DOI QR코드

DOI QR Code

Deep Learning Object Detection to Clearly Differentiate Between Pedestrians and Motorcycles in Tunnel Environment Using YOLOv3 and Kernelized Correlation Filters

  • Received : 2019.10.31
  • Accepted : 2019.12.17
  • Published : 2019.12.30

Abstract

With increasing criminal rates and number of CCTVs, much attention has been paid to intelligent surveillance system on the horizon. Object detection and tracking algorithms have been developed to reduce false alarms and accurately help security agents immediately response to undesirable changes in video clips such as crimes and accidents. Many studies have proposed a variety of algorithms to improve accuracy of detecting and tracking objects outside tunnels. The proposed methods might not work well in a tunnel because of low illuminance significantly susceptible to tail and warning lights of driving vehicles. The detection performance has rarely been tested against the tunnel environment. This study investigated a feasibility of object detection and tracking in an actual tunnel environment by utilizing YOLOv3 and Kernelized Correlation Filter. We tested 40 actual video clips to differentiate pedestrians and motorcycles to evaluate the performance of our algorithm. The experimental results showed significant difference in detection between pedestrians and motorcycles without false positive rates. Our findings are expected to provide a stepping stone of developing efficient detection algorithms suitable for tunnel environment and encouraging other researchers to glean reliable tracking data for smarter and safer City.

Keywords

References

  1. B. N. Silva, M. Khan, and K. Han, "Towards sustainable smart cities: A review of trends, architectures, components, and open challenges in smart cities," Sustainable Cities and Society, Vol.38, pp.697-713, Apr, 2018. https://doi.org/10.1016/j.scs.2018.01.053
  2. M. F. Xiong, D. Chen, J. Chen, J. Y. Chen, B. Y. Shi, C. Liang, and R. M. Hu, "Person re-identification with multiple similarity probabilities using deep metric learning for efficient smart security applications," Journal of Parallel and Distributed Computing, Vol.132, pp.230-241, Oct, 2019. https://doi.org/10.1016/j.jpdc.2017.11.009
  3. A. Sharif, M. A. Khan, K. Javed, H. G. Umer, T. Iqbal, T. Saba, H. Ali, and W. Nisar, "Intelligent Human Action Recognition: A Framework of Optimal Features Selection based on Euclidean Distance and Strong Correlation," Control Engineering and Applied Informatics, Vol.21, pp.3-11, Sep, 2019.
  4. B. N. Subudhi, D. K. Rout, and A. Ghosh, "Big data analytics for video surveillance," Multimedia Tools and Applications, Vol.78, pp.26129-26162, Sep, 2019. https://doi.org/10.1007/s11042-019-07793-w
  5. R. Iguernaissi, D. Merad, K. Aziz, and P. Drap, "People tracking in multi-camera systems: a review," Multimedia Tools and Applications, Vol.78, pp.10773-10793, Apr, 2019. https://doi.org/10.1007/s11042-018-6638-5
  6. G. Y. Lee, and H. J. Kim, "Optimum Configuration of Surveillance Camera System Based on Real Time Image Recognition Server," The Journal of Korean Institute of Communications and Information Sciences, Vol.44, pp.1124-1127, 2019. https://doi.org/10.7840/kics.2019.44.6.1124
  7. A. K. Chandran, L. A. Poh, and P. Vadakkepat, "Real-time identification of pedestrian meeting and split events from surveillance videos using motion similarity and its applications," Journal of Real-Time Image Processing, Vol.16, pp.971-987, Aug, 2019. https://doi.org/10.1007/s11554-016-0584-0
  8. M. Lotfi, S. A. Motamedi, and S. Sharifian, "Time-based feedback- control framework for real-time video surveillance systems with utilization control," Journal of Real-Time Image Processing, Vol.16, pp.1301-1316, Aug, 2019. https://doi.org/10.1007/s11554-016-0637-4
  9. E. Padmalatha, K. A. S. Sekhar, and D. R. R. Mudiam, "Real Time Analysis of Crowd Behaviour for Automatic and Accurate Surveillance," International Journal of Advanced Computer Science and Applications, Vol.10, pp.492-496, Mar, 2019.
  10. R. Eshel, and Y. Moses, "Tracking in a Dense Crowd Using Multiple Cameras," International Journal of Computer Vision, Vol.88, pp.129-143, May 01, 2010. https://doi.org/10.1007/s11263-009-0307-0
  11. P. M. Roth, C. Leistner, A. Berger, and H. Bischof. Multiple instance learning from multiple cameras. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, 13-18 June 2010 2010. 17-24.
  12. A. T. Y. Chen, M. Biglari-Abhari, and K. I. K. Wang, "Investigating fast re-identification for multi-camera indoor person tracking," Computers & Electrical Engineering, Vol.77, pp.273-288, Jul, 2019. https://doi.org/10.1016/j.compeleceng.2019.06.009
  13. C. C. Sun, M. H. Sheu, J. Y. Chi, and Y. K. Huang, "A Fast Non-Overlapping Multi-Camera People Re-Identification Algorithm and Tracking Based on Visual Channel Model," Ieice Transactions on Information and Systems, Vol.E102D, pp.1342-1348, Jul, 2019.
  14. F. Previtali, D. D. Bloisi, and L. Iocchi, "A distributed approach for real- time multi-camera multiple object tracking," Machine Vision and Applications, Vol.28, pp.421-430, May, 2017. https://doi.org/10.1007/s00138-017-0827-5
  15. J. Redmon, and A. Farhadi, "YOLOv3: An Incremental Improvement," arXiv preprint arXiv:1804.02767, April, 2018.
  16. Y. Li, and J. Zhu, " A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration," Lecture Notes in Computer Science, Vol.8926, pp.254-265, March, 2015.
  17. M. Hasan, J. Choi, J. Neumann, A. K. Roy-Chowdhury, and L. S. Davis, "Learning Temporal Regularity in Video Sequences," arXiv preprint arXiv:1604.04574 April, 2016.
  18. KOSIS National Tunnel Statistics, http://kosis.kr/statHtml/statHtml.do?orgId=116&tblId=DT_MLTM_1040 (accessed Oct. 29, 2019).