The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Traffic Data Calculation Solution for Moving Vehicles using Vision Tracking

Vision Tracking을 이용한 주행 차량의 교통정보 산출 기법

  • Park, Young ki (Graduate School of Nano IT Design Fusion, Seoul National University of Science & Technology) ;
  • Im, Sang il (Graduate School of Nano IT Design Fusion, Seoul National University of Science & Technology) ;
  • Jo, Ik hyeon (Signtelecom Co.) ;
  • Cha, Jae sang (Dept. of Electronics & IT Media Eng., Seoul National University of Science and Technology)
  • 박영기 (서울과학기술대학교 나노IT디자인융합대학원) ;
  • 임상일 (서울과학기술대학교 나노IT디자인융합대학원) ;
  • 조익현 ((주)싸인텔레콤) ;
  • 차재상 (서울과학기술대학교 전자IT미디어공학과)
  • Received : 2020.09.23
  • Accepted : 2020.10.26
  • Published : 2020.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, for a smart city, there is a demand for a technology for acquiring traffic information using an intelligent road infrastructure and managing it. In the meantime, various technologies such as loop detectors, ultrasonic detectors, and image detectors have been used to analyze road traffic information but these have difficulty in collecting various informations, such as traffic density and length of a queue required for building a traffic information DB for moving vehicles. Therefore, in this paper, assuming a smart city built on the basis of a camera infrastructure such as intelligent CCTV on the road, a solution for calculating the traffic DB of moving vehicles using Vision Tracking of road CCTV cameras is presented. Simulation and verification of basic performance were conducted and solution can be usefully utilized in related fields as a new intelligent traffic DB calculation solution that reflects the environment of road-mounted CCTV cameras and moving vehicles in a variable smart city road environment. It is expected to be there.

최근 스마트시티 구축을 위하여 지능형 도로인프라를 이용한 차량의 교통정보를 취득하고, 이를 효율적으로 관리하기 위한 기술의 개발이 요구되고 있다. 그동안 도로의 교통정보를 분석하기 위해서는 루프 검지기, 초음파 검지기, 영상식 검지기 등의 다양한 기술들이 활용되고 있었다. 그런데, 이러한 종래의 기술들은 도로내에서 이동하는 차량을 대상으로 교통정보 DB 구축을 위해 필요한 교통 밀도, 대기행렬의 길이등 다양한 교통 DB의 수집에 어려움이 있었다. 따라서, 본 논문에서는 도로위에 지능형 CCTV등 카메라 인프라를 기본으로 구축되는 스마트 시티를 가정하여 도로의 CCTV카메라를 이용하여 도로 CCTV의 Vision Tracking을 이용한 주행차량의 교통DB산출하는 솔루션을 제시하고, 이에 대한 모의실험과 기초성능 검증을 행하였다. 본 논문에서 제시한 솔루션은 일반론으로 발전시켜야할 숙제는 여전히 남아있지만, 가변하는 스마트시티 도로환경속에서 도로부착형 CCTV카메라 이동차량 환경을 반영한 새로운 지능형 교통DB산출솔루션으로 관련 분야에서 유용하게 활용될수 있을것으로 기대된다.

Keywords

References

  1. Coifman and Benjamin(1998), "A real-time computer vision system for vehicle tracking and traffic surveillance," Transportation Research Part C: Emerging Technologies, vol. 6, no. 4, pp.271-288. https://doi.org/10.1016/S0968-090X(98)00019-9
  2. Dalal N., and Triggs B.(2005), "Histograms of oriented gradients for human detection," 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp.886-893.
  3. Farneback G.(2000), "Fast and Accurate Motion Estimation Using Orientation Tensors and Parametric Motion Models," Proceeding of 15th International Conference on Pattern Recognition, pp.135-139.
  4. Godbehere A. B., Matsukawa A. and Goldberg K.(2012), "Visual Tracking of Human Visitors Under Variable-Lighting Conditions for a Responsive Audio Art Installation," Proceeding of American Control Conference, pp.4305-4312.
  5. Han and Feng(2006), "A two-stage approach to people and vehicle detection with hog-based svm," Performance Metrics for Intelligent Systems 2006 Workshop.
  6. Jang J. H., Park C. S., Baek N. C. and Lee M. Y.(2005), "Analysis on Video Image Detection System Performance by Vehicle Speed," Journal of Korean Society of Transportation, vol. 23, no. 5, pp.105-112.
  7. KaewTraKulPong P. and Bowden R.(2001), "An Improved Adaptive Background Mixture Model for Realtime Tracking with Shadow Detection," Proceeding of European Workshop Advanced Video Based Surveillance Systems.
  8. Kalal Z., Mikolajczyk K. and Matas J.(2011), "Tracking-learning-detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 7, pp.1409-1422. https://doi.org/10.1109/TPAMI.2011.239
  9. Ko K. Y., Kim M. S., Lee C. K., Jeong J. H. and Heo N. W.(2015), "Applicability Evaluation of FMCW Radar Detector on Signal Intersections," The Journal of the Korea Institute of Intelligent Transportation Systems, vol. 14, no. 1, pp.1-12.
  10. Liu and Wei(2016), "Ssd: Single shot multibox detector," European Conference on Computer Vision, Springer.
  11. Redmon and Joseph(2016), "You only look once: Unified, real-time object detection," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.
  12. Redmon J., and Farhadi A.(2018), Yolov3: An incremental improvement, arXiv preprint arXiv:1804.02767.
  13. Saunier N., and Sayed T.(2006), "A feature-based tracking algorithm for vehicles in intersections," Computer and Robot Vision, The 3rd Canadian Conference on, IEEE.
  14. Shin J.(2005), "Optical flow-based real-time object tracking using non-prior training active feature model," Real-Time Imaging, vol. 11, no. 3, pp.204-218. https://doi.org/10.1016/j.rti.2005.03.006
  15. Zivkovic Z.(2004), "Improved Adaptive Gaussian Mixture Model for Background Subtraction," Proceedings of the 17th International Conference on Pattern Recognition, pp.28-31.