intentions of tracked passengers. The system can be installed on the bus's CCTV terminals, allowing for real-time visual confirmation of passengers' intentions throughout driving. It also provides alerts to the driver, mitigating potential accidents during passenger transitions. Test results show accuracy rates of 0.81 for analyzing boarding intentions and 0.79 for predicting alighting intentions onboard. To ensure real-time performance, we verified that a minimum of 5 frames per second analysis is achievable in a GPU environment. his algorithm enhance the safety of passenger transitions during bus operations. In the future, with improved hardware specifications and abundant data collection, the system's expansion into various safety-related metrics is promising. This algorithm is anticipated to play a pivotal role in ensuring safety when autonomous driving becomes commercialized. Additionally, its applicability could extend to other modes of public transportation, such as subways and all forms of mass transit, contributing to the overall safety of public transportation systems.

• Transportation Technology and Policy
• /
• v.5 no.1
• /
• pp.161-171
• /
• 2008

아시아의 도시교통사고는 빠른 인구증가와 경제성장으로 인한 자동차 보급 확대로 인해 OECD 국가에 비해 2${\sim}$3배 높은 수준으로 교통사고절감을 위한 대안 마련이 시급한 실정이다. 이에 본고에서는 ITS기반 도로교통 안전시스템의 정착을 통해서 아시아 도시의 공통된 교통안전문제를 해소하기 위한 공동대응방안을 제시하고 있다. 이를 요약하면, 첫째, 도로사고와 ITS관계를 규명하고 사고요인을 도로상에서 제거할 수 있는 ITS기술을 소개하였다. 교통사고원인의 95%가 운전자관련인자로 나타나 운전자관련 ITS요소기술(HMI 등)의 개발이 시급한 것으로 나타났다. 또한 현재 도로 안전분야에서 적용 가능한 실용기술로는 돌발상황관리시스템, 충돌경고시스템, 비상연락시스템, 단속시스템 등인 것으로 판단된다. 둘째, ITS기반 도로교통 안전시스템의 조기 정착을 위해서는 기존 조직 법 제도의 정비가 필요하다. 아시아 도시에서는 ITS 도입 초기 정부주도형으로 추진하는 것이 바람직한데, 이를 위해서는 정부조직 내 ITS 전담기구 (Headquarter)를 신설하고, 도로안전 ITS관련 법령 및 ITS Master Plan에 근거한 권한과 사업, 예산을 확보해야한다. 또한 인프라 및 ITS 구축 운영과 함께 RSA(Road Safety Audit)와 같은 선진안전제도 시스템을 벤치마킹하여 국내 현실에 맞도록 접목시켜 나가야한다. 셋째, 교통관제 (광역)정보센터, 버스센터, 구간속도단속 등 혁신적인 도로안전사업을 지속적으로 발굴 확충하여 노하우를 축적해야 한다. 넷째, 아시아 도시의 공통된 교통문제를 해소하기 위한 공동대응방안을 마련하기 위하여 각국의 노하우를 전파하고 공유하는 창구로 아시아 태평양지역 ITS포럼을 더욱 육성해야 하겠다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.87-104
• /
• 2015

Currently the IoT (Internet of Things) environments and related technologies are being developed rapidly through the networks for connecting many intelligent objects. The IoT is providing artificial intelligent services combined with context recognition based knowledge and communication methods between human and objects and objects to objects. With the help of IoT technology, many research works are being developed using the C-ITS (Cooperative Intelligent Transport System) which uses road infrastructure and traveling vehicles as traffic control infrastructures and resources for improving and increasing driver's convenience and safety through two way communication such as bus-only lane and license plate recognition and road accidents, works ahead reports, which are eventually for advancing traffic effectiveness. In this paper, a system for deciding whether the traveling vehicle is possible or not to drive on bus-only lane in highway is researched using the lane and number plate recognition on the road in C-ITS traffic infrastructure environments. The number plates of vehicles on the straight ahead and sides are identified after the location of bus-only lane is discovered through the lane recognition method. Research results and experimental outcomes are presented which are supposed to be used by traffic management infrastructure and controlling system in future.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.01a
• /
• pp.177-178
• /
• 2021

우리나라 차량의 수는 매년 증가한다. 한 가구당 2대 이상의 차량을 가지고 있는 경우는 드물지 않다. 이는 도로의 포화를 발생시키고 교통사고의 원인이 된다. 본 연구에서는 안전성을 더욱 증가시키는 것을 전제로 아두이노를 이용한 초음파 센서와 라즈베리를 통한 블루투스 기술을 통해 LED 패널에 적용하고자 한다. 현재 많은 차량에는 후방 감지 센서와 차량 후방에서 다가오는 차량을 감지하는 센서 등을 사용하고 있다. 이 기술들은 운전자를 보호하는 장치이지만 모두 개인적으로 사용되는 장치이므로 다른 운전자를 보호하기 위한 장치가 필요하다. 또한, 이러한 시스템이 설치되어 있지 않은 차량이 많다. 추가로 설치하기 위해서 보다 큰 비용을 내야 하므로 적은 비용에 비해 큰 효율을 발생할 수 있는 가성비 좋은 장치가 필요하다. 본 논문은 이러한 문제점들을 개선하기 위해 버스에 장착된 LED 패널과 도로정비 차량 후방에 장착된 LED 패널에서 아이디어에 착안하여 '차량용 후방 안전 LED 패널' 기술을 제안한다. 기존에 글자를 이용해 단순히 의사소통이 가능한 LED 패널을 아두이노와 라즈베리 파이를 통해 사용자가 출력하고 싶은 문구를 실시간으로 출력하여 다른 운전자에게 정보를 전달할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.05a
• /
• pp.735-738
• /
• 2013

CAN(Controller Area Network)은 차량내부의 제어하기 위하여 디바이스, 센서, 액츄에이터 등을 연결하는 비동기 직렬버스 네트워크이다. 이 CAN은 ECU들 사이에 통신을 위해 효율적으로 사용되고 있다. 또한 CAN은 엔진 진단, ABS, 에어백 등과 같은 메시지를 전송하며 창문 조작, 전조등 등의 제어 명령들을 전송한다. 본 논문에서는 차량 네트워크 환경으로부터 차량상태를 WiFi 통신을 이용하여 운전자에게 스마트폰으로 제공하는 시스템을 구현하였다. 또한 차량의 연비관리, 차량 관리하는 차계부, 블랙박스 기능이 포함된 안드로이드 애플리케이션을 구현하였다.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.2
• /
• pp.42-49
• /
• 2021

In this paper, we proposes a study on the derivation of inspection factors for the periodic inspection of large buses equipped with AEBS and LDWS. we investigate the safety evaluation (NCAP) of domestic and foreign vehicles and safety standards for the two functions currently in operation and analyze the evaluation factors, measurement methods and evaluation scenarios and so on. In addition, the test scenario was derived by analyzing the vehicle safety evaluation data already held, Therefore, we use an real large bus and the inspection elements for the periodic inspection were derived.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.410-413
• /
• 2011

본 논문에서는 도로 영상에서 검출된 자동차 영상을 종류별 분류를 위해 효과적인 질감 특징정보 기반의 자동차 종류별 분류 방안을 제안한다. 제안한 연구에서는 운전자의 안전운전지원을 위해 도로상에서 검출된 자동차 영역과 자신의 차량과 거리를 추정하기 위해 검출된 자동차의 종류를 인식할 필요가 있다. 즉, 인식된 자동차의 종류에 따라 차량 간 거리를 추정에 필요한 파라미터로 사용할 수 있기 때문이다. 따라서 본 연구에서는 검출된 자동차 영상들로부터 GLCM(gray-level co-occurrence matrix)의 7가지의 특징정보들을 추출하고 SVM을 사용하여 학습 한 후 자동차의 종류(승용, 화물, 버스)를 분류하는 방법을 제안한다. GLCM은 영상이 가진 질감 정보를 효율적으로 분석함으로써 영역의 밝기 변화 정도, 거침 정도, 픽셀 분포 정도 등을 표현하기 때문에 영상내의 포함된 영역을 분류하는데 효과적이다. 제안한 방법을 실제 자동차 규모별 분류에 적용한 결과 약 83%의 분류 성공률을 제시하였다.

• Journal of Korean Society of Transportation
• /
• v.35 no.5
• /
• pp.423-433
• /
• 2017

During recent 5 years, it was recorded that 20% of total accident frequency and 30% of total number of death have been occurred due to drowsy driving. Drowsy driving accident is result from the loss of driving ability due to driver's accumulated fatigue. Continuous driving time can be measured as a surrogate variable to quantify the level of fatigue. The main purpose of this research is to investigate statistical correlation between the proportion of continuous driving vehicle (more than 2 hours) and the number of drowsy accidents. To carry this out, continuous driving time was measured using GPS route-guidance trajectory data. Also, accident frequency, traffic volume and segment length were collected to estimate safety performance function (SPF) for Jungbunearuk expressway in Korea. Through various types of estimated SPFs, statistical correlation was analyzed based on estimated statistical indices. This research can provide theoretical background for enforcement to regulate commercial vehicle driver's continuous driving time. In addition, throughout the trajectory data expansion, it is expected that strategy for anti-drowsy driving facilities installation can be established based on the suggested methodology.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4367-4373
• /
• 2010

The purpose of this study was to compared the effectiveness of erector spine taping and lumbar taping maintained in bus driver's back pain. The research subjects were some bus drivers working in Changwon, Masan, and Busan terminal. And we concluded this research; By selecting a group of 15 people taping erector spine, a group of lumbar taping, and a control group of 15 people randomly. Because we measured them before treatment and two weeks after treatment by the time, we could get the results which were as follows. The experiment group applied of taping therapy would be reduced in back pain when compared to the control group. The experiment group applied of taping therapy would be improved in muscle flexibility when compared to the control group. After treatment, the experiment group compared to control group showed decrease pain and an increase of flexibility. In conclusion, we could know that taping reduces back pain of bus drivers and gives a positive impact to muscle flexibility improvement, we finded out a distinct difference between the erector spine taping and the lumbar taping. Thus, the taping treatment can be applied easily to the bus driver and used as a way of therapeutic approach.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.6
• /
• pp.49-59
• /
• 2012

Recently, various alternatives for safety and efficiency of commercial vehicles have been considered, and one of the new alternatives is the application of a digital tachograph. In Korea, the installation of a digital tachograph to commercial vehicles was regulated from 2011 and Korea Transportation Safety Authority developed e-TAS to analyze the monitoring data from digital tachographs installed in the order of 100 commercial vehicles. This study performs the potential impact analysis of the DTG installation, which includes a trend of dangerous driving, a trend of traffic accidents and cost-effective analysis, a trend of fuel consumption and cost-effective analysis, a cost-effective analysis of social benefits using e-TAS data. Depending on the frequency of dangerous driving, the participants are divided into three groups; high-dangerous group, average-dangerous group and low-dangerous group. The high-dangerous driving group shows lower km/liter than the low-dangerous driving group by 15% for buses and taxis and by 30% for trucks. About $CO_2$ emission, the difference becomes bigger; 25%, 25% and 42% for buses, taxis and trucks, respectively. Although this study is a short-term period analysis, the methodology will be applicable for the long-term period analysis with larger data.