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

  • 제18권6호
  • /
  • Pages.191-201
  • /
  • 2019
  • /
  • 1738-0774(pISSN)
  • /
  • 2384-1729(eISSN)
한국ITS학회 (The Korea Institute of Intelligent Transport Systems)
권호 표지
DOI QR코드

DOI QR Code

교통 데이터 수집을 위한 객체 인식 통합 프레임워크 개발

Development of an Integrated Traffic Object Detection Framework for Traffic Data Collection

  • 양인철 (한국건설기술연구원 인프라안전연구본부 도로관리통합센터) ;
  • 전우훈 (한국건설기술연구원 인프라안전연구본부 도로관리통합센터) ;
  • 이조영 ;
  • 박지현
  • Yang, Inchul (Integrated Road Management Center, Dept. of Infrastructure Safety Research, KICT) ;
  • Jeon, Woo Hoon (Integrated Road Management Center, Dept. of Infrastructure Safety Research, KICT) ;
  • Lee, Joyoung (Dept. of Civil and Environmental Engineering, New Jersey Institute of Technology) ;
  • Park, Jihyun (Dept. of Civil and Environmental Engineering, New Jersey Institute of Technology)
  • 투고 : 2019.11.11
  • 심사 : 2019.11.28
  • 발행 : 2019.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구에서는 다양한 외부 조건 하에서 촬영된 영상을 대상으로 신속하고 정확하게 교통 객체를 검출하는 교통 객체 검출 통합 프레임워크를 개발하였다. 제안된 프레임워크는 딥러닝 기술 기반의 직접 객체 인식 기술과 다중 객체 추적 기술, 그리고 동영상 전처리 기술로 구성되며, 영상의 안정성, 기상, 촬영 각도 등의 다양한 외부 조건에서 촬영된 영상을 대상으로 승용차, 버스, 트럭, 및 미니밴과 같은 교통 객체를 인식하고, 이를 실시간으로 추적하여 교통량 데이터를 계수한다. 제안된 방법의 성능 검증을 위해 다양한 외부 조건에서 촬영된 영상 8개를 대상으로 제안된 방법의 성능 검증을 수행한 결과, 우천 및 강설을 제외한 모든 조건에서 98% 이상의 높은 정확도를 보이는 것으로 나타났다.

A fast and accurate integrated traffic object detection framework was proposed and developed, harnessing a computer-vision based deep-learning approach performing automatic object detections, a multi object tracking technology, and video pre-processing tools. The proposed method is capable of detecting traffic object such as autos, buses, trucks and vans from video recordings taken under a various kinds of external conditions such as stability of video, weather conditions, video angles, and counting the objects by tracking them on a real-time basis. By creating plausible experimental scenarios dealing with various conditions that likely affect video quality, it is discovered that the proposed method achieves outstanding performances except for the cases of rain and snow, thereby resulting in 98% ~ 100% of accuracy.

키워드

참고문헌

  1. Allen J., Richard Y. D., Jin S.(2004), "Object Tracking Using Cam Shift Algorithm and Multiple Quantized Feature Spaces," '05 Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing, pp.3-7.
  2. Henriques J. F., Caseiro R., Martins P. and Batista J.(2015), "High-Speed Tracking with Kernelized Correlation Filters," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, pp.583-596. https://doi.org/10.1109/TPAMI.2014.2345390
  3. Lee K. and Shin H.(2019), "Effect on self-enhancement of deep-learning inference by repeated training of false detection cases in tunnel accident image detection," Journal of Korean Tunnelling and Underground Space Association, vol. 21, no. 3, pp.419-432. https://doi.org/10.9711/KTAJ.2019.21.3.419
  4. Lee T., Kim K., Yun K., Kim K. and Choi D.(2018), "A Method of Counting Vehicle and Pedestrian Using Deep Learning Based on CCTV," Journal of Korean Institute of Intelligent Systems, vol. 28, no. 3, pp.219-224. https://doi.org/10.5391/JKIIS.2018.28.3.219
  5. Lukezic A., Vojir T., Cehovin Zajc L., Matas J. and Kristan M.(2017), "Discriminative Correlation Filter with Channel and Spatial Reliability," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6309-6318.
  6. Malik A. A., Khalil A. and Khan H. U.(2013), "Object detection and tracking using background subtraction and connected component labeling," International Journal of Computer Applications, vol. 75, no. 13.
  7. Nam S.(2018), Deep learning-based real-time object tracking on CCTV, M.S Thesis, Kwangwoon University, South Korea.
  8. Park M., Kim H., Choi H. and Park S.(2019), "A Study on Vehicle Detection and Distance Classification Using Mono Camera Based on Deep Learning," Journal of Korean Institute of Intelligent Systems, vol. 29, no. 2, pp.90-96. https://doi.org/10.5391/JKIIS.2019.29.2.90
  9. Redmon J., Divvala S., Girshick R. and Farhadi A.(2016), "You only look once: Unified, real-time object detection," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788.
  10. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S. E., Anguelov D., Erhan D., Vanhoucke V. and Rabinovich A.(2014), "Going deeper with convolutions," 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp.1-9.
  11. Szegedy C., Vincent V., Sergey I., Jonathon S. and Zbigniew W.(2016), "Rethinking the Inception Architecture for Computer Vision," 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.2818-2826.
  12. Yilmaz A., Javed O. and Shah M.(2006), "Object tracking: A survey," ACM Computing Surveys, vol. 38, no. 4, p.13. https://doi.org/10.1145/1177352.1177355
  13. Youtube, https://www.youtube.com/watch?v=UM0hX7nomi8, Last Access: 2019.10.31.

피인용 문헌

  1. CCTV 영상을 활용한 동적 객체의 위치 추적 및 시각화 방안 vol.51, pp.1, 2019, https://doi.org/10.22640/lxsiri.2021.51.1.53