Advertisement

Segmentation of Cast Shadow in Surveillance Video Sequence: A Mean-Shift Filtering Based Approach

  • M. Chandrajit
  • R. Girisha
  • T. Vasudev
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 14)

Abstract

The accuracy of the segmented motion objects tracking in surveillance videos will decline when shadows are detected as moving objects. To address this, a new spatial based method for the segmentation of cast shadow regions from the motion segmented video sequence is proposed. The motion segmented frame is processed using Mean-Shift filter for smoothening and then the cast shadow pixels are segmented by interval value based representation of RGB color channels. The proposed model overcomes the restrictions on direction of light source and surface orientation which are generally considered for cast shadow segmentation. Experiments have been conducted on challenging indoor and outdoor video sequences of IEEE Change Detection (CD) 2014 and ATON datasets. Further, comparative evaluation with contemporary methods using standard evaluation metrics has been carried out to corroborate the efficacy of proposed method.

Keywords

Cast shadow segmentation Video surveillance Mean-shift Interval value 

References

  1. 1.
    Zhang D, Lu G (2001) Segmentation of moving objects in image sequence: a review. Circuits, Syst Signal Process 20(2):143–183Google Scholar
  2. 2.
    Prati A, Cucchiara R, Mikic I, Trivedi M (2001) Analysis and detection of shadows in video streams: a comparative evaluation. IEEE Trans 2:IIGoogle Scholar
  3. 3.
    Sanin A, Sanderson C, Lovell BC (2012) Shadow detection: a survey and comparative evaluation of recent methods. Pattern Recogn 45:1684–1695Google Scholar
  4. 4.
    Ullah H, Ullah M, Uzair M, Rehman F (2010) Comparative study: the evaluation of shadow detection methods. Int J Video Image Proc Netw Secur 01(10)Google Scholar
  5. 5.
    Salvador E, Cavallaro A, Ebrahimi T (2004) Cast shadow segmentation using invariant color features. Comput Vis Image Underst 95(2):238–259Google Scholar
  6. 6.
    Leone A, Distante C (2007) Shadow detection for moving objects based on texture analysis. ELSEVIER, Pattern Recogn 40:1222–1233Google Scholar
  7. 7.
    Souza T, Schnitman L, Oliveira L (2012) Eigen analysis and gray alignment for shadow detection applied to urban scene images. In: IEEE international conference on intelligent robots and systems (IROS) workshop on planning, perception and navigation for intelligent vehiclesGoogle Scholar
  8. 8.
    Amato A, Mozerov MG, Bagdanov AD, Gonzalez J (2011) Accurate moving cast shadow suppression based on local color constancy detection. Image Proc, IEEE Trans 20(10):2954–2966MathSciNetCrossRefGoogle Scholar
  9. 9.
    Nadimi S, Bhanu B (2004) Physical models for moving shadow and object detection in video. Pattern Anal Mach Intell, IEEE Trans 26(8):1079–1087CrossRefGoogle Scholar
  10. 10.
    Huerta I, Holte MB, Moeslund TB, Gonzàlez J (2015) Chromatic shadow detection and tracking for moving foreground segmentation. Image Vis Comput 41:42–53Google Scholar
  11. 11.
    Cucchiara R, Grana C, Piccardi M, Prati A (2003) Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans Pattern Anal Mach Intell 25(10):1337–1342Google Scholar
  12. 12.
    Chandrajit M, Girisha R, Vasudev T, Ashok CB (2016) Cast and self shadow segmentation in video sequences using interval based eigen value representation. Int J Comput Appl 142(4):27–32Google Scholar
  13. 13.
    Girisha R, Murali S (2009) Adaptive cast shadow elimination algorithm for surveillance videos using t random values. In: India conference (INDICON), 2009 Annual IEEE, pp 1–4Google Scholar
  14. 14.
    Huang J-B, Chen C-S (2009) Moving cast shadow detection using physics-based features. In: IEEE conference on computer vision and pattern recognition (CVPR 2009), pp 2310–2317, 20–25Google Scholar
  15. 15.
    Chen C-C, Aggarwal JK (2010) Human shadow removal with unknown light source. In: 2010 20th international conference on pattern recognition (ICPR), pp 2407–2410, 23–26Google Scholar
  16. 16.
    Wang Y, Tan T, Loe K-F, Wu J-K (2005) A probabilistic approach for foreground and shadow segmentation in monocular image sequences. ELSEVIER, Pattern Recogn 38:1937–1946Google Scholar
  17. 17.
    Wang J, Wang Y, Jiang M, Yan X, Song M (2014) Moving cast shadow detection using online sub-scene shadow modeling and object inner-edges analysis. J Vis Commun Image Represent 25(5):978–993Google Scholar
  18. 18.
    Hsieh J-W, Hu W-F, Chang C-J, Chen Y-S (2003) Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image Vis Comput 21(6):505–516Google Scholar
  19. 19.
    Tian J, Qi X, Qu L, Tang Y (2016) New spectrum ratio properties and features for shadow detection. Pattern Recogn 51:85–96Google Scholar
  20. 20.
    Al-Najdawi N, Bez HE, Singhai J, Edirisinghe EA (2015) A survey of cast shadow detection algorithms. Pattern Recogn Lett 33(6):752–764Google Scholar
  21. 21.
    Chandrajit M, Girisha R, Vasudev T (2014) Motion segmentation from surveillance videos using T-test statistics. In Proceedings of the 7th ACM india computing conference (COMPUTE’14), vol 2. ACM, 10 p. doi: 10.1145/2675744.2675748
  22. 22.
    Soille P (1999) Morphological image analysis: principles and applications. Springer, pp 173–174Google Scholar
  23. 23.
    Comaniciu D, Meer P (2002) Mean shift: a robust approach toward feature space analysis. IEEE Trans Pattern Anal Mach Intell (IEEE) 24(5):603–619Google Scholar
  24. 24.
    Keinosuke F, Hostetler LD (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Transac Inf Theory (IEEE) 21(1):32–40. doi: 10.1109/TIT.1975.1055330
  25. 25.
    Goyette N, Jodoin PM, Porikli F, Konrad J, Ishwar P (2012) ChangeDetection.net: a new change detection benchmark dataset. In: Proceedings of IEEE workshop on change detection (CDW-2012) at CVPR-2012, Providence, RIGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Maharaja Research FoundationMaharaja Institute of Technology MysoreMandyaIndia
  2. 2.PET Research FoundationPES College of EngineeringMandyaIndia

Personalised recommendations