Multimedia Tools and Applications

, Volume 76, Issue 18, pp 18321–18337 | Cite as

Shadow removal for pedestrian detection and tracking in indoor environments

  • Lingxiang Zheng
  • Xiaoyang Ruan
  • Yunbiao Chen
  • Minzheng Huang


This paper presents a method of shadow removal to improve the accuracy of pedestrian detection and tracking in indoor environments. The proposed method can be divided into four steps: building a background model which can be automatically updated, extract moving objects region, eliminating moving objects shadows, classifying and track pedestrians. The background model is built with pixel value and the updating of Gussian. The approach for real time background-foreground extraction is used to extract pedestrian region that may contains multiple shadows. In the gray histogram space, based on the depth value of the gray images, a reasonable threshold is set to remove shadows from various pedestrians. In this work, we propose a methodology using the foreground frames without shadows to detect and track the pedestrians across training datasets. Comparative experimental results show that our method is capable of dealing with shadows and detecting moving pedestrians in cluttered environments.


Background elimination Shadow removal Gray histogram space Pedestrian detectiing Pedestrian tracking 


  1. 1.
    Chen B, Lei Y (2004) Indoor and outdoor people detection and shadow suppression by exploiting HSV color information. In: CIT’04. The Fourth International Conference on Computer and Information Technology. IEEEGoogle Scholar
  2. 2.
    Chen C, Aggarwal JK (2010) Human shadow removal with unknown light source. In: 20th International Conference on Pattern Recognition (ICPR). IEEEGoogle Scholar
  3. 3.
    Choi J, Yoo YJ, Choi JY (2010) Adaptive shadow estimator for removing shadow of moving object. Comput Vis Image Underst 114(9):1017–1029CrossRefGoogle Scholar
  4. 4.
    Cheung SS, Kamath C (2004) Robust techniques for background subtraction in urban traffic video. In: Proceedings of SPIEGoogle Scholar
  5. 5.
    Cheng HD, Chen YH, Jiang XH (2000) Thresholding using two-dimensional histogram and fuzzy entropy principle. IEEE Trans Image Process 9(4):732–735CrossRefGoogle Scholar
  6. 6.
    Dollar P et al (2012) Pedestrian detection: An evaluation of the state of the art. IEEE Trans Pattern Anal Mach Intell 34(4):743–761CrossRefGoogle Scholar
  7. 7.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. IEEEGoogle Scholar
  8. 8.
    Everingham M et al (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338CrossRefGoogle Scholar
  9. 9.
    Gavrila DM, Giebel J, Munder S (2004) Vision-based pedestrian detection: The protector system. In: Intelligent Vehicles Symposium. IEEEGoogle Scholar
  10. 10.
    Guo L et al (2010) Study on pedestrian detection and tracking with monocular vision. In: 2nd International Conference on Computer Technology and Development (ICCTD). IEEEGoogle Scholar
  11. 11.
    Huerta I et al (2007) Detection and removal of chromatic moving shadows in surveillance scenarios. In: Computer Vision, IEEE 12th International Conference on 2009. IEEEGoogle Scholar
  12. 12.
    Horn BK, Schunck BG (1981) Determining optical flow. Artif Intell 17 (1):185–203CrossRefGoogle Scholar
  13. 13.
    Hsieh J et al (2003) Shadow elimination for effective moving object detection by Gaussian shadow modeling. Image Vis Comput 21(6):505–516CrossRefGoogle Scholar
  14. 14.
    Hurney P et al (2015) Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors. Intelligent Transport Systems, IET 9.1:75–85Google Scholar
  15. 15.
    Jeong S, Kang S, Kim J (2013) Vehicle detection based on the use of shadow region and edge. In: Fifth International Conference on Digital Image Processing. International Society for Optics and PhotonicsGoogle Scholar
  16. 16.
    Jia Y et al (2013) A novel moving cast shadow detection of vehicles in traffic scene. In: Intelligent Science and Intelligent Data Engineering. Springer, pp 115–124Google Scholar
  17. 17.
    Ji-Hong P, Wei-Xin X (1999) Adaptive multi thresholds image segmentation based on potential function clustering. Chin J Comput 22(7):758–762Google Scholar
  18. 18.
    Kurup U et al (2012) Predicting and Classifying Pedestrian Behavior Using an Integrated Cognitive Architecture. Proceedings Behavior Representation in Modeling Simulation (BRIMS)Google Scholar
  19. 19.
    Kelly P (2008) Pedestrian detection and tracking using stereo vision techniques. Dublin City UniversityGoogle Scholar
  20. 20.
    Leone A, Distante C, Buccolieri F (2006) A shadow elimination approach in video-surveillance context. Pattern Recogn Lett 27(5):345–355CrossRefGoogle Scholar
  21. 21.
    Liu Y, Bin Z (2010) The improved moving object detection and shadow removing algorithms for video surveillance. In: International Conference on Computational Intelligence and Software Engineering (CiSE). IEEEGoogle Scholar
  22. 22.
    Leone A, Distante C (2007) Shadow detection for moving objects based on texture analysis. Pattern Recogn 40(4):1222–33CrossRefzbMATHGoogle Scholar
  23. 23.
    Munder S, Schnorr C, Gavrila DM (2008) Pedestrian detection and tracking using a mixture of view-based shapeCtexture models. IEEE Trans Intell Transp Syst 9 (2):333–343CrossRefGoogle Scholar
  24. 24.
    Mohan A, Papageorgiou C, Poggio T (2001) Example-based object detection in images by components. IEEE Trans Pattern Anal Mach Intell 23(4):349–361CrossRefGoogle Scholar
  25. 25.
    Maddalena L, Petrosino A (2008) A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans Image Process 17 (7):1168–1177MathSciNetCrossRefGoogle Scholar
  26. 26.
    Otsu N (1975) A threshold selection method from gray-level histograms. Automatica 11(285-296):23–27Google Scholar
  27. 27.
    Singh VK, Wu B, Nevatia R (2008) Pedestrian tracking by associating tracklets using detection residuals, Motion and video Computing. WMVC 2008 IEEE Workshop on IEEE:1–8Google Scholar
  28. 28.
    Saadat S, Teknomo K (2011) Automation of pedestrian tracking in a crowded situation. In: Pedestrian and Evacuation Dynamics. Springer, pp 231–239Google Scholar
  29. 29.
    Shrivastava A, Patel VM, Pillai JK, Chellappa R (2015) Generalized dictionaries for multiple instance learning. Int J Comput Vis 114(2-3):288–305MathSciNetCrossRefGoogle Scholar
  30. 30.
    Wang L et al (2007) Object detection combining recognition and segmentation. Comput Vis CACCV:189–199Google Scholar
  31. 31.
    Wang S, Su T, Lai S (2011) Detecting moving objects from dynamic background with shadow removal. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEEGoogle Scholar
  32. 32.
    Wang J et al (2004) Shadow detection and removal for traffic images. In: IEEE International Conference on Networking, Sensing and Control. IEEEGoogle Scholar
  33. 33.
    Wu M, Lin C, Chang C (2007) Brain tumor detection using color-based k-means clustering segmentation. In: IIHMSP 2007. Third International Conference on Intelligent Information Hiding and Multimedia Signal Processing. IEEEGoogle Scholar
  34. 34.
    Xu L, Landabaso JL, Pards M (2005) Shadow removal with blob-based morphological reconstruction for error correction. In: IEEE International Conference on Acoustics, Speech and Signal ProcessingGoogle Scholar
  35. 35.
    Xu T et al (2012) A fast and robust pedestrian detection framework based on static and dynamic information. In: IEEE International Conference on Multimedia and Expo (ICME). IEEEGoogle Scholar
  36. 36.
    Ye J, Gao T, Zhang J (2012) Moving object detection with background subtraction and shadow removal. In: 9th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD). IEEEGoogle Scholar
  37. 37.
    Ye Q, Han Z, Jiao J et al (2013) Human detection in images via piecewise linear support vector machines[J]. IEEE Trans Image Process 22(2):778–789MathSciNetCrossRefGoogle Scholar
  38. 38.
    Zhou Y, Sun L, Zhang J A shadow elimination method based on color and texture. In: 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems (ICIS). IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Lingxiang Zheng
    • 1
  • Xiaoyang Ruan
    • 1
  • Yunbiao Chen
    • 1
  • Minzheng Huang
    • 1
  1. 1.School of Information Science and EngineeringXiamen UniversityXiamenChina

Personalised recommendations