• 한국정보통신학회논문지
• /
• 제25권12호
• /
• pp.1723-1728
• /
• 2021

C-ITS는 차량, 도로 인프라, 운전자, 보행자 등 구성요소 간 교통정보를 수집·관리·제공함으로써 교통 이용 편의, 교통안전을 제고 할 수 있는 지능형교통시스템이다. 국내에서는 C-ITS 사업을 통해 도로인프라가 국내 전역에 구축되고, 실시간 교통정보 제공, 버스운행 관리 등 다양한 서비스가 제공되고 있다. 그러나 현재 도로상황 인지·전파 등을 통한 교통안전 중심의 C-ITS를 구축하기에는 첨단도로 인프라 및 정보 연계 체계가 미흡한 실정이다. 본 논문에서는 다양한 공간적 측면에서 시간의 연속성을 고려하여, 교통 인프라 간 정보 연계를 통해 교통흐름과 돌발 사고를 인지할 수 있는 그룹형 Zigbee Mesh 네트워크 기반 교통상황인지 시스템을 제시하였다. 제안하는 시스템은 1차적으로 현장에서 사고감지 및 경보 등의 대응이 가능하며, 타 시스템과의 정보 연계를 통해 보다 다양한 교통정보 서비스로의 활용이 가능할 것으로 기대한다.

• 대한의용생체공학회:의공학회지
• /
• 제18권3호
• /
• pp.315-323
• /
• 1997

Driving is a complex vigilance task that includes improper lookout, excessive speed and inattention. The primary objective of this research is to detect driver drowsiness so that the driver can be alerted to an impending traffic accident in performance. We developed the automatic detection and warning system during drowsy driving. A drowsiness detection system must be able to monitor driver status and detect the detrimental changes of a driver performance. Eyeblink has been found to be a reliable factor of drowsiness detection in earlier studies. As an additional parameter, we also considered the yawning which often occurs in a low vigilance state and predicts the drowsy state. We used a computer vision method to extract the eyeblink and yawning in the face image sequences. When the drowsy state was detected, the driver was refreshed by alarming device and menthol scent generator after deciding the warning level by fuzzy logic. For the evaluation of our system, we measured the physiological parameters such as EOG and EEG. The results indicated that it is possible to detect and alert the driver drowsiness temporarily or continuously by using our system.

• 한국전자통신학회논문지
• /
• 제17권6호
• /
• pp.1229-1236
• /
• 2022

본 논문에서는 고속도로에서 주행시 2차 사고를 방지하기 위한 사고인식 스마트 가로등에 대해 연구하였다. 가로등에 아두이노 및 센서를 활용하여 운전자에게 기상 상태를 알리고, 햇빛 및 야간 주행 차량에 따른 LED 밝기 조절과 같은 기능을 삽입하였고, 라즈베리파이 카메라 OpenCV를 활용해 텐서플로우 라이트 프로그램을 이용하여 각종 교통사고, 자연재해 및 야생동물 출현을 Deep Learning을 한 후 그 장면들을 인식하여 고속도로에서 일어날 수 있는 사고들을 감지하여 운전자에게 알려주며 각종 2차 사고를 예방하는 것을 보였다.

• 자동차안전학회지
• /
• 제4권1호
• /
• pp.27-32
• /
• 2012

Recently, in order to reduce traffic accident related fatalities, increasing number of studies are conducted regarding the vehicle safety enhancement devices. But very few studies about test procedures and requirements for vehicle safety systems are being carried out. Since BSD, as one of the most important safety features, is installed on a new vehicle, its performance test method has to be evaluated. Independent factors irrelevant to the device types including collision position, vehicle speed and closing speed are used to calculate test distance away from the current vehicle. Effect of roadway geometry as radius of curvature is introduced to propose possible misjudgement of following vehicle as adjacent one. The study results would be utilized to enhance the test procedure of BSD performance.

• 자동차안전학회지
• /
• 제11권3호
• /
• pp.7-12
• /
• 2019

AEB (Autonomous Emergency Braking system), a system in which vehicles automatically recognize forward objects or pedestrians and actively brake when forward collisions are expected, has been mandated by NHTSA (National Highway Traffic Safety Administration) and IIHS (Insurance Institute for Highway Safety) for all vehicles sell in the United States since 2022, and AEB research is also actively underway in korea. In this study, it can be confirmed that the passenger injury is reduced according to the AEB detection distance when it is assumed that the AEB is mounted in the actual event generated from KIDAS (Korea New Car Assessment Program) data through various analysis programs.

• 대한원격탐사학회지
• /
• 제39권1호
• /
• pp.77-86
• /
• 2023

Ship detection is widely used in areas such as maritime security, maritime traffic, fisheries management, illegal fishing, and border control, and ship detection is important for rapid response and damage minimization as ship accident rates increase due to recent increases in international maritime traffic. Currently, according to a number of global and national regulations, ships must be equipped with automatic identification system (AIS), which provide information such as the location and speed of the ship periodically at regular intervals. However, most small vessels (less than 300 tons) are not obligated to install the transponder and may not be transmitted intentionally or accidentally. There is even a case of misuse of the ship'slocation information. Therefore, in this study, ship detection was performed using high-resolution optical satellite images that can periodically remotely detect a wide range and detectsmallships. However, optical images can cause false-alarm due to noise on the surface of the sea, such as waves, or factors indicating ship-like brightness, such as clouds and wakes. So, it is important to remove these factors to improve the accuracy of ship detection. In this study, false alarm wasreduced, and the accuracy ofship detection wasimproved by removing wake.As a ship detection method, ship detection was performed using machine learning-based random forest (RF), and convolutional neural network (CNN) techniquesthat have been widely used in object detection fieldsrecently, and ship detection results by the model were compared and analyzed. In addition, in this study, the results of RF and CNN were combined to improve the phenomenon of ship disconnection and the phenomenon of small detection. The ship detection results of thisstudy are significant in that they improved the limitations of each model while maintaining accuracy. In addition, if satellite images with improved spatial resolution are utilized in the future, it is expected that ship and wake simultaneous detection with higher accuracy will be performed.

• 대한임베디드공학회논문지
• /
• 제7권6호
• /
• pp.339-343
• /
• 2012

Security and monitoring system has many applications and commonly used for detection, warning, alarm, etc. As the networking technology advances, user requirements are getting higher. An intelligent and cooperative surveillance system is proposed to meet current user demands and improve the performance. This paper focuses on the implementation issue for the embedded intelligent surveillance system. To cover wide area cooperative function is implemented and connected by wireless sensor network technology. Also to improve the performance lots of sensors are employed into the surveillance system to reduce the error but improve the detection probability. The proposed surveillance system is composed of vision sensor (camera), mic array sensor, PIR sensor, etc. Between the sensors, data is transferred by IEEE 802.11s or Zigbee protocol. We deployed a private network for the sensors and multiple gateways for better data throughput. The developed system is targeted to the traffic accident detection and alarm. However, its application can be easily changed to others by just changing software algorithm in a DSP chip.

• 디지털융복합연구
• /
• 제14권8호
• /
• pp.253-259
• /
• 2016

차선의 인식을 위한 연구는 차량의 자율 주행 또는 교통사고의 예방을 위하여 지속적인 연구가 진행되고 있으며, 최근에는 다양한 알고리즘이 등장하여 차선 인식과 검출은 비약적으로 발전하였다. 이들 연구는 주로 비전 시스템 기반의 연구이며 인식률 또한 상당히 좋아 졌다. 그러나 야간의 도로 또는 우천 시에는 그 인식률이 아직 만족할 수준까지 도달하지는 못하였다. 본 논문은 이러한 비전 시스템 기반의 차선 인식 및 검출의 단점을 개선하여 사고 발생 후 대응을 위한 센서 융합 기술을 적용하여 차선 검출에 대한 연구를 수행하였고, 차선 검출에 대한 연구 중 곡선차선의 검출에 대한 연구를 진행하였다. 도로는 직선도로 뿐만 아니라 다양한 곡선도로까지 검출 가능해야 하며 이는 교통사고 조사 시에 활용될 수 있다. 커브의 굽은 정도를 나타내는 곡률의 임계값을 0.001~0.06로 하여 곡선자선을 산출해 낼 수 있음을 보였다.

• 한국정보통신학회논문지
• /
• 제26권12호
• /
• pp.1794-1799
• /
• 2022

최근 증가하고 있는 도로 위 적재 불량 화물차는 비정상적인 무게 중심으로 인해 물체 낙하, 도로 파손, 연쇄 추돌 등 교통안전에 위해가 되고 한번 사고가 발생하면 큰 피해가 유발할 수 있다. 하지만 이러한 비정상적인 무게 중심은 적재 불량 차량 인식을 위한 주행 중 축중 시스템으로는 검출이 불가능하다는 한계점이 있다. 본 논문에서는 이러한 사회 문제를 야기하는 적재 불량 차량을 관리하기 위한 객체 인식 기반 AI 모델을 구축하고자 한다. 또한 AI-Hub에 공개된 약 40만 장의 데이터셋을 비교 분석하여 전처리를 통해 적재 불량 차량 검지 AI 모델의 성능을 향상시키는 방법을 제시한다. 또한 객체 추적을 통해 실시간 검지를 수행하는 방법을 제안한다. 이를 통해, 원시 데이터를 활용한 학습 성능 대비 약 23% 향상된 적재 불량 차량의 검출 성능을 나타냄을 보였다. 본 연구 결과를 통해 공개 빅데이터를 보다 효율적으로 활용하여, 객체 인식 기반 적재 불량 차량 탐지 모델 개발에 적용할 수 있을 것으로 기대된다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2010년도 춘계학술대회 논문집
• /
• pp.1112-1117
• /
• 2010

The intelligent safety system for level crossing which employs information and communication technology has been developed in USA and Japan, etc. But, in Korea, the relevant research has not been performed. In this paper, we analyze the cause of railway level crossing accidents and the inherent problem of the existing safety equipments. Based on analyzed results, we design the intelligent safety system which prevent collision between a train and a vehicle. This system displays train approaching information in real-time at roadside warning devices, informs approaching train of the detected obstacle in crossing areas, and is interconnected with traffic signal to empty the crossing area before train comes. Especially, we present the video based obstacle detection algorithm and verify its performance with prototype H/W since the abrupt obstacles in crossing areas are the main cause of level crossing accidents. We identify that the presented scheme detects both pedestrian and vehicle with good performance. Currently, we demonstrate developed railway crossing intelligence system at one crossing of Young-dong-seon line of Korail with Sea Train cockpit.