All Issue

2024 Vol.42, Issue 5 Preview Page

Article

Study on the Application of Black Box Image Recognition Techniques for Driving Safety Evaluation

주행 안전성 평가를 위한 블랙박스 영상 인식 적용 기법 연구

Junhan CHO1
,
Yoonyoung CHOI1
,
Sungjun LEE2
,
Juneyoung PARK3
,
Seongmin PARK4*
조 준한1
,
최 윤영1
,
이 성준2
,
박 준영3
,
박 성민4*
1Chief Reseacher, Samsung Traffic Safety Research Institute, Seoul 06626, Korea
2Master Student, Department of Transportation and Logistic Engineering, Hanyang University, Gyeonggi 15588, Korea
3Associate Professor, Department of Transportation & Logistics Engineering / Smart City Engineering, Hanyang University, Ansan 15588, Korea
4Senior Researcher, Mobility Policy Office, Korea Transportation Safety Authority, Gyeongbuk 39660, Korea
1삼성교통안전문화연구소 수석연구원
2한양대학교 교통물류공학과 석박사통합과정
3한양대학교 교통물류공학과, 스마트시티공학과 부교수
4한국교통안전공단 모빌리티정책처 선임연구원
*Corresponding Author
31 October 2024. pp. 595-607
PDF XML Citation
Abstract

To evaluate traffic safety, traffic accident data, navigation systems, driving recorders, and simulations are commonly used. However, these methods have limitations in identifying situations immediately before accidents occur. In contrast, black box camera footage can be obtained with the vehicle owner's consent and, with a 100% penetration rate, allows for comprehensive analysis of all vehicles. This study aims to analyze vehicle behavior in rear-end collision situations based on black box camera footage and to establish foundational data for future collision avoidance and response strategies for autonomous vehicles. To analyze rear-end collision black box camera footage, an image recognition algorithm based on OpenCV's YOLO5 is developed to perform object recognition in the footage. Additionally, algorithms are developed to predict the speed of preceding and following vehicles and to estimate the inter-vehicle distance. Real road driving experiments were conducted to train and calibrate the developed algorithms. Speeds and Time-to-Collision were extracted from 12 rear-end collision cases that occurred on highways. These 12 accidents were categorized into three groups based on speed, and the characteristics of each group were analyzed. Through this study, an algorithm was developed to analyze vehicle behavior immediately before rear-end collisions using black box camera footage. The further refinement of this algorithm and evaluation metrics is expected to advance video-based traffic accident analysis and contribute to the development of strategies for improving traffic safety in real road conditions.

Keywords
black box
image recognition algorithm
rear-end crash
time to collision
traffic safety

교통 안전성 평가는 교통사고 자료, 내비게이션 및 운행기록장치, 시뮬레이션 등을 주로 사용하고 있으나, 사고 발생 직전의 상황을 규명하는 데에는 한계가 있다. 블랙박스 영상의 경우 사고 발생 직전의 상황을 가장 잘 설명할 수 있는 데이터를 얻을 수 있으며, 차량 소유주의 동의를 얻으면 사고 영상을 쉽게 취득할 수 있고, 보급률이 100%에 달해 샘플 데이터 구득이 용이하다는 장점이 있다(Han and Yang, 2007). 본 연구는 블랙박스 영상에서 관련된 데이터를 추출하고, 후미추돌 교통사고 상황에서의 차량 행태를 분석하여 교통안전성을 평가하는 방법론을 제시하고자 한다. 이를 위해 후미추돌 교통사고의 블랙박스 영상 분석을 위하여 OpenCV의 YOLO5에 기반한 영상인식 알고리즘을 개발하여 블랙박스 영상에서의 객체 인식을 수행한다. 그리고 선행 및 후행 차량 속도를 예측하고 차간 거리를 추정하는 알고리즘을 개발한다. 실도로 주행실험을 통해 개발된 알고리즘의 학습 및 보정을 진행하였으며 고속도로 본선에서 발생한 12건의 후미추돌사고에 대해 각각의 속도 및 TTC를 추출하였다. 12건의 사고를 속도를 기준으로 3가지 그룹으로 나누어 각 그룹별 특성을 분석하였다. 본 연구는 블랙박스 영상을 통한 후미추돌사고 발생 직전의 차량 행태 분석을 위한 알고리즘을 개발하였으며, 추후 카메라를 이용한 영상분석에 기반한 안전성 분석 및 자율주행차량의 사고 회피 및 대응을 위한 기초자료를 구축할 때 활용될 수 있다. 또한, 알고리즘 및 평가지표의 고도화를 통하여 실 도로 상황에서의 교통안전성 증진을 위한 전략 수립에 기여할 수 있을 것으로 기대된다.

키워드
블랙박스
영상인식 알고리즘
후미추돌사고
TTC
교통안전
References
1

Calvi A., D'Amico F., Ferrante C., Ciampoli, L. B. (2020), A driving simulator study to assess driver performance during a car-following maneuver after switching from automated control to manual control, Transportation Research Part F: Traffic Psychology And Behaviour, 70, 58-67.

10.1016/j.trf.2020.02.014
2

Cunto F., Saccomanno F. F. (2008), Calibration and Validation of Simulated Vehicle Safety Performance at Signalized Intersections, Accident Analysis & Prevention, 40(3), 1171-1179.

10.1016/j.aap.2008.01.00318460386
3

Czajewski W., Iwanowski M. (2010), Vision-based Vehicle Speed Measurement Method, In International Conference on Computer Vision and Graphics, 308-315, Berlin, Heidelberg: Springer Berlin Heidelberg.

10.1007/978-3-642-15910-7_35
4

Dehghani A., Parsayan A. (2013), Single Camera Vehicles Speed Measurement, In 2013 8th Iranian Conference on Machine Vision and Image Processing (MVIP), 190-193, IEEE.

10.1109/IranianMVIP.2013.6779976
5

Gousios S., Garber N. (2009), Relationship between Time to Collision Conflicts and Crashes on Interstate Highways Dubjected to Truck Lane Restrictions, Transportation Research Board: Washington.

6

Han H.M., Park S.Y. (2017), Vehicle Detection and Inter-vehicle Distance Estimation using Smart Mobile Device, The Korean Institutes of Communications and Information Sciences Conference, 753-754.

7

Han I.H., Yang K.S. (2007), Recognition of Dangerous Driving using Automobile Black Boxes, J. Korean Soc. Transp., 25(5), Korean Society of Transportation, 149-160.

8

Jeong S.H. (2014), A Study on Detection and Distance Estimation of Forward Vehicle for FCWS: Forward Collision Warning System, Master Dissertation, Sungkyunkwan University.

9

Kim K.S., Cho J.S. (2012), Vision-based Vehicle Detection and Inter-vehicle Distance Estimation, Journal of the Institute of Electronics and Information Engineers-SP, 49(3), 1-9.

10

Kim T.H., Kang M.S. (2012), Driving Vehicle Detection and Distance Estimation using Vehicle Shadow, Journal of the Korea Institute of Information and Communication Engineering, 16(8), 1693-1700.

10.6109/jkiice.2012.16.8.1693
11

Ko J.E., Jang J.Y., Oh C. (2021), Assessing the Safety Benefits of In-Vehicle Warning Information by Vehicle Interaction Analysis in C-ITS Environments, J. Korean Soc. Transp., 39(1), Korean Society of Transportation, 1-13.

10.7470/jkst.2021.39.1.001
12

Ko K.H. (2018), An Estimating Algorithm of Vehicle Collision Speed through Images of Black box, Journal of Digital Convergence, 16(9).

13

National Police Agency (2022), Traffic Signal Installation Operation Guidelines

14

Oh C., Oh J.T., Song T.J., Park J.H., Kim T.J. (2009), Advanced Freeway Traffic Safety Warning Information System based on Surrogate Safety Measures (SSM): Information Processing Methods.

15

Park J.S., Kim G.S., Roh S.J., Cho J.S. (2015), Camera Calibration Method for an Automotive Safety Driving System, Journal of Institute of Control, Robotics and Systems, 21(7), 621-626.

10.5302/J.ICROS.2015.15.0055
16

Park S.H., Hwang J.W., Park G.H., Cho Y.J. (2023), Intelligent Driving Habit Analysis Service using Dash Cam Videos, Journal of Digital Contents Society, 24(1), 103-110.

10.9728/dcs.2023.24.1.103
17

Road Traffic Act Enforcement Rules Appendix 6 (2023), Korean Law Information Center, https://www.law.go.kr/ lsSc.do?section=&menuId=1&subMenuId=15&tabMenuId=81&eventGubun=060101&query=%EB%8F%84%EB%A1%9C%EA%B5%90%ED%86%B5%EB%B2%95+%EC%8B%9C%ED%96%89%EA%B7%9C%EC%B9%99#J15627329, 2023.7.14.

Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 42
  • No :5
  • Pages :595-607
  • Received Date : 2024-08-07
  • Revised Date : 2024-08-13
  • Accepted Date : 2024-09-02
  • DOI :https://doi.org/10.7470/jkst.2024.42.5.595
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close