Real-Time Traffic Video Analysis Using Intel Viewmont Coprocessor

  • Seon Ho Kim
  • Junyuan Shi
  • Abdullah Alfarrarjeh
  • Daru Xu
  • Yuwei Tan
  • Cyrus Shahabi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7813)

Abstract

Vision-based traffic flow analysis is getting more attention due to its non-intrusive nature. However, real-time video processing techniques are CPU-intensive so accuracy of extracted traffic flow data from such techniques may be sacrificed in practice. Moreover, the traffic measurements extracted from cameras have hardly been validated with real dataset due to the limited availability of real world traffic data. This study provides a case study to demonstrate the performance enhancement of vision-based traffic flow data extraction algorithm using a hardware device, Intel Viewmont video analytics coprocessor, and also to evaluate the accuracy of the extracted data by comparing them to real data from traffic loop detector sensors in Los Angeles County. Our experimental results show that comparable traffic flow data to existing sensor data can be obtained in a cost effective way with Viewmont hardware.

Keywords

Video Analysis Intel Viewmont Traffic Flow Data Inference 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cheung, S.-C., Kamath, C.: Robust Techniques for Back-ground Subtraction in Urban Traffic Video. In: Proc. SPIE, vol. 5308, pp. 881–892 (2004)Google Scholar
  2. 2.
    Harvey, B.A., Champion, G.H., Deaver, R.: Accuracy of Traffic Monitoring Equipment Field Tests. In: IEEE Vehicle Navigation and Information Systems Conference (1993)Google Scholar
  3. 3.
    Fishbain, B., Ideses, I., Mahalel, D., Yaroslavsky, L.: Real-Time Vision-Based Traffic Flow Measurements and Incident Detection. In: Real-Time Image and Video Processing (2009)Google Scholar
  4. 4.
    Federal Highway Administration, Traffic Detector Handbook, 3rd edn., vol. I (2006)Google Scholar
  5. 5.
    Sanders-Reed, J.N.: Multi-target, Multi-Sensor Closed Loop Tracking. In: Proc. SPIE, vol. 5430 (2004)Google Scholar
  6. 6.
    Hsu, Y.C., Jenq, N.H.: Multiple-Target Tracking for Crossroad Traffic Utilizing Modified Probabilistic Data Association. In: Acoustics, Speech and Signal Processing (2007)Google Scholar
  7. 7.
    Gartner, N.H., Rathi, A.J., Messer, C.J. (eds.): Revised Monograph on Traffic Flow Theory: A State-of-the-Art Report. Special Report by the Transportation Research Board of the National Research Council (2005)Google Scholar
  8. 8.
    Vandervalk-Ostrander, A.: AASHTO Guidelines for Traffic Data Programs, 2nd edn. (2009)Google Scholar
  9. 9.
    Wang, G., Xiao, D., Gu, J.: A Robust Traffic State Parameters Extract Approach Based on Video for Traffic Surveillance. In: IEEE International Conference on Automation and Logistics (2008)Google Scholar
  10. 10.
    Highway Administration, U.S.: Manual on Uniform Traffic Control Devices, http://mutcd.fhwa.dot.gov/htm/2003r1r2/part3/part3a.htm#section3A05
  11. 11.
    Lin, C.-P., Tai, J.-C., Song, K.-T.: Traffic Monitoring Based on Real-time Image Tracking. In: IEEE International Conference on Robotics and Automation (2003)Google Scholar
  12. 12.
    Batista, J., Peixoto, P., Fernandes, C., Ribeiro, M.: A Dual-Stage Robust Vehicle Detection and Tracking for Real-time Traffic Monitoring. In: IEEE International Conference on Intelligent Transportation Systems Conference (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Seon Ho Kim
    • 1
  • Junyuan Shi
    • 2
  • Abdullah Alfarrarjeh
    • 3
  • Daru Xu
    • 2
  • Yuwei Tan
    • 3
  • Cyrus Shahabi
    • 1
    • 2
    • 3
  1. 1.Integrated Media Systems CenterUniversity of Southern CaliforniaUSA
  2. 2.Department of Electrical EngineeringUniversity of Southern CaliforniaUSA
  3. 3.Department of Computer ScienceUniversity of Southern CaliforniaUSA

Personalised recommendations