A Hybrid Shadow Removal Algorithm for Vehicle Classification in Traffic Surveillance System

  • Long Hoang PhamEmail author
  • Hung Ngoc Phan
  • Duong Hai Le
  • Synh Viet-Uyen HaEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 695)


Shadow is one of the common parts in the natural scenes and has become an important topic in the field of computer vision. In many vision-based traffic surveillance systems, shadows interfere with fundamental tasks such as vehicle detection, classification, and tracking. Thus, it is necessary to suppress the effect of shadows. A difficult part of the shadow removal problem is how to accurately detect and remove shadow regions and recover the boundaries of the vehicles, while still achieving real-time processing performance. Many powerful methods have been proposed to solve this dilemma; however, instabilities at the boundaries of moving vehicles are still challenges. In this paper, an improved algorithm to remove shadow regions, and quickly recovering the boundaries of moving vehicles is presented in a detailed manner. The proposed method applies edge information with background subtraction to handle daytime traffic scenes. Our approach has demonstrated more accurate results than previous approaches regardless of lighting luminance levels or shadow orientations.


Traffic surveillance system Shadow removal Edge detection Vehicle recovery Daytime detection Vietnam 



The study was supported by Science and Technology Incubator Youth Program, managed by the Center for Science and Technology Development, Ho Chi Minh Communist Youth Union, the contract number is “20/2017/ HÐ-KHCN-VU”.


  1. 1.
    Nguyen, T.P., Tran, D.N.-N., Huynh, T.K., Ha, S.V.-U.H.: Disorder detection approach to background modeling in traffic surveillance system. J. Sci. Technol. Vietnamese Acad. Sci. Technol. 52(4A), 140149 (2014)Google Scholar
  2. 2.
    Pham, L.H., Duong, T.T., Tran, H.M., Ha, S.V.U.: Vision-based approach for urban vehicle detection and classification. In: 2013 Third World Congress on Information and Communication Technologies (WICT 2013), pp. 305–310 (2013)Google Scholar
  3. 3.
    Ha, S.V.-U., Pham, L.H., Tran, H.M., Ho-Thanh, P.: Improved vehicles detection and classification algorithm for traffic surveillance system. J. Inf. Assurance Secur. 9(5), 268277 (2014)Google Scholar
  4. 4.
    ATON datasets by UCSD.
  5. 5.
    Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans. Pattern Anal. Mach. Intell. 25(10), 1337–1342 (2003)CrossRefGoogle Scholar
  6. 6.
    Hsieh, J.-W., Wen-Fong, H., Chang, C.-J., Chen, Y.-S.: Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image Vis. Comput. 21(6), 505–516 (2003)CrossRefGoogle Scholar
  7. 7.
    Xiao, M., Han, C.-Z., Zhang, L.: Moving shadow detection and removal for traffic sequences. Int. J. Autom. Comput. 4(1), 3846 (2007)CrossRefGoogle Scholar
  8. 8.
    Huang, J.B., Chen, C.S.: Moving cast shadow detection using Physics-based features. In: 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009, pp. 2310–2317 (2009)Google Scholar
  9. 9.
    Leone, A., Distante, C.: Shadow detection for moving objects based on texture analysis. Pattern Recognit. 404 (2007)Google Scholar
  10. 10.
    Sanin, A., Sanderson, C., Lovell, B.C.: Improved shadow removal for robust person tracking in surveillance scenarios. In: 2010 20th International Conference on Pattern Recognition, pp. 141–144 (2010)Google Scholar
  11. 11.
    Chien, S., Ma, S., Chen, L.: Efficient moving object segmentation algorithm using background registration technique. IEEE Trans. Circuits Syst. Video Technol. 12(7), 577586 (2002)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringInternational University, Vietnam National University HCMCHo Chi Minh CityVietnam

Personalised recommendations