Algorithm to Detect Vehicles, Count and SegregationUsing SIFT for Non-lane Indian Roads

  • Mr.Siddalingesh G
  • DR.LATHA PARTHIBAN
Keywords: Intelligent Transportation System (ITS), Otsu's Threshold, Support Vector Machine (SVM), Scale Invariant Feature Transform (SIFT)

Abstract

Vehicle detection, counting and type segregation is an important part of Intelligent Transportation System (ITS). Accurate and real-time collection of traffic data is a key factor impacting ITS performance. Image-based solution for this task, comparing to other solutions, does not disturb traffic flow and can be easily implemented taking advantage of already established CCTV system at traffic signals. Number of algorithms have been developed so far on this topic. Motion blurs, changes in image resolution are still the challenges in developing a working algorithm, to name a few. The work presented in this paper focuses on developing algorithms to detect vehicles, count and segregated them based on their type. The vehicle detection and counting algorithm is based on Background Subtraction method and other image processing techniques. Testing of this algorithm shows promising results for images with low to medium vehicle density. For type segregation of vehicles, Scale Invariant Feature Transform(SIFT) is used for feature extraction. These obtained features are used to train Support Vector Machine (SVM) to classify vehicles..

References

[2] NarheM.C, Dr.Nagmode M.S. "Vehicle Classification using Sift" International Journal of Engineering Research &Technology (IJERT) ISSN Vol:3 Issue6,June-2014. [3] Da Li, Bodong Liang ,Weigang Zhang " Real-time Moving Vehicle Detection, Tracking, and Counting System Implemented with OpenCV" 4th IEEE International Conference on Information Science and Technology, 26-28 April 2014. [4] Ahmed Nidhal, Dr UmiKalthumNgah, Dr Widad Ismail "REAL TIME TRAFFIC CONGESTION DETECTION SYSTEM" Intelligent and Advanced Systems (ICIAS), 2014 5th International Conference. 3-5 June 2014 [5] Venkata Naresh Mandhalai, V.Sujatha ,B.Renuka Devi" Scene Classification Using Support Vector Machines" 2014 IEEE International Conference on Advanced Communication Control and Computing Technologies. [6] David G.Lowe "Distinctive Image Feature from Scale-Invariant Keypoints" January 5, 2014. [7] Ye Li , Fei-Yue Wang," Vehicle detection based on And–Or Graph and Hybrid ImageTemplates for complex urban traffic conditions" Transportation Research Part C 51 (2015) 19–28 [8] Yoginee B. Bramhe,P.S. Kulkarni"An implementation of Moving Object Detection, Tracking and Counting Objects for Traffic Surveillance System" [9] R. C. Gonzalez and R. E. Woods, Digital Image Processing Pearson Education, 2002.
Published
2017-07-10
How to Cite
G, M., & PARTHIBAN, D. (2017). Algorithm to Detect Vehicles, Count and SegregationUsing SIFT for Non-lane Indian Roads. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 3(3). Retrieved from http://www.asianssr.org/index.php/ajct/article/view/540
Section
Electronics and Telecommunication

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.