• Title/Summary/Keyword: 추돌사고

Search Result 107, Processing Time 0.019 seconds

An Overloaded Vehicle Identifying System based on Object Detection Model (객체 인식 모델을 활용한 적재 불량 화물차 탐지 시스템)

  • Jung, Woojin;Park, Jinuk;Park, Yongju
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.12
    • /
    • pp.1794-1799
    • /
    • 2022
  • Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. therefore we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Also, we propose an integrated system for tracking the detected vehicles. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data.

Smart Electric Wheelchair using Eye-Tracking (아이트래킹을 이용한 스마트 전동휠체어)

  • Kim, Tae-Sun;Yoon, Seung-Mok;Kim, Tae-Seong;Park, Hyeon-Kyeong;Park, Seong-Hwan;Kim, Woo-Jong;Jeong, Sang-Su;Jang, Young-Sang;Jung, Hyo-Jin;Park, Su-Bin
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2020.07a
    • /
    • pp.259-260
    • /
    • 2020
  • 기존의 전동휠체어를 사용하는 약자 또는 중증 장애인 등 지체(肢體)가 불편한 사람들이 휠체어 사용 시 생기는 문제점을 해소할 목적으로 시작되었다. 이는 전동휠체어가 보행 기구임에도 자동차에 준하는 교통사고에 대해 무방비하게 노출되고, 중증 장애인에 대한 이동권 보장이 아직 미흡하여 생기는 문제이다. 따라서 본 연구에서는 이러한 문제로 인한 불편함을 해소하고자 아이트래킹을 이용한 스마트 전동휠체어 기술을 적용하고자 한다. 루게릭병 등으로 인해 지체(肢體)의 움직임에 제한이 있는 사람들에게 보호자가 밀어주는 휠체어에 의존하는 것이 아닌 Eye-Tracker를 이용한 시선 추적(Eye-Tracking) 기술로 휠체어 동작이 가능하다. Web-Cam과 라즈베리 파이를 통해 얻은 전·후·좌·우의 영상정보를 디스플레이 화면에 송출한다. 그 후 Eye-Tracking 기술을 이용해 디스플레이 화면에 표시된 전·후·좌·우 이동에 관한 UI(User Interface)룰 사용자가 송출된 영상을 보면서 눈의 움직임만으로 선택해 휠체어의 방향을 제어한다. 또한 전동휠체어의 조작 실수로 다른 행인 또는 장애물과 충돌하는 문제점을 초음파 센서를 이용하여 일정 거리 내에 사물이나 사람이 있을 경우 디스플레이 화면에 경고표시 및 경고음, 각 초음파 센서 위치에 맞는 LED작동으로 사용자들에게 추돌 위험경고와 함께 장애물의 위치파악이 가능하도록 한다. 따라서 스마트 전동휠체어를 통하여 수동적인 움직임이 아닌 능동적이고, 초음파 센서로 인해 안전한 이동이 가능하게 한다.

  • PDF

Development and Evaluation of Traffic Conflict Criteria at an intersection (교차로 교통상충기준 개발 및 평가에 관한 연구)

  • 하태준;박형규;박제진;박찬모
    • Journal of Korean Society of Transportation
    • /
    • v.20 no.2
    • /
    • pp.105-115
    • /
    • 2002
  • For many rears, traffic accident statistics are the most direct measure of safety for a signalized intersection. However it takes more than 2 or 3 yearn to collect certain accident data for adequate sample sizes. And the accident data itself is unreliable because of the difference between accident data recorded and accident that is actually occurred. Therefore, it is rather difficult to evaluate safety for a intersection by using accident data. For these reasons, traffic conflict technique(TCT) was developed as a buick and accurate counter-measure of safety for a intersection. However, the collected conflict data is not always reliable because there is absence of clear criteria for conflict. This study developed objective and accurate conflict criteria, which is shown below based on traffic engineering theory. Frist, the rear-end conflict is regarded, when the following vehicle takes evasive maneuver against the first vehicle within a certain distance, according to car-following theory. Second, lane-change conflict is regarded when the following vehicle takes evasive maneuver against first vehicle which is changing its lane within the minimum stopping distance of the following vehicle. Third, cross and opposing-left turn conflicts are regarded when the vehicle which receives green sign takes evasive maneuver against the vehicle which lost its right-of-way crossing a intersection. As a result of correlation analysis between conflict and accident, it is verified that the suggested conflict criteria in this study ave applicable. And it is proven that estimating safety evaluation for a intersection with conflict data is possible, according to the regression analysis preformed between accident and conflict, EPDO accident and conflict. Adopting the conflict criteria suggested in this study would be both quick and accurate method for diagnosing safety and operational deficiencies and for evaluation improvements at intersections. Further research is required to refine the suggested conflict criteria to extend its application. In addition, it is necessary to develope other types of conflict criteria, not included in this study, in later study.

A Study on the Effects of High-lift Rudder on Ship's Maneuverability (고 양력 타가 선박의 조종성능에 미치는 영향에 관한 연구)

  • Kim, Sang-Hyun;Kim, Hyun-Jun;Jun, Hee-Chul;Yoon, Seung-Bae;Park, Hwa-Pyeong;Gim, Ok-Sok
    • Journal of the Korean Society of Marine Environment & Safety
    • /
    • v.16 no.4
    • /
    • pp.393-399
    • /
    • 2010
  • Recently, a vessel's maneuvering performance is considered to be an important subject as marine pollution from the ships that stranded on a rock becomes more severe. So, IMO(International maritime organization) has adopted Resolution MSC.l37 to enhance international standards of ship's maneuverability. There's more than one way to improve ship's maneuverability. This research focused on improving ship's maneuverability by high-lift rudder. To predict the maneuverability, the numerical simulation model was used. The evaluation of maneuverability was carried out by turning test and zig-zag test. The results obtained with these simulation showed that the high-lift rudder would be effective in improving the turning ability of the ship. But it was clarified that there Has a possibility that course changing ability night become bad through an increase of rudder lift.

Mechanical Properties of Laser-Welded Multi-Material Tailor-Welded Blanks (레이저 TWB된 이종접합강의 기계적 특성)

  • Nam, Ki-Woo;Park, Sang-Hyun;Lee, Kyu-Hyun;Lee, Mun-Yong
    • Transactions of the Korean Society of Mechanical Engineers A
    • /
    • v.36 no.8
    • /
    • pp.857-863
    • /
    • 2012
  • In this study, tailor-welded blanks(TWB) were formed between high-strength steel(SABC1470) and cold rolled steels(SPFH590 and SPFC980) to improve passenger safety and reduce the weight of cars. Multi-material TWB specimens were highly strengthened through the heat treatment of SABC1470. The change in tensile strength caused by the stand-by time until water cooling after stamping and the deformation behavior of high-speed bending in a statically indeterminate condition such as in the center-pillar were evaluated. Multi-material TWB specimens that were heat-treated at the same temperature tended to show a decrease in tensile and yield strength, depending on the stand-by time until water cooling. On the other hand, Multi-material TWB specimens(SABC1470+SPFH590) that were heat treated at $850^{\circ}C$ showed good properties that were suitable for ensuring passenger safety in car accidents. From the viewpoint of passenger safety, it is best to use SABC1470 and SPFH590 in the upper and lower area of the center-pillar, respectively.

A Study on Side Impact from Car-to-Car using Finite Element Analysis (유한요소해석을 이용한 차대차 측면충돌에 대한 연구)

  • Han, Yuong-Kyu;Baek, Se-Ryong;Yoon, Jun-Kyu;Lim, Jong-Han
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.15 no.3
    • /
    • pp.201-209
    • /
    • 2015
  • The deformed degree of car body varies largely with the collision part from side collision of car-to-car. In case of deformation of car body caused by collision, the movement is different as speed energy changes to strain energy. Generally, in the analysis of traffic accident, the movement of car after the collision is analyzed by law of conservation of motion and the error of energy absorption rate along the deformation of car body can be calibrated by inputting coefficient of restitution, but it is current situation that coefficient of restitution applied by referring to the research results of forward collision and backward collision because the research results of side collision is rare. Vehicle model of finite element method applied by structure of car body and materials of each component was analyzed by explicit finite element method, and coefficient of restitution and collision detection time along contact part of side collision was drawn by analyzing the results. Analysis result acquired through the law of conservation momentum by applying finally-computed coefficient of restitution and crash detection time compared to collision result of actual vehicle. As a result, the reliability of analysis was higher than the existing analysis method were acquired when applying the drawn initial input value that used finite element method analysis model.

An Overloaded Vehicle Identifying System based on Object Detection Model (객체 인식 모델을 활용한 적재불량 화물차 탐지 시스템 개발)

  • Jung, Woojin;Park, Yongju;Park, Jinuk;Kim, Chang-il
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2022.10a
    • /
    • pp.562-565
    • /
    • 2022
  • Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. However, this irregular weight distribution is not possible to be recognized with the current weight measurement system for vehicles on roads. To address this limitation, we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles from the CCTV, black box, and hand-held camera point of view. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data. From the result, we believe that public big data can be utilized more efficiently and applied to the development of an object detection-based overloaded vehicle detection model.

  • PDF