Total views : 465

Classifying Traffic Accidents with Unmanned Aerial Vehicle

Affiliations

  • Moscow Aviation Institute, National Research University, Russian Federation

Abstract


Background/Objectives: The study suggests a methodology for classifying traffic situations based on the images received on board UAV to improve monitoring efficiency and to eliminate the consequences of traffic accidents (TAs). Methods: The methodology for classifying traffic situations relies upon the images obtained after traffic accidents (TA), and it is based on a set of factors and attributes identifying directly and/or indirectly the potential class of the situation. A hierarchical structure has been developed to describe the situation that occurs after TA (“Description of Observed Scene”). The production model for knowledge representation and the relevant knowledge base (KB) have been suggested. Findings: Employing UAVs for the purposes of automated traffic monitoring can help improve the throughput capacity of the road, streamline the activities on eliminating the consequences of traffic accidents, reduce losses associated with accidents, etc. The study gives an example of classifying a situation based on the real image of the traffic accident. The novelty of the study is that it considers the case when UAV arrives at the region of interest, after the traffic accident. Applications/ Improvements: The obtained results prove that the suggested methodology can be applied to develop UAV on-board systems for automated traffic monitoring.

Keywords

Road Traffic Monitoring, Situation Classification, Traffic Accident, Unmanned Aerial Vehicle.

Full Text:

 |  (PDF views: 324)

References


  • Tormer S, Leitloff J, Reinartz P, Stilla U. Evaluation of selected features for car detection in aerial images. Hannover: ISPRS Hannover Workshop 2011, 14-17 Jun 2011. 2011.
  • Qadir A, Semke W, Neubert J. Implementation of an Onboard Visual Tracking System with Small Unmanned Aerial Vehicle (UAV). International Journal of Innovative Technology & Creative Engineering (issn: 2045-8711). 2011 October; 1(10).
  • Kim N, Chervonenkis M. Situational control of unmanned aerial vehicles for traffic monitoring. Modern Applied Science. 2015 May; 9(5) Special Issue. Canadian Center of Science and Education. ISSN (printed): 1913-1844. ISSN (electronic): 1913-1852.
  • Lienhart R, Maydt J. An extended set of haar-like features for rapid object detection. IEEE, Proceedings, 2002 International Conference on Image Processing. 2002; 1.
  • Zhang J, Liu L, Wang B, Chen X, Wang Q, Zheng T. High speed automatic power line detection and tracking for UAV-based inspection. International Conference on Industrial Control and Electronics Engineering (ICICEE). 2012; p. 266-69.
  • Forssyth DA, Ponce J. Prentice Hall, Ptr., Pearson Education, Inc.: Computer Vision: a Modern Approach. 2003.
  • Bernd J. Springer: Digital Image Processing. 2005. ISBN 3-540-24035-7.
  • Kim N, Bodunkov N. Springer: Computer Vision in Advanced Control Systems: Innovations in Practice, 2, Editors M. Favorskaya, Lakhmi C. Jain. 2014.
  • Yilmaz A, Javed O, Shah M. Object tracking: A survey. ACM Comput. Surv. 2006 Dec; 38(4):45 pages. Article 13. Date accessed: 05.15.2016: Available from: http://doi.acm.org/10.1145/1177352.1177355.
  • Lin Feng, Lum Kai-Yew, Chen Ben M, Lee Tong H. Development of vision-based ground target detection and tracking system for a small unmanned helicopter. Springer: Science in China Series F: Information Sciences. 2009.
  • Yuping Lin, Qian Yu, Gιrard Medioni. Efficient detection and tracking of moving objects in geo-coordinates. Springer-Verlag: Machine Vision and Applications. 2010.
  • Kim N. Automated Decision Making in Road Traffic Monitoring by on-Board Unmanned Aerial Vehicle System. Indian Journal of Science and Technology. 2015 December; 8(S10).
  • Gorelik AL, Skripkin VA. Moscow, Vysshaya shkola: Detection methods. 2004.
  • Pospelov DA. Moscow, Nauka: Chief Editorial Board of Physical and Mathematical literature: Situational control: theory and practice. 1986.
  • Liang Li, Shuqiang Jiang, Qingming Huang. Learning Hierarchical Semantic Description via Mixed-Norm Regularization for Image Understanding. Multimedia, IEEE Transactions. 2012; 14(5):1401–13.
  • Oberle D, Guarino N, Staab S. What is an ontology? Springer: Handbook on Ontologies, 2nd edition. 2009.
  • Mizoguchi R. Tutorial on ontological engineering: part 3: Advanced course of ontological engineering. Ohmsha & Springer-Verlag: New Generation Computing. 2004; 22(2):198-220.
  • Tsz-Ho Yu, Yiu-Sang Moon. Unsupervised Abnormal Behavior Detection for Real-time Surveillance Using Observed History. Yokohama, Japan: MVA2009 IAPR, Conference on Machine Vision Applications, May 20-22, 2009.
  • Ying-Ying Zhu, Yan-Yan Zhu, Wen Zhen-Kun, Wen-Sheng Chen, Qiang Huang. Detection and Recognition of Abnormal Running Behavior in Surveillance Video. Mathematical Problems in Engineering. 2012; Article ID 296407.

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.