Multimedia Tools and Applications

, Volume 77, Issue 17, pp 22567–22586 | Cite as

Efficient background subtraction for thermal images using reflectional symmetry pattern (RSP)

  • D. JeyabharathiEmail author
  • Dejey


Nowadays, thermal image processing has gained more attention. Thermal camera’s cost is decreasing, and so many real-time applications use thermal cameras since they have an ability to detect objects in darkness and track objects in the video. A background subtraction approach using Reflectional Symmetry Pattern (RSP) for thermal image background subtraction is proposed based on the assumption that the geometric reflectional symmetrical pattern of each of the objects (person) is much lower than the surrounding background. Reflectional symmetrical texture pattern can be used to create a subspace from the result of frame differencing approach. Statistical parameters such as VP (Vector Product), VD (Vector Direction) can be used to create an accurate background model. As a result, the proposed scheme can provide a high precision and less error rate to meet the requirements of object detection from real-time thermal videos.


Vector product Vector direction Reflectional symmetrical patterns 


  1. 1.
    Cheng L, Gong M (2009) Realtime background subtraction from dynamic scenes. Proc 2th IEEE ICCV: 2066–2073Google Scholar
  2. 2.
    Conaire C, Connor N, Cooke E, Smeaton A (2006a) Comparison of fusion methods for thermo-visual surveillance tracking. 9th Int Conf Info Fusion: 1–7Google Scholar
  3. 3.
    Conaire C, Connor N, Cooke E, Smeaton A (2006b) Multispectral object segmentation and retrieval in surveillance video. Int Conf Image Process: 2381–2384Google Scholar
  4. 4.
    Davis J, Sharma V (2005) Fusion-based background-subtraction using contour saliency. IEEE Conf Comput Vision Pattern Recogn - Workshops 3:11–23Google Scholar
  5. 5.
    Javed S, Oh S, Sobral S, Bouwmans T, Jung S (2014) Or-pca with mrf for robust foreground detection in highly dynamic backgrounds. Asian Conf Comput Vision. Springer: 284–299Google Scholar
  6. 6.
    Jeyabharathi, D, Dejey, 2016,Vehicle tracking and speed measurement system (VTSM) based on novel feature descriptor: diagonal hexadecimal pattern (DHP), J Visual Commun Image Rep, ,vol 40, part B, pp. 816–830Google Scholar
  7. 7.
    Jeyabharathi D, Dejey (2017) Background subtraction and object tracking via key frame-based rotational symmetry dynamic texture. Adv Image Process Tech Appl.
  8. 8.
    Jeyabharathi D, Dejey D (2016) A novel rotational symmetry dynamic texture (RSDT) based sub space construction and SCD (similar-congruent-dissimilar) based scoring model for background subtraction in real time videos. Multimed Tools Appl 75(24):17617–17645CrossRefGoogle Scholar
  9. 9.
    Jeyabharathi D, Dejey D (2018) New feature descriptor: extended symmetrical-diagonal hexadecimal pattern for efficient background subtraction and object tracking. Comput Elect EngGoogle Scholar
  10. 10.
    Kesavaraja D, Shenbagavalli A (2017) QoE enhancement in cloud virtual machine allocation using eagle strategy of hybrid krill herd optimization. J Parallel Distrib Comput.
  11. 11.
    Li P, Wang Q, Hu, Cai S (2016) Efficient background modeling based on sparse representation and outlier iterative removal. IEEE Trans Circ Syst Video Technol 26(2):278–289CrossRefGoogle Scholar
  12. 12.
    Li W, Zheng D, Zhao T, Yang M (2012) An effective approach pedestrian detection in Thennal imagery. 8th ICNC(IEEE): 82–97Google Scholar
  13. 13.
    Liao S, Zhao G, Kellokumpu V, Pietikainen M, Li S (2010) Modeling pixel process with scale invariant local patterns for background subtraction in complex scenes. IEEE Int Conf CVPR: 1301–1306Google Scholar
  14. 14.
    Lin L, Xu Y, Liang X, Lai J (2014) Complex background subtraction by pursuing dynamic Spatio – temporal models. IEEE Trans Image Process 23(7):3191–3201MathSciNetCrossRefzbMATHGoogle Scholar
  15. 15.
    Liu X, China X, Zhao G, Yao J, Qi C (2015a) Background subtraction based on low-rank and structured sparse decomposition. IEEE Trans Image Process 24(8):2502–2514MathSciNetCrossRefGoogle Scholar
  16. 16.
    Monnet A, Mittal A, Paragios N, Ramesh V (2003) Background modeling and subtraction of dynamic scenes. Proc 9th IEEE ICCV: 1305–1312Google Scholar
  17. 17.
    Nascimento J, Marques J (2006) Performance evaluation of object detection algorithms for video surveillance. IEEE Trans Multimed 8:761–774CrossRefGoogle Scholar
  18. 18.
    Panda D, Meher S (2016a) 'Detection of moving objects using fuzzy color difference histogram based background subtraction. IEEE Sign Process Lett 23(1):45–49CrossRefGoogle Scholar
  19. 19.
    Peijiang C (2009) Moving object detection based on background extraction. Comput Netw Multimed Technol (CNMT)Google Scholar
  20. 20.
    San M, Crocco M, Cristani M (2012) Recursive segmentation based on higher order statistics in thermal imaging pedestrian detection. ISCCSPGoogle Scholar
  21. 21.
    Sheikh Y, Shah M (2005) Bayesian modeling of dynamic scenes for object detection. IEEE Trans Pattern Anal Mach Intell 27(11):1778–1792CrossRefGoogle Scholar
  22. 22.
    Singh S, Csonka P, Waldron K (2006) Optical flow aided motion estimation for legged locomotion. IEEE-lCIR&SGoogle Scholar
  23. 23.
    Sobral A, Baker C, Bouwmans T, Zahzah E (2014) Incremental and multi-feature tensor subspace learning applied for background modeling and subtraction. International Conference Image Analysis and Recognition, Springer, pp. 94–103Google Scholar
  24. 24.
    Stauffer C, Grimson W (1999) Adaptive background mixture models for real-time tracking. IEEE Conf Comput Vision Pattern Recogn: 2246–2252Google Scholar
  25. 25.
    Stocker A (2002) An improved 2D optical flow sensor for motion segmentation. Proc IEEE Int Sym Circ Syst 2Google Scholar
  26. 26.
    Valizadeh S, Nasiopoulos P, Ward R (2016) Perceptual distortion measurement in the coding unit mode selection for 3D-HEVC. Consum Electro (ICCE), 2016 IEEE Int ConfGoogle Scholar
  27. 27.
    Valizadeh S, Nasiopoulos P, Ward R (2017) Perceptual rate distortion optimization of 3D–HEVC using PSNR-HVS. Multimed Tools Appl.
  28. 28.
    Venkataraman B, Saandeep R, Baskaran N, Roy M, Madhivanan A, Sukumar R (2005) Using satellite telemetry to mitigate elephant-human conflict: an experiment in northern West Bengal, India. Curr Sci 88(11):1827–1831 Vol. 66, pp. 454–473Google Scholar
  29. 29.
    Wang Q, Zhang R (2008) LPP-HOG: a new local image descriptor for fast human detection. IEEE 2008Google Scholar
  30. 30.
    Xin B, Tian Y, Wang Y, Gao, W (2015a) Background subtraction via generalized fused lasso foreground modeling. IEEE Conf Comput Vision Pattern Recogn (CVPR): 4676–4684Google Scholar
  31. 31.
    Xu Z, Zhu S, Cheng Y (2017) Object detection via superpixel and 3D self-organizing background subtraction. Contrl Decision Conf (CCDC), 2017 29th ChineseGoogle Scholar
  32. 32.
    Zhu Q, Yeh M, Cheng K, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. CVPR 2:1491–1498Google Scholar
  33. 33.
    Zivkovic Z (2004) Improved adaptive Gaussian mixture model for background subtraction. Proc 17th IEEE ICPR: 28–31Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Information TechnologySri Krishna College of TechnologyCoimbatoreIndia
  2. 2.Department of Computer Science and EngineeringAnna University Regional Campus - TirunelveliTirunelveliIndia

Personalised recommendations