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

Microscopic Traffic Parameters Estimation from UAV Video Using Multiple Object Tracking of Deep Learning-based

다중객체추적 알고리즘을 활용한 드론 항공영상 기반 미시적 교통데이터 추출

  • Jung, Bokyung (Dept. of Spatial Information Eng., Pukyong National University) ;
  • Seo, Sunghyuk (Dept. of Spatial Information Eng., Pukyong National University) ;
  • Park, Boogi (Dept. of Spatial Information Eng., Pukyong National University) ;
  • Bae, Sanghoon (Dept. of Spatial Information Eng., Pukyong National University)
  • 정보경 (부경대학교 지구환경시스템과학부 공간정보시스템공학전공) ;
  • 서성혁 (부경대학교 지구환경시스템과학부 공간정보시스템공학전공) ;
  • 박부기 (부경대학교 지구환경시스템과학부 공간정보시스템공학전공) ;
  • 배상훈 (부경대학교 공간정보시스템공학과)
  • Received : 2021.08.30
  • Accepted : 2021.10.07
  • Published : 2021.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the advent of the fourth industrial revolution, studies on driving management and driving strategies of autonomous vehicles are emerging. While obtaining microscopic traffic data on vehicles is essential for such research, we also see that conventional traffic data collection methods cannot collect the driving behavior of individual vehicles. In this study, UAV videos were used to collect traffic data from the viewpoint of the aerial base that is microscopic. To overcome the limitations of the related research in the literature, the micro-traffic data were estimated using the multiple object tracking of deep learning and an image registration technique. As a result, the speed obtained error rates of MAE 3.49 km/h, RMSE 4.43 km/h, and MAPE 5.18 km/h, and the traffic obtained a precision of 98.07% and a recall of 97.86%.

4차 산업혁명의 도래와 함께 자율주행자동차의 주행관리 및 주행 전략과 관련된 연구들이 대두되고 있다. 이러한 연구를 위해서는 차량의 미시적 교통데이터의 확보가 필수적이나, 기존 교통정보 수집 방식은 개별차량의 주행행태를 수집할 수 없다. 본 연구에서는 미시적 교통정보를 수집 가능한 항공에서 내려다보는 관점의 교통정보 수집을 위해 드론 항공영상을 활용하였다. 관련 연구의 한계점을 극복하기 위하여 딥러닝 기반 다중객체추적 알고리즘과 영상정합을 활용하여 미시적 교통데이터를 추출하였다. 그 결과로 속도는 MAE 3.49km/h, RMSE 4.43km/h, MAPE 5.18km/h의 오차율과 교통량 Precision 98.07%, Recall 97.86%의 정확도를 획득하였다.

Keywords

References

  1. AlexeyAB/Yolo_mark, https://github.com/AlexeyAB/Yolo_mark, 2020.10.01.
  2. Angel A., Hickman M., Chandnani D. and Mirchandani P.(2002), "Application of aerial video for traffic flow monitoring and management," ASCE 7th International Conference on Applications of Advanced Technologies in Transportation, pp.346-353.
  3. Baek N. C. and Lee S. H.(2012), "A Study on the Possibility of Using the Aerial-Based Vehicle Detection System for Real-Time Traffic Data Collection," Journal of Korean Society of Civil Engineers, vol. 32, no. 2, pp.129-136. https://doi.org/10.12652/Ksce.2012.32.4C.129
  4. Carlos F. D.(1997), Fundamentals of Transportation and Traffic Operations, Emerald Group Publishing Limited(West Yorkshire, England), p.14.
  5. Coifman B., McCord M., Mishalani R. and Redmill K.(2004), "Surface Transportation Surveillance from Unmanned Aerial Vehicles," Proc. 83d Annual Meeting of the Transportation Research Board.
  6. Dawei D., Yuankai Q., Hongyang Y., Yifan Y., Kaiwen D., Guorong L., Weigang Z., Qingming H. and Qi T.(2018), "The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking," ECCV 2018, pp.375-391.
  7. Doherty P., Granlund G., Kuchcinski K., Sandewall E., Nordberg K., Skarman E. and Wiklund J.(2000), "The WITAS Unmanned Aerial Vehicle Project," ECAI, vol. 14, pp.747-755.
  8. Gao H., Kong S. L., Zhou S., Lv F. and Chen Q.(2014), "Automatic Extraction of Multi-Vehicle Trajectory Based on Traffic Videotaping from Quadcopter Model," Applied Mechanics and Materials, vol. 552, pp.232-239. https://doi.org/10.4028/www.scientific.net/amm.552.232
  9. Granlund G., Nordberg K., Wiklund J., Doherty P., Skarman E. and Sandewall E.(2000), "WITAS: An Intelligent Autonomous Aircraft Using Active Vision," Proceedings of the UAV 2000 International Technical Conference and Exhibition (UAV), Paris, France: Euro UVS.
  10. Jeong J. H., Park J. Y. and Oh C.(2020), "Assessing the Safety Effects of Expressway Managed Lane for Autonomous Bus Using Traffic Simulation," Journal of Korean Society of Transportation, vol. 38, no. 1, pp.58-67. https://doi.org/10.7470/jkst.2020.38.1.058
  11. Kim S. H., Lee J. K., Han D. H., Yoon J. Y. and Jeong S. Y.(2017), "Preliminary Study Related with Application of Transportation Survey and Analysis by Unmanned Aerial Vehicle(Drone)," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 16, no. 6, pp.182-194. https://doi.org/10.12815/kits.2017.16.6.182
  12. Kim Y. M., Lee D. H. and Bae S. H.(2018), "Identification of Lane Changing on Arterial Road by Adopting Drone Image," Journal of Transport Research, vol. 25, no. 1, pp.29-39. https://doi.org/10.34143/JTR.2018.25.1.29
  13. Lee S. Y. and Oh C.(2017), "Lane Change Behavior of Manual Vehicles in Automated Vehicle Platooning Environments," Journal of Korean Society of Transportation, vol. 35, no. 4, pp.332-347. https://doi.org/10.7470/jkst.2017.35.4.332
  14. Massachusetts Department of Transportation Office of Transportation Planning(2019), The Application of Unmanned Aerial Systems In Surface Transportation-VolumeII-C: Evaluation of UAS Highway Speed-Sensing Application, pp.1-47.
  15. Mikel-brostrom/Yolov5_DeepSort_Pytorch, https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch, 2020.10.01.
  16. Ministry of Land, Infrastructure and Transport(2021), Annual Traffic Volume Report 2020, p.6.
  17. Park H. L., Byun S. H. and Lee H. S.(2020), "Application of Deep Learning Method for Real-Time Traffic Analysis using UAV," Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, vol. 38, no. 4, pp.353-361. https://doi.org/10.7848/KSGPC.2020.38.4.353
  18. Puri A.(2005), A Survey of Unmanned Aerial Vehicles(UAV) for Traffic Surveillance, Department of Computer Science and Engineering, University of South Florida, Florida, pp.1-29.
  19. Ruimin K., Shou F., Zhiyong C. and Yinhai W.(2020), "Advanced framework for microscopic and lane-level macroscopic traffic parameters estimation from UAV video," IET Intelligent Transport Systems 2020, vol. 14, no. 7, pp.724-734.
  20. Ruimin K., Zhibin L., Jinjun T., Zewen P. and Yinhai W.(2019), "Real-Time Traffic Flow Parameter Estimation Frow UAV Video Based on Ensemble Classifier and Optical Flow," IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 1, pp.54-64. https://doi.org/10.1109/tits.2018.2797697
  21. Seo S. H. and Lee S. B.(2018), "A Study on Traffic Data Collection and Analysis for Uninterrupted Flow using Drones," The Journal of The Korea Institute of Intelligent Transport Systems, vol. 17, no. 6, pp.144-152. https://doi.org/10.12815/kits.2018.17.6.144
  22. Ultralytics/Yolov5, https://github.com/ultralytics/yolov5, 2020.10.01.
  23. Wojke N., Bewley A. and Paulus D.(2017), "Simple Online and Realtime Tracking with a Deep Association Metric," ICIP 2017, pp.3645-3649.