A Scheme on Object Tracking Techniques in Multiple CCTV IoT Environments

다중 CCTV 사물인터넷 환경에서의 객체 추적 기법

  • Hong, Ji-Hoon (Div. of Information Communication, BaekSeok University) ;
  • Lee, Keun-Ho (Div. of Information Communication, BaekSeok University)
  • 홍지훈 (백석대학교 정보통신학부) ;
  • 이근호 (백석대학교 정보통신학부)
  • Received : 2019.02.10
  • Accepted : 2019.03.29
  • Published : 2019.06.30


This study suggests a methodology to track crime suspects or anomalies through CCTV in order to expand the scope of CCTV use as the number of CCTV installations continues to increase nationwide in recent years. For the abnormal behavior classification, we use the existing studies to find out suspected criminals or abnormal actors, use CNN to track objects, and connect the surrounding CCTVs to each other to predict the movement path of objectified objects CCTVs in the vicinity of the path were used to share objects' sample data to track objects and to track objects. Through this research, we will keep track of criminals who can not be traced, contribute to the national security, and continue to study them so that more diverse technologies can be applied to CCTV.


Supported by : 백석대학교


  1. Y.K.Son and T.H.Kim, "Practical use plan of equipment security system for efficient crime prevention (CCTV system in priority," KOREAN INSTITUTE OF FIRE SCIENCE & ENGINEERING, pp.393-399. 2003.
  2. H.J.Kyung, "A Study on Establishment and Management of the Crime Prevention CCTV", The korean Association for Public Society, Vol.8, No.4, pp.109-137, 2018.
  3. H.S.Young and M.T.Heon, "An Analysis on the CCTV Location Appropriateness and Effectiveness for the Crime Prevention". The Korean Association Of Regional Geographers, Vol.21, No.4, pp.739-750, 2015.
  4. D.W.Kim, B.J.Park and S.K.Oh, "The Implementation of the structure and algorithm of Fuzzy Self-organizing Neural Networks(FSONN) based on CNN" Korean Institute of Intelligent Systems, Vol.10, No.1, pp.114-117. 2000.
  5. B.J.Park, S.K.Oh and H.K.Kim. "The Hybrid Multi-layer Inference Architectures and Algorithms of FPNN Based on CNN and PNN." The Korean Institute of Electrical Engineers, Vol.49, No.7, pp.378-388. 2000.
  6. J.H.Kim, W.C.Gyun, K.H.Park and Y.H.Kim, "Shadow Detection for the Accuracy of Object Detection in CCTV Image", Korean Institute of Information Technology, pp.191-193, 2018.
  7. S.H.Lee and M.S.Kang, "Design of Efficient Object Detection System Using Object Recognition Technology". The Institute of Electronics and Information Engineers, pp.829-831. 2018.
  8. S.K.Kim, E.Dinesh, M.S.Sung and Y.H.Joo. "Connectivity Based Object Tracking Model for Intelligent Video Surveillance", The Korean Institute of Electrical Engineers, pp.1131-1132. 2018.
  9. T.Y.Nam and D.W.Jung, "Design of KLT Tracker for Real-time Object Detection and Tracking using System-on-Chip", The Korean Society for Aeronautical & Space Sciences, pp.805-807, 2016.
  10. Jonathan. Hui. "Object detection: speed and accuracy comparison (Faster R-CNN, R-FCN, SSD, FPN, RetinaNet and YOLOv3)", 2018.
  11. J.H.Elder, J.D.Prince, Y.Hou, M.Sizintsev and E.Olevskiy, "Pre-Attoentive and Attentive Detection of Humans in Wide-Filed Scence", Intematinal Journal of Computer, Vol.72, No.1, pp.47-66. 2007.
  12. W.J.Lee and B.H.Lee, "Multiple Object Detection and Tracking System robust to various Environment". The Institute of Electronics and Information Engineers, Vol..46 No.6, pp.88-94, 2009.
  13. J.W.Park and S.Y.Kwak. "Crowed abnormal behaviors detection for video surveillance systems". Korea Institute Of Communication Sciences, pp.376-377, 2014.
  14. Y.J.Jung and Y.g.Yoon., "A Study on Abnormal Behavior Analysis and Pattern Prediction using Multi-object". The Korean Institute of Information Scientists and Engineers, pp.440-441. 2014.
  15. S.W.Lee and T.Y.Kim, J.H.Yoo, J.K.Paik. "Abnormal Behavior Detection Based on Adaptive Background Generation for Intelligent Video Analysis". The Institute of Electronics and Information Engineers, Vol.48. No.1, pp.111-121. 2011.