드론 영상을 이용한 딥러닝 기반 회전 교차로 교통 분석 시스템
Deep Learning-Based Roundabout Traffic Analysis System Using Unmanned Aerial Vehicle Videos
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.
Abstract
Roundabouts have strengths in traffic flow and safety but can present difficulties for inexperienced drivers. Demand to acquire and analyze drone images has increased to enhance a traffic environment allowing drivers to deal with roundabouts easily. In this paper, we propose a roundabout traffic analysis system that detects, tracks, and analyzes vehicles using a deep learning-based object detection model (YOLOv7) in drone images. About 3600 images for object detection model learning and testing were extracted and labeled from 1 hour of drone video. Through training diverse conditions and evaluating the performance of object detection models, we achieved an average precision (AP) of up to 97.2%. In addition, we utilized SORT (Simple Online and Realtime Tracking) and OC-SORT (Observation-Centric SORT), a real-time object tracking algorithm, which resulted in an average MOTA (Multiple Object Tracking Accuracy) of up to 89.2%. By implementing a method for measuring roundabout entry speed, we achieved an accuracy of 94.5%.
참고문헌 (27)
- S. W. Lee, "Use of Drone", AUTO JOURNAL : Journal of the Korean Society of Automotive Engineers, 44(5), pp.57~60 (2022)
- H. Shakhatreh, "Unmanned Aerial Vehicles (UAVs): A Survey on Civil Applications and Key Research Challenges", IEEE Access, 7, pp.48572~48634 (2019)
- M. Mozaffari, "A Tutorial on UAVs for Wireless Networks:Applications, Challenges, and Open Problems", IEEE Communications Surveys & Tutorials, 21(3), pp.2334~2360 (2019)
- J. T. Oh, "A Comparison and Analysis of Traffic Information Collection Devices focus on Loop Detection Device and Developed Image Detection Device", Proceedings of the Korean Society of Transportation (KOR-KST) Conference, 58, pp.727~736 (2008)
- 한음, "V2I 통신환경을 활용한 연동교차로 교통신호 실시간 제어 연구", 한국ITS학회 논문지, 17(3), pp.59~71 (2018), 한국ITS학회[DOI]
- 김봉근, "CCTV 카메라를 이용한 실시간 도로시정 측정", 대한교통학회지, 28(4), pp.125~138 (2011), 대한교통학회
- D. S. Park, "Deep Neural Network Based Traffic CCTV Data Analysis", pp.2018
- R. Ke, "Real-time Bidirectional Traffic Flow Parameter Estimation from Aerial Videos", IEEE Transaction of Intelligent Transportation System, 18(4), pp.890~901 (2016)
- 한동권, "드론영상과 인공지능 기반 교통량 추정을 위한 데이터 구축 가이드라인 도출 연구", 한국측량학회지, 40(3), pp.147~157 (2022), 한국측량학회[DOI]
- S. W. Byeon, "Drone Image Analysis Based On Deep Learning For Traffic Measurement", pp.2021
- 김준용, "지능형 교통 체계를 위한 딥러닝 기반 객체 검출 활용 방법론", 제어.로봇.시스템학회 논문지, 27(12), pp.1016~1022 (2021), 제어·로봇·시스템학회[DOI]
- 서홍덕, "스테레오 CCTV 영상에서 딥러닝을 이용한 교통량 추정", 한국측량학회지, 38(3), pp.269~279 (2020), 한국측량학회[DOI]
- 박홍련, "UAV를 활용한 실시간 교통량 분석을 위한 딥러닝 기법의 적용", 한국측량학회지, 38(4), pp.353~361 (2020), 한국측량학회[DOI]
- D. Du, "The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking", Proceedings of the European Conference on Computer Vision (ECCV), pp.370~386 (2018)
- H. Koo, "A Comprehensive Evaluation Methods of Roundabout by Managing Entering Speed and Conflicts", Traffic Safety Research, 31(0), pp.207~224 (2012)
- F. Sultana, "A Review of Object Detection Models Based on Convolutional Neural Network", Intelligent Computing : Image Processing Based Applications, 1157, pp.1~16 (2020)
- L. Du, "Overview of Two-stage Object Detection Algorithms", Journal of Physics:Conference Series, 1544 (2020)
- C. Y. Wang, "YOLOv7:Trainable Bag-of-freebies Sets New State-of-the-art for Real-time Object Detectors", ~ (2022)
- A. Bewley, "Simple Online and Realtime Tracking", IEEE International Conference on Image Processing, pp.3464~3468 (2016)
- "Heartexlabs"[URL]
- "Darkpgmr"[URL]
- N. Wojke, "Simple Online and Realtime Tracking with a Deep Association Metric", ~ (2017)
- "Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking"[URL]
- 이준하, "다중 도메인 데이터 기반 구별적 모델 예측 트레커를 위한 동적 탐색 영역 특징 강화 기법", 대한임베디드공학회논문지, 16(6), pp.323~330 (2021), 대한임베디드공학회[DOI]
- "Wkentaro"[URL]
- R. Padilla, "A Survey on Performance Metrics for Object-Detection Algorithms", International Conference on Systems, Signals and Image Processing (IWSSIP), pp.237~242 (2020)
- A. Milan, "MOT16: A Benchmark for Multi-Object Tracking", ~ (2016)