Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Multiple Camera-Based Real-Time Long Queue Vision Algorithm for Public Safety and Efficiency

  • Tae-hoon Kim (Dept. of Computer Science and Engineering, Kyonggi University) ;
  • Ji-young Na (Dept. of Computer Science and Engineering, Kyonggi University) ;
  • Ji-won Yoon (Dept. of Computer Science and Engineering, Kyonggi University) ;
  • Se-Hun Lee (Dept. of Computer Science and Engineering, Kyonggi University) ;
  • Jun-ho Ahn (Dept. of Computer Science and Engineering, Kyonggi University)
  • Received : 2024.07.19
  • Accepted : 2024.09.30
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a system to efficiently manage delays caused by unmanaged and congested queues in crowded environments. Such queues not only cause inconvenience but also pose safety risks. Existing systems, relying on single-camera feeds, are inadequate for complex scenarios requiring multiple cameras. To address this, we developed a multi-vision long queue detection system that integrates multiple vision algorithms to accurately detect various types of queues. The algorithm processes real-time video data from multiple cameras, stitching overlapping segments into a single panoramic image. By combining object detection, tracking, and position variation analysis, the system recognizes long queues in crowded environments. The algorithm was validated with 96% accuracy and a 92% F1-score across diverse settings.

본 논문은 대기 인원이 많은 혼잡한 환경에서 대기 시간이 지체되어 관리되지 않는 상황을 효율적으로 관리하는 시스템을 제안한다. 혼잡하고 긴 대기 줄은 불편하고 안전사고를 유발할 수 있다. 기존의 시스템은 단순한 하나의 영상 기반으로 대기 줄을 관리했지만, 혼잡한 상황에 다수의 카메라를 통해서 관리해야 하는 복잡한 상황에서는 적용이 어렵다. 이러한 상황에서 효율적으로 다수의 카메라로 탐지된 하나의 줄을 관리하기 위해 다수의 비전 알고리즘을 융합하여 여러 형태의 대기 줄을 정확하게 인식하는 효율적인 멀티비전 긴 대기 줄 탐지 시스템을 개발하였다. 이 줄 인식 융합 알고리즘은 다수의 카메라의 실시간 영상 데이터를 활용하여 중첩된 부분을 이어 붙여 하나의 실시간 파노라마 영상 이미지로 가공한다. 이러한 영상 데이터를 바탕으로 비전 객체 탐지, 객체 추적, 이미지 스티칭, 각도, 간격, 위치 변화량을 융합해 Queue Recognition 알고리즘을 개발하여, 많은 군중 속에서 다양한 형태의 긴 줄을 인식한다. 본 연구는 다양한 환경에서 실시간 대기 다수의 카메라로 인식된 긴 줄을 탐지하는 융합 알고리즘을 통해서 정확도 96%와 F1-score 92%로 높은 성능을 검증하였다.

Keywords

Acknowledgement

"This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW supervised by the IITP(Institute of Information & communications Technology Planning & Evaluation)"(2021-0-01393)

References

  1. Policy Research Team, Incheon International Airport Corporation, "Time Series Statistics," https://www.airport.kr/co/ko/cpr/statisticCategoryOfTimeSeries.do. 
  2. Jung Da-min, "Feature: K-pop Concerts as Cultural Exports," The Korea Times, 2024, https://www.koreatimes.co.kr/www/culture/2024/06/135_365480.html. 
  3. JC Park, "Incheon Airport Free from COVID-19... But 'Queueing' Has Worsened," Kyunghyang shinmun, 2024. https://www.khan.co.kr/economy/market-trend/article/202401081543001. 
  4. Soo Kim, "I Want to Ride Too: Commute Shuttles," Journal of Transportation Technology and Policy, vol. 20, no. 2, pp. 70-71, 2023, DOI: https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE11409532. 
  5. Hyo-Jin Kim, "Domestic Tourism Rebounds in Summer," Hankook Ilbo, 2023, https://www.hankookilbo.com/News/Read/A2023072617250003934. 
  6. Parameswaran, Vasu, Vinay Shet, and Visvanathan Ramesh, "Design and Validation of a System for People Queue Statistics Estimation," Video Analytics for Business Intelligence, Berlin, Heidelberg: Springer Berlin Heidelberg, vol. 409, pp. 355-374, 2012, DOI: 10.1007/978-3-642-28598-1_11. 
  7. Jiangtao Wang, et al., "Real-time and generic queue time estimation based on mobile crowdsensing," Frontiers of Computer Science, vol. 11, pp. 49-60, 2017, DOI: https://doi.org/10.1007/s11704-016-5553-z. 
  8. Nicolai Wojke, Alex Bewley, and Dietrich Paulus, "Simple online and realtime tracking with a deep association metric," 2017 IEEE International Conference on Image Processing (ICIP), IEEE, 2017, DOI: 10.1109/ICIP.2017.8296962. 
  9. Juan Du, "Understanding of object detection based on CNN family and YOLO," Journal of Physics: Conference Series, vol. 1004, IOP Publishing, 2018, DOI: 10.1088/1742-6596/1004/1/012029. 
  10. A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple online and realtime tracking," 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, Sep. Feb 2016. DOI: 10.1109/ICIP.2016.7533003. 
  11. J. Terven, D.-M. Cordova-Esparza, and J.-A. Romero-Gonzalez, "A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680-1716, Nov. 2023. DOI: 10.3390/make5040083. 
  12. Ultralytics, "YOLOv9," Ultralytics Documentation. https://docs.ultralytics.com/ko/models/yolov9/. 
  13. C.-Y. Wang, I.-H. Yeh, and H.-Y. M. Liao, "YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information," arXiv preprint arXiv:2402.13616, Feb 2024. DOI: https://arxiv.org/abs/2402.13616. 
  14. V. Parameswaran, M. Singh, and V. Ramesh, "Illumination compensation based change detection using order consistency," 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA, 2010, pp. 1982-1989. DOI: 10.1109/CVPR.2010.5539873. 
  15. M. Singh, V. Parameswaran, and V. Ramesh, "Order consistent change detection via fast statistical significance testing," 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, 2008, pp. 1-8. DOI: 10.1109/CVPR.2008.4587668. 
  16. J. S. Speagle, "A Conceptual Introduction to Markov Chain Monte Carlo Methods," arXiv preprint arXiv:1909.12313, Sep 2020. DOI: https://arxiv.org/abs/1909.12313. 
  17. Zhang, Yifu, et al., "ByteTrack: Multi-Object Tracking by Associating Every Detection Box," GitHub repository, 2021. Available: https://github.com/ifzhang/ByteTrack. 
  18. Y. Zhang, P. Sun, Y. Jiang, D. Yu, F. Weng, Z. Yuan, P. Luo, W. Liu, and X. Wang, "ByteTrack: Multi-Object Tracking by Associating Every Detection Box," arXiv preprint arXiv:2110.06864, Apr 2022. DOI: https://arxiv.org/abs/2110.06864.  https://doi.org/10.06864
  19. Nebula4869, "Real-time-Panoramic-Stitching," GitHub. https://github.com/Nebula4869/Real-time-Panoramic-Stitching. 
  20. T. Lindeberg, "Scale Invariant Feature Transform," Scholarpedia, vol. 7, no. 5, pp. 10491, 2012. DOI: 10.4249/scholarpedia.10491 
  21. M. A. Fischler, and R. C. Bolles, "Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography," Commun. ACM, Vol. 24, No. 6, pp. 381-395, June 1981. DOI: 10.1145/358669.358692. 
  22. D. DeTone, T. Malisiewicz, and A. Rabinovich, "Deep Image Homography Estimation," arXiv preprint arXiv:1606.03798, June 2016. DOI: https://arxiv.org/abs/1606.03798. 
  23. Dong-Bin Xu, He-Meng Tao, Jing Yu, Chuang-Bai Xiao, "Real-Time Multi-camera Video Stitching Based on Improved Optimal Stitch Line and Multi-resolution Fusion," Lecture Notes in Computer Science, pp. 124-133, ICIG, Beijing, China, December 2017, DOI: 10.1007/978-3-319-71598-8_12. 
  24. Yanfang Zhang, Xinyu Zhang, "Real-time Image Stitching with Improved Seam Cutting and Blending," 2015 IEEE International Conference on Image Processing (ICIP), pp. 3509-3513, Quebec City, Canada, Sep 2015. DOI: 10.1109/ICIP.2015.7351332. 
  25. Kailee Kodama Muscente, "Audio and Video Recording in Remote Research," Teachers College, Columbia University. https://www.tc.columbia.edu/institutional-review-board/irb-blog/2022/audio-and-video-recording-in-remote-research/. 
  26. M. Vakili, M. Ghamsari, and M. Rezaei, "Performance Analysis and Comparison of Machine and Deep Learning Algorithms for IoT Data Classification," arXiv preprint arXiv:2001.09636, Jan 2020. DOI: https://arxiv.org/abs/2001.09636. 
  27. Mihaela Muntean, Florin-Daniel Militaru, "Metrics for Evaluating Classification Algorithms," in Education, Research and Business Technologies, Smart Innovation, Systems and Technologies, vol 321, Springer, pp. 307-317, Singapore, Jan 2023. DOI: 10.1007/978-981-19-6755-9_24.