International Journal of Vehicle Structures and Systems

Open Access Open Access  Restricted Access Subscription Access

Detection and Tracking of Vehicles Based on Colour Probability Density


Affiliations
1 Hunan University of Tech., Zhuzhou and ATR Lab. National University of Defence Tech., Changsha, China
2 Hunan University of Tech., Zhuzhou, China
3 Zhu Zhou CSR Times Electric Co., Ltd. Zhuzhou, China
 

   Subscribe/Renew Journal


Vehicle monitoring is a very important part in the intelligent transportation systems towards real-time monitoring of intersection traffic condition, the dynamic traffic incident detection and traffic parameter extraction. This paper proposes a vehicle tracking method based on mean shift. During the detection period, tracking objects of vehicles are constructed. The current vehicle position is predicted from the target area of former frame. In the candidate area of the target image, foreground area mask is adopted as a condition whether a pixel is selected; this makes the colour probability density to more accurately reflect the characteristics of the vehicle, and avoids the background region's influence on the mean shift iterations. Experiments show that this method can effectively detect the position of the vehicle, and provides an effective vehicle tracking method in the intelligent transportation system.

Keywords

Vehicle Tracking, Colour Probability Density, Vehicle Detection.
User
Subscription Login to verify subscription
Notifications
Font Size

  • S. Sivaraman and M. Trivedi. 2013. Integrated lane and vehicle detection, localization, and tracking: a synergistic approach, IEEE Trans. Intell. Transp. Syst., 14(2), 906-917. https://doi.org/10.1109/TITS.2013.2246835.

  • A. Fossati, P. Schoenmann and P. Fua. 2011. Real-time, vehicle tracking for driving assistance, Mach. Vis. Appl., 22(2), 439-448. https://doi.org/10.1007/s00138-009-0243-6.

  • R. O’Malley, E. Jones and M. Glavin. 2010. Rear-lamp vehicle detection and tracking in low-exposure colour video for night conditions, IEEE Trans. Intell. Transp. Syst., 11(2), 453-462. https://doi.org/10.1109/TITS.2010.2045375.

  • A.M. López, J. Hilgenstock and A. Busse. 2008. Nighttime vehicle detection for intelligent headlight control, Advanced Concepts for Intelligent Vision Systems, 5259LNCS, 113-124. https://doi.org/10.1007/978-3-540-88458-3_11.

  • A. Broggi, M. Cellario, P. Lombardi and M. Porta. 2003. An evolutionary approach to visual sensing for vehicle navigation, IEEE Trans. Ind. Electron, 50 (1), 18-29. https://doi.org/10.1109/TIE.2002.807688.

  • Y. Chen, B. Wu, H. Huang and Ch. Fan. 2011. A real-time vision system for night time vehicle detection and traffic surveillance, IEEE Trans. Ind. Electron, 58 (5), 2030-2044. https://doi.org/10.1109/TIE.2010.2055771.

  • W. Zhang, Q.M.J. Wu, G. Wang and X. You. 2012. Tracking and pairing vehicle headlight in night scenes, IEEE Trans. Intell. Transp. Syst., 13(1), 140-153. https://doi.org/10.1109/TITS.2011.2165338.

  • G. Agarwal, K.K. Agarwal and S. Roy. 2014. Investigations on physical and mechanical properties of short jute fibre reinforced epoxy composites, J. Mech. Engg. Research & Develop., 37(2), 1-10.

  • H. Kim, J. Do, G. Kim, J. Park and Y. Yu. 2012. Vehicle detection using running Gaussian average and laplacian of Gaussian in the night time, Community Comput. Inf. Sci., 353, 172-177. https://doi.org/10.1007/978-3-642-35521-9_25.

  • S. Zhou, J. Li, Z. Shen and L. Ying. 2013. A night time application for a real-time vehicle detection algorithm based on computer vision, Res. J. Appl. Sci. Eng. Tech., 5(10), 3037-3043. https://doi.org/10.19026/rjaset.5.4620.

  • Y. Cheng. 1995. Mean shift, mode seeking, and clustering, IEEE Trans. Pattern Analysis and Machine Intelligence, 17(8), 790-799. https://doi.org/10.1109/34.400568.

  • P.S. Maity, V. Kumar and A.B. Gupta. 2014. Rapid removal of metals from aqueous solution by magnetic Nano adsorbent: A kinetic study, J. Mech. Engg. Research & Develop., 37(2), 33-41.

  • D. Comaniciu, V. Ramesh and P. Meer. 2000. Real time tracking of non-rigid objects using mean shift, IEEE Conf. Computer Vision and Pattern Recognition, 142-149. https://doi.org/10.1109/CVPR.2000.854761.

  • K. Fukunaga and L.D. Hostetler. 1975. The estimation of the gradient of density function with applications in pattern recognition, IEEE Trans. Information Theory, 21, 32-40. https://doi.org/10.1109/TIT.1975.1055330.

  • D. Comaniciu, V. Ramesh and P. Meer. 2003. Kernelbased object tracking, IEEE Trans. Pattern Analysis Machine Intel., 5(25), 564-575. https://doi.org/10.1109/TPAMI.2003.1195991.

  • S.F. Liu and M.H. Lee. 2014. Research on prospective innovation design of smart electric vehicle, J. Mech. Engg. Research & Develop., 37(1), 22-29.

  • K. Nummiaro，E. Koller-Meier and L. Van Gool. 2002. A colour-based particle filter, Proc. 1st Int. Workshop on Generative-Model-Based Vision, 53-60.

  • A. Djouadi, O. Snorrason and F.D. Garber. 1990. The quality of training-sample estimates of the Bhattacharyya co-efficient, IEEE Trans. Pattern Analysis Machine Intelligence, 12, 92-97. https://doi.org/10.1109/34.41388.


Abstract Views: 683

PDF Views: 230




  • Detection and Tracking of Vehicles Based on Colour Probability Density

Abstract Views: 683  |  PDF Views: 230

Authors

Xiaohua Shu
Hunan University of Tech., Zhuzhou and ATR Lab. National University of Defence Tech., Changsha, China
Yonghong Long
Hunan University of Tech., Zhuzhou, China
Xiyu Xiao
Zhu Zhou CSR Times Electric Co., Ltd. Zhuzhou, China
Pei Shu
Zhu Zhou CSR Times Electric Co., Ltd. Zhuzhou, China

Abstract


Vehicle monitoring is a very important part in the intelligent transportation systems towards real-time monitoring of intersection traffic condition, the dynamic traffic incident detection and traffic parameter extraction. This paper proposes a vehicle tracking method based on mean shift. During the detection period, tracking objects of vehicles are constructed. The current vehicle position is predicted from the target area of former frame. In the candidate area of the target image, foreground area mask is adopted as a condition whether a pixel is selected; this makes the colour probability density to more accurately reflect the characteristics of the vehicle, and avoids the background region's influence on the mean shift iterations. Experiments show that this method can effectively detect the position of the vehicle, and provides an effective vehicle tracking method in the intelligent transportation system.

Keywords


Vehicle Tracking, Colour Probability Density, Vehicle Detection.

References





DOI: https://doi.org/10.4273/ijvss.11.1.02