Skip to main content

Self-organizing background subtraction using color and depth data

Abstract

Background subtraction from color and depth data is a fundamental task for video surveillance applications that use data acquired by RGBD sensors. We present a method that adopts a self-organizing neural background model previously adopted for RGB videos to model the color and depth background separately. The resulting color and depth detection masks are combined to guide the selective model update procedure and to achieve the final result. Extensive experimental results and comparisons with several state-of-the-art methods on a publicly available dataset show that the exploitation of depth information allows achieving much higher performance than just using color, accurately handling color and depth background maintenance challenges.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Notes

  1. http://SceneBackgroundModeling.net

References

  1. Almazan EJ, Jones GA (2013) Tracking people across multiple non-overlapping RGB-D sensors. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2013). Portland, pp 831–837

  2. Barnich O, Droogenbroeck MV (2009) Vibe: a powerful random technique to estimate the background in video sequences. In: 2009 IEEE international conference on acoustics, speech and signal processing, pp 945–948. https://doi.org/10.1109/ICASSP.2009.4959741

  3. Bouwmans T, Maddalena L, Petrosino A (2017) Scene background initialization: a taxonomy. Pattern Recogn Lett 96:3–11

    Article  Google Scholar 

  4. Cai Z, Han J, Liu L, Shao L (2017) RGB-D datasets using microsoft Kinect or similar sensors: a survey. Multimed Tools Appl 76(3):4313–4355

    Article  Google Scholar 

  5. Camplani M, del Blanco CR, Salgado L, Jaureguizar F, García N (2014) Multi-sensor background subtraction by fusing multiple region-based probabilistic classifiers. Pattern Recogn Lett 50:23–33. https://doi.org/10.1016/j.patrec.2013.09.022. Depth Image Analysis

    Article  Google Scholar 

  6. Camplani M, Salgado L (2014) Background foreground segmentation with RGB-D Kinect data: An efficient combination of classifiers. J Vis Commun Image Represent 25(1):122–136. https://doi.org/10.1016/j.jvcir.2013.03.009. Visual Understanding and Applications with RGB-D Cameras

    Article  Google Scholar 

  7. Camplani M, Maddalena L, Moyá Alcover G, Petrosino A, Salgado L (2017) SBM-RGBD Dataset. http://rgbd2017.na.icar.cnr.it/SBM-RGBDdataset.html

  8. Camplani M, Maddalena L, Moyá Alcover G, Petrosino A, Salgado L (2017) A Benchmarking framework for background subtraction in RGBD videos. In: Battiato S, Farinella GM, Leo M, Gallo G (eds) New trends in image analysis and processing – ICIAP 2017. Springer International Publishing, pp 219–229

  9. Camplani M, Paiement A, Mirmehdi M, Damen D, Hannuna S, Burghardt T, Tao L (2017) Multiple human tracking in rgb-depth data: a survey. IET Comput Vis 11(4):265–285

    Article  Google Scholar 

  10. Clapés A, Reyes M, Escalera S (2013) Multi-modal user identification and object recognition surveillance system. Pattern Recogn Lett 34(7):799–808

    Article  Google Scholar 

  11. Crabb R, Tracey C, Puranik A, Davis J (2008) Real-time foreground segmentation via range and color imaging. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2008), pp 1–5. https://doi.org/10.1109/CVPRW.2008.4563170

  12. De Gregorio M, Giordano M (2017) WiSARD-based learning and classification of background in RGBD videos. In: Battiato S, Farinella GM, Leo M, Gallo G (eds) New trends in image analysis and processing – ICIAP 2017. Springer International Publishing

  13. Ding J, Ma R, Chen S (2008) A scale-based connected coherence tree algorithm for image segmentation. IEEE Trans Image Process 17(2):204–216

    MathSciNet  Article  Google Scholar 

  14. Dollȧr P, Zitnick CL (2015) Fast edge detection using structured forests. IEEE Trans Pattern Anal Mach Intell 37(8):1558–1570

    Article  Google Scholar 

  15. Elgammal AM, Harwood D, Davis LS (2000) Non-parametric model for background subtraction. In: Proceedings of ECCV. Springer-Verlag, pp 751–767

  16. Fernandez-Sanchez EJ, Diaz J, Ros E (2013) Background subtraction based on color and depth using active sensors. Sensors 13:8895–8915

    Article  Google Scholar 

  17. Fernandez-Sanchez EJ, Rubio L, Diaz J, Ros E (2014) Background subtraction model based on color and depth cues. Mach Vis Appl 25(5):1211–1225. https://doi.org/10.1007/s00138-013-0562-5

    Article  Google Scholar 

  18. Firman M (2016) RGBD datasets: past, present and future. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2016), pp 661–673

  19. Frick A, Kellner F, Bartczak B, Koch R (2009) Generation of 3d-tv ldv-content with time-of-flight camera. In: 2009 3DTV conference: the true vision - capture, transmission and display of 3d video, pp 1–4. https://doi.org/10.1109/3DTV.2009.5069624

  20. Galanakis G, Zabulis X, Koutlemanis P, Paparoulis S, Kouroumalis V (2014) Tracking persons using a network of rgbd cameras. In: Proceedings of the 7th international conference on PErvasive technologies related to assistive environments, PETRA ’14. ACM, New York, pp 63:1–63:4

  21. Gallego J, Pardás M (2014) Region based foreground segmentation combining color and depth sensors via logarithmic opinion pool decision, vol 25. https://doi.org/10.1016/j.jvcir.2013.03.019. Visual Understanding and Applications with RGB-D Cameras

    Article  Google Scholar 

  22. Gordon G, Darrell T, Harville M, Woodfill J (1999) Background estimation and removal based on range and color. In; IEEE conference on computer vision and pattern recognition (CVPR ’99), Ft. Collins, pp 2459–2464. https://doi.org/10.1109/CVPR.1999.784721

  23. Goyette N, Jodoin P, Porikli F, Konrad J, Ishwar P (2012) Changedetection.net: a new change detection Benchmark dataset. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2012), pp 1–8. https://doi.org/10.1109/CVPRW.2012.6238919

  24. Goyette N, Jodoin P, Porikli F, Konrad J, Ishwar P (2014) A novel video dataset for change detection Benchmarking. IEEE Trans Image Process 23 (11):4663–4679

    MathSciNet  Article  Google Scholar 

  25. Guomundsson SA, Larsen R, Aanaes H, Pardas M, Casas JR (2008) Tof imaging in smart room environments towards improved people tracking. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2008), pp 1–6. https://doi.org/10.1109/CVPRW.2008.4563154

  26. Han J, Shao L, Xu D, Shotton J (2013) Enhanced computer vision with microsoft Kinect sensor: A review. IEEE Trans Cybern 43(5):1318–1334. https://doi.org/10.1109/TCYB.2013.2265378

    Article  Google Scholar 

  27. Harville M, Gordon G, Woodfill J (2001) Foreground segmentation using adaptive mixture models in color and depth. In: Proceedings IEEE workshop on detection and recognition of events in video, pp 3–11. https://doi.org/10.1109/EVENT.2001.938860

  28. Huang J, Wu H, Gong Y, Gao D (2016) Random sampling-based background subtraction with adaptive multi-cue fusion in RGBD videos. In: 2016 9th international congress on image and signal processing, biomedical engineering and informatics (CISP-BMEI), pp 30–35. https://doi.org/10.1109/CISP-BMEI.2016.7852677

  29. Javed S, Bouwmans T, Sultana M, Jung SK (2017) Moving object detection on rgb-d videos using graph regularized spatiotemporal rpca. In: Battiato S, Farinella GM, Leo M, Gallo G (eds) New trends in image analysis and processing – ICIAP 2017. Springer International Publishing, pp 230–241

  30. Jodoin P, Maddalena L, Petrosino A, Wang Y (2017) Extensive Benchmark and survey of modeling methods for scene background initialization. IEEE Trans Image Process 26(11):5244–5256. https://doi.org/10.1109/TIP.2017.2728181

    MathSciNet  Article  Google Scholar 

  31. Kim Y Unpublished

  32. Kwolek B, Kepski M (2014) Human fall detection on embedded platform using depth maps and wireless accelerometer. Comput Methods Programs Biomed 117 (3):489–501

    Article  Google Scholar 

  33. Laugraud B, Piérard S, Braham M, Van Droogenbroeck M (2015) Simple median-based method for stationary background generation using background subtraction algorithms. In: New trends in image analysis and processing-ICIAP 2015 workshops, LNCS, vol 9281. Springer, pp 477–484. https://doi.org/10.1007/978-3-319-23222-5_58

    Chapter  Google Scholar 

  34. Leens J, Piérard S, Barnich O, Van Droogenbroeck M, Wagner JM (2009) Combining color, depth, and motion for video segmentation. In: Fritz M, Schiele B, Piater JH (eds) Proceedings of computer vision systems: 7th international conference on computer vision systems, ICVS 2009 Liège, Belgium. Springer Berlin Heidelberg, Berlin, pp 104–113. https://doi.org/10.1007/978-3-642-04667-4_11

    Google Scholar 

  35. Li GL, Wang X Avgm-d. Unpublished

  36. Liang Z, Liu X, Liu H, Chen W (2016) A refinement framework for background subtraction based on color and depth data. In: 2016 IEEE international conference on image processing (ICIP), pp 271–275. https://doi.org/10.1109/ICIP.2016.7532361

  37. Maddalena L, Petrosino A RGBD-SOBS Software. http://www.na.icar.cnr.it/maddalena.l/MODLab/SoftwareRGBD-SOBS.html

  38. Maddalena L, Petrosino A (2008) A self-organizing approach to background subtraction for visual surveillance applications. IEEE Trans Image Process 17 (7):1168–1177

    MathSciNet  Article  Google Scholar 

  39. Maddalena L, Petrosino A (2010) A fuzzy spatial coherence-based approach to background/foreground separation for moving object detection. Neural Comput Appl 19:179–186

    Article  Google Scholar 

  40. Maddalena L, Petrosino A (2012) The SOBS algorithm: what are the limits? In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2012), pp 21–26. https://doi.org/10.1109/CVPRW.2012.6238922

  41. Maddalena L, Petrosino A (2017) Exploiting color and depth for background subtraction. In: Battiato S, Farinella GM, Leo M, Gallo G (eds) New trends in image analysis and processing – ICIAP 2017. Springer International Publishing, pp 254–265

  42. Maddalena L, Petrosino A (2018) Background subtraction for moving object detection in RGBD data: a survey. J Imag 4(5). https://doi.org/10.3390/jimaging4050071. http://www.mdpi.com/2313-433X/4/5/71

    Article  Google Scholar 

  43. Mahbub U, Imtiaz H, Roy T, Rahman MS, Ahad MAR (2013) A template matching approach of one-shot-learning gesture recognition. Pattern Recogn Lett 34 (15):1780–1788. Smart Approaches for Human Action Recognition

    Article  Google Scholar 

  44. Minematsu T, Shimada A, Uchiyama H, Taniguchi R (2017) Simple combination of appearance and depth for foreground segmentation. In: Battiato S, Farinella GM, Leo M, Gallo G (eds) New trends in image analysis and processing – ICIAP 2017. Springer International Publishing

  45. Moyá-Alcover G, Elgammal A, Jaume-i-Capó A, Varona J (2017) Modeling depth for nonparametric foreground segmentation using RGBD devices. Pattern Recogn Lett 96:76–85

    Article  Google Scholar 

  46. Nguyen VT, Vu H, Tran TH (2015) An efficient combination of RGB and depth for background subtraction. In: Dang QA, Nguyen XH, Le HB, Nguyen VH, Bao VNQ (eds) Some current advanced researches on information and computer science in Vietnam: post-proceedings of the first NAFOSTED conference on information and computer science. https://doi.org/10.1007/978-3-319-14633-1_4. Springer International Publishing, pp 49–63

    Google Scholar 

  47. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66

    Article  Google Scholar 

  48. Schiller I, Koch R (2011) Improved video segmentation by adaptive combination of depth keying and mixture-of-gaussians. In: Proceedings of the 17th Scandinavian conference on image analysis, SCIA 2011, Ystad, pp 59–68. https://doi.org/10.1007/978-3-642-21227-7_6

    Chapter  Google Scholar 

  49. Song S, Xiao J (2013) Tracking revisited using RGBD camera: unified Benchmark and baselines. In: IEEE international conference on computer vision (ICCV 2013), pp 233–240

  50. Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: Proceedings of 1999 IEEE computer society conference on computer vision and pattern recognition (cat. no PR00149), vol 2, pp 252. https://doi.org/10.1109/CVPR.1999.784637

  51. Stormer A, Hofmann M, Rigoll G (2010) Depth gradient based segmentation of overlapping foreground objects in range images. In: 2010 13th international conference on information fusion, pp 1–4. https://doi.org/10.1109/ICIF.2010.5712108

  52. Toyama K, Krumm J, Brumitt B, Meyers B (1999) Wallflower: principles and practice of background maintenance. In: Proceedings of the seventh IEEE international conference on computer vision, vol 1, pp 255–261. https://doi.org/10.1109/ICCV.1999.791228

  53. Trabelsi R, Jabri I, Smach F, Bouallegue A (2017) Efficient and fast multi-modal foreground-background segmentation using RGBD data. Pattern Recogn Lett 97:13–20

    Article  Google Scholar 

  54. Xia L, Chen CC, Aggarwal JK (2011) Human detection using depth information by Kinect. In: IEEE computer society conference on computer vision and pattern recognition workshops (CVPRW 2011), pp 15–22. https://doi.org/10.1109/CVPRW.2011.5981811

  55. Zhang Z (2012) Microsoft Kinect sensor and its effect. IEEE MultiMedia 19 (2):4–10

    Article  Google Scholar 

Download references

Acknowledgements

L. Maddalena acknowledges the GNCS (Gruppo Nazionale di Calcolo Scientifico) and the INTEROMICS Flagship Project funded by MIUR, Italy. A. Petrosino wishes to acknowledge Project VIRTUALOG Horizon 2020-PON 2014/2020.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Lucia Maddalena.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Maddalena, L., Petrosino, A. Self-organizing background subtraction using color and depth data. Multimed Tools Appl 78, 11927–11948 (2019). https://doi.org/10.1007/s11042-018-6741-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6741-7

Keywords

  • Background subtraction
  • Color and depth data
  • RGBD