• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.1115-1117
• /
• 2010

안전운전 지원 시스템 개발을 위해서 고려되어야 할 요소는 차량정보, 운전자정보, 외부 환경정보가 있다. 기존의 안전운전 지원 시스템 개발은 주로 차량의 종방향 제어, 횡방향 제어, 조향각 제어 등 차량으로부터 직접 추출한 주행정보를 이용하여 운전자의 안전유무를 평가하였다. 그러나 최근의 조사결과에 따르면 교통사고의 90%이상이 운전자 실수에 의해서 발생한다는 것을 알 수 있다. 이와 관련하여 차량의 주행 정보뿐만 아니라 실제 운전자가 주행 중에 행하게 되는 행동정보기반의 안전운전지원시스템 개발이 활발히 연구되어 지고 있다. 본 논문에서는 운전자의 행동정보를 이용한 안전운전 평가시스템의 설계 개념과 안전운전 평가시스템의 핵심 요소인 표준모델 구축 방법에 대해서 논의하고자 한다.

• Journal of the HCI Society of Korea
• /
• v.4 no.2
• /
• pp.1-8
• /
• 2009

User-centered design aims to develop device naturally without the interference of user' s conscious and unconscious behavior. Accordingly, designers need to understand their user's requirements, observe user behavior and interaction in the real environment. However, existing observations suggested a vast range of analysis system and observation techniques which are often ambiguous to the designers. Therefore, this research is aimed to propose an observation system for collecting data from user's behavior. In order to do so, we define the components and behavior level within the context of driving.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.330-332
• /
• 2017

최근 차량사고는 운전자의 운전 행동이 많은 비중을 차지하며 행동이 올바르지 못했을 경우 주의가 분산되어 사고가 발생하고 있다. 자동차 업계에서는 자율주행 기술의 출현으로 운전자의 운전환경이 변화되고 있다. 차량 서비스들은 차량에 부착된 센서들을 이용한 다양한 차량 서비스가 개발되고 있으며 차량 서비스는 도로주변 환경과 운전자의 안전에 집중된 서비스가 대부분이다. 하지만 차량에 부착된 센서들의 성능문제로 인한 기능적 문제점으로 상용화가 늦어지고 있다. 본 논문에서는 사용자에게 효율적인 차량 서비스를 제공하기 위해 사용자의 음성을 활용한 상품구매 시스템을 제안한다. 본 시스템은 딥 러닝 기술이 적용된 DB를 통해 사용자의 음성데이터 분류를 통해 상품을 검색 및 구매할 수 있는 시스템이다. 제안된 시스템은 음성인식을 활용하여 별도의 과정 없이 간편하게 상품을 구매할 수 있으며, 사고의 위험으로부터 벗어날 수 있다.

• Journal of Korean Society of Transportation
• /
• v.29 no.3
• /
• pp.41-48
• /
• 2011

In order to detect driver's state in a driver safety system, both overt and covert measures such as driving performance, visual attention, physiological arousal and traffic situation should be collected and interpreted in the driving context. In this paper, we suggest a vehicle monitoring system that provides multimodal information on a broad set of measures simultaneously collected from multiple domains including driver, vehicle and road environment using an elaborate timer equipped as a soft synchronization mechanism. Using a master timer that records key values from various modules with the same master time of short and precise interval, the monitoring system provides more accurate context awareness through synchronized data at any given time. This paper also discusses the data collected from nine young drivers performing a cognitive secondary task through this system while driving.

• Korean Journal of Culture and Social Issue
• /
• v.8 no.1
• /
• pp.61-77
• /
• 2002

This study focuses on drivers' risk perception & construct in risk scene. The measures used were the scores of hazard perception, namely the subjects' evaluation of the degree of risk through the 'Q-sorting' with 30 drivers. The subjects were divided into 3 groups according to their evaluating score, Z-score, road users' hazard(type 1), environmental hazard(type 2), situational hazard(type 3). And ten constructs derived from Q-sorting were compared through 'consensus item analysis'. It suggest that there are different in constructs for risk perception. Then those results are discussed in terms of theoretical and practical implication of traffic safety including accidents analysis and drivers' education.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.135-141
• /
• 2006

In order to prevent traffic accident, it is very important that the driver regulates the location of rear view mirror using the automatic seat regulation system which guarantees the maximum vision of the possibility for accuracy. In order to solve this problem the paper deals with the automatic seat control system which guarantees comfortable and safe seating and good visual field. Also a automatic car seat control algorithm has been developed to regulate the back mirror. Particularly, the automatic seat control algorithm function for the air bag operation in case of an accident has been added depending on passengers weight. Moreover when the driver passes a dangerous area an algorithm has been developed which gives the driver a naming sign and has been simulated in a ubiquitous environment. The simulation result proved that the Intelligence analysis for traffic accidents can reduce franc accidents more than 25% than the currently existing methods.

• 한국HCI학회:학술대회논문집
• /
• 2008.02c
• /
• pp.150-151
• /
• 2008

With the proliferation of vehicles and advancement of Information Technology, the technology of Telematics, which provides valuable services to people by collecting and analyzing the information from drivers, vehicles and Telematics environments (e.g. traffic information, road condition, weather information, etc.), has been a hot research area in IT and automotive recently. As the information technology revolution brings more and more assistance for driver information processing becomes increasing important. Therefore, drivers' workload is very essential factor for safety driving in Telematics environment. For managing drivers' workload effectively, ETRI haven been developing vehicle and driver management system which can collect data from drivers and vehicle in realtime and analyze the data to manage drivers' and vehcles' status since 2007. This technology will apply to commercial vehicle telematics such as texi or truck management system in the future for increasing driving safety. In this presentation, I would like to explain what we had developed so far and discuss future direction.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.173-182
• /
• 2021

In this paper, we analyzed driver's and passenger's motions that cause driver's distraction, and recognized 10 driver's behaviors related to mobile phones. First, distraction-inducing behaviors were classified into environments and factors, and related recent papers were analyzed. Based on the analyzed papers, 10 driver's behaviors related to cell phones, which are the main causes of distraction, were recognized. The experiment was conducted based on about 100,000 image data. Features were extracted through SURF and tested with three models (CNN, ResNet-101, and improved ResNet-101). The improved ResNet-101 model reduced training and validation errors by 8.2 times and 44.6 times compared to CNN, and the average precision and f1-score were maintained at a high level of 0.98. In addition, using CAM (class activation maps), it was reviewed whether the deep learning model used the cell phone object and location as the decisive cause when judging the driver's distraction behavior.

• Journal of Korean Society of Transportation
• /
• v.18 no.6
• /
• pp.101-110
• /
• 2000

본 논문의 목적은 우리들의 현실적 노면표지 형태가 그 강도, 종류 및 출현빈도 측면에서 드러내는 지속적 증대 내지 강화 경향성을 문제점으로 제기하면서, 이런 노면표지 형태와 운전행동 간의 관련성에 대한 심리학적 제반 이론들을 고찰해보고 아울러 여기서 상호 연관적 특성을 밝혀주는 하나의 적절한 모델을 개발해보고자 하는 데에 두었다 이 모델에서는 운전자의 사고예방이나 안전운행이 곡 필요한 수준의 노면표지 자극화(stimulation)를 통해 조성된 쾌적한 교통환경에서 보다 용이하게 가능하다는 점이 전제되고 있다. 우리가 인간행동을 총체적으로나 효과적으로 분석하는 데 있어서는 일반심리적이거나 행동주의적 제반 이론 관점이 다소 미흡하다는 점이 지적되었다. 반면에 보다 거시적이고 종합적인 통찰에 중점을 두고있는 형태주의 심리학이나 장 이론적 시각은 행동분석 시에 비교적 결실적인 것으로 밝혀졌다 노면표지 자극의 양상여하가 운전자에게 스트레스, 정보과부담, 과도한 심리적 각성상태 등으로 인해 부정적인 영향을 미친다는 점에서는 이런 문제점이 환경심리학적 고찰측면에서도 관심의 대상이 되고 있다. \"노면표지 조성화 양 관점 모델\"에서 시사되고 는 터이지만. 이 모델에서의 노면표지 형태가 이론적인 면에서 \"정서-인지적\" 인간관에 근거를 두고있어 궁극적으로 이것이 옳다면, 그것은 곡 필요한 최소한의 수준에 머물러야 한다는 것이다. 올바른 운전행동, 다시 말해 교통법규 준수 행동은 노면표지 양상 측면의 각종 자극적 강화대책보다도 오히려 실효성 있는 교통교육, 확실한 적발 단속과 엄중한 처벌대책에 상대적으로 훨씬 더 큰 비중을 두고있는, 바로 그런 운전자의 의식개혁을 통해 비로소 제대로 정착될 수 있기 때문이다. 이 모델의 타당성 여부는 후속적 실증연구를 통해 해명되어질 수 있을 것이다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.2
• /
• pp.78-85
• /
• 2011

In this paper, a research on multi-agent is carried out in order to develop a system that can provide drivers with real-time route recommendation by reflecting Dynamic Environment Information which acts as an agent in charge of Driver's trait, road condition and Route recommendation system. DEI is equivalent to number of n multi-agent and is an environment variable which is used in route recommendation system with optimal routes for drivers. Route recommendation system which reflects DEI can be considered as a new field of topic in multi-agent research. The representative research of Multi-agent, the Prey Pursuit Problem, was used to generate a fresh solution. In this thesis paper, you will be able to find the effort of indulging the lack of Prey Pursuit Problem,, which ignored practicality. Compared to the experiment, it was provided a real practical experiment applying the algorithm, the new Ant-Q method, plus a comparison between the strategies of the established direction vector was put into effect. Together with these methods, the increase of the efficiency was able to be proved.