Abstract
Background subtraction is an important computer vision scheme for segmenting moving objects from a video. The imminent IoT era imposes severe constraints on camera systems in terms of area, speed, power, and accuracy. This chapter presents a new background subtraction scheme which is based on Poisson noise model, where we use a Poisson mixture model (PMM) for modeling dynamic backgrounds. Furthermore, we have used a method for sequential estimation of parameters of the PMM which does not allow the parameters to fluctuate with random noise. Resultantly, our method achieves a reduction of 17.76% and 8.16% in percent of wrong classification compared to the hardware implementations of Gaussian Mixture Models and Pixel-based Adaptive Segmented (PBAS) methods, respectively. The proposed scheme is also very fast, low power, and requires very little logic resources. The memory bandwidth requirement of the proposed scheme is 6.66%, 41.36%, and 90.48% lower compared to state-of-the-art FPGA implementation of GMM, ViBe, and PBAS algorithms, respectively. The proposed background subtraction scheme achieves a significant speed up compared to FPGA implementations of GMM (by 42.68%), ViBe (by 115%), and PBAS (by 142.2%) schemes. Similarly, the energy consumption of the proposed method is 76.39% and 99.9% less compared to GMM and PBAS, respectively. In summary, the advantages of the proposed method in accuracy, speed, and energy consumption combined together make it especially suitable for embedded applications.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
McIvor AM (2000) Background subtraction techniques. Proc Image Vision Comput 4:3099–3104
Khan MUK, Kyung CM, Yahya KM (2013) Optimized learning rate for energy waste minimization in a background subtraction based surveillance system. In: IEEE int. symp. on circuits and sys. (ISCAS). IEEE, Piscataway, pp 2355–2360
Khan MUK, Khan A, Kyung C-M (2014) Dual frame rate motion detection for memory-and energy-constrained surveillance systems. In: IEEE int. conf. on adv. video and signal based surveillance (AVSS). IEEE, Piscataway, pp 81–86
Khan MUK, Khan A, Kyung C-M (2017) Ebscam: background subtraction for ubiquitous computing. IEEE Trans Very Large Scale Integra VLSI Syst 25(1):35–47
Piccardi M (2004) Background subtraction techniques: a review. In: 2004 IEEE international conference on systems, man and cybernetics, vol 4. IEEE, Piscataway, pp 3099–3104
Kristensen F, Hedberg H, Jiang H, Nilsson P, Öwall V (2008) An embedded real-time surveillance system: implementation and evaluation. J Signal Process Syst 52(1):75–94
Radke RJ, Andra S, Al-Kofahi O, Roysam B (2005) Image change detection algorithms: a systematic survey. IEEE Trans Image Process 14(3):294–307
Seki M, Wada T, Fujiwara H, Sumi K (2003) Background subtraction based on cooccurrence of image variations. In: Proceedings 2003 IEEE computer society conference on computer vision and pattern recognition, 2003, vol 2. IEEE, Piscataway, pp II–II
Power PW, Schoonees JA (2002) Understanding background mixture models for foreground segmentation. In: Proceedings image and vision computing, New Zealand, vol 2002, pp 10–11
Tsai D-M, Lai S-C (2009) Independent component analysis-based background subtraction for indoor surveillance. IEEE Trans Image Process 18(1):158–167
Lin H-H, Liu T-L, Chuang J-H (2009) Learning a scene background model via classification. IEEE Trans Signal Process 57(5):1641–1654
Sivabalakrishnan M, Manjula D (2009) An efficient foreground detection algorithm for visual surveillance system. Int J Comput Sci Netw Secur 9(5):221–227
Jacques J, Jung CR, Musse SR (2006) A background subtraction model adapted to illumination changes. In: Proc. IEEE int. conf. on image processing, pp 1817–1820
Davis JW, Sharma V (2004) Robust background-subtraction for person detection in thermal imagery. In: IEEE int. workshop on object tracking and classification beyond the visible spectrum
Wren CR, Azarbayejani A, Darrell T, Pentland AP (1997) Pfinder: real-time tracking of the human body. IEEE Trans Pattern Anal Mach Intell 19(7):780–785
Manzanera A, Richefeu JC (2007) A new motion detection algorithm based on σ − δ background estimation. Pattern Recogn Lett 28(3):320–328
Manzanera A (2007) σ-δ background subtraction and the Zipf law. In: Progress in pattern recognition, image analysis and applications, pp 42–51
Lacassagne L, Manzanera A, Denoulet J, Mérigot A (2009) High performance motion detection: some trends toward new embedded architectures for vision systems. J Real-Time Image Process 4(2):127–146
Lacassagne L, Manzanera A (2009) Motion detection: fast and robust algorithms for embedded systems. In: Proc. IEEE int. conf. on image processing
Elgammal A, Harwood D, Davis L (2000) Non-parametric model for background subtraction. In: Computer VisionECCV 2000, pp 751–767
Tavakkoli A, Nicolescu M, Bebis G, Nicolescu M (2009) Non-parametric statistical background modeling for efficient foreground region detection. Mach Vis Appl 20(6):395–409
Stauffer C, Grimson WEL (1999) Adaptive background mixture models for real-time tracking. In: IEEE conf. on comp. vis. and pattern recog., vol 2. IEEE, Piscataway
White B, Shah M (2007) Automatically tuning background subtraction parameters using particle swarm optimization. In: 2007 IEEE international conference on multimedia and expo. IEEE, Piscataway, pp 1826–1829
Atrey PK, Kumar V, Kumar A, Kankanhalli MS (2006) Experiential sampling based foreground/background segmentation for video surveillance. In: 2006 IEEE international conference on multimedia and expo. IEEE, Piscataway, pp 1809–1812
Park J, Tabb A, Kak AC (2006) Hierarchical data structure for real-time background subtraction. In: 2006 IEEE international conference on image processing. IEEE, Piscataway, 1849–1852
Porikli F, Tuzel O (2003) Human body tracking by adaptive background models and mean-shift analysis. In: IEEE international workshop on performance evaluation of tracking and surveillance, pp 1–9
Yang S-Y, Hsu C-T (2006) Background modeling from GMM likelihood combined with spatial and color coherency. In: 2006 IEEE international conference on image processing. IEEE, Piscataway, pp 2801–2804
Lee D-S (2005) Effective gaussian mixture learning for video background subtraction. IEEE Trans Pattern Anal Mach Intell 27(5):827–832
Zivkovic Z (2004) Improved adaptive gaussian mixture model for background subtraction. In: Proc. IEEE int. conf. on pattern recognition, vol 2, pp 28–31
Wang R, Bunyak F, Seetharaman G, Palaniappan K (2014) Static and moving object detection using flux tensor with split gaussian models. In: Proc. IEEE conf. on computer vision and pattern recognition Wkshps., pp 414–418
Kim K, Chalidabhongse TH, Harwood D, Davis L (2005) Real-time foreground–background segmentation using codebook model. Real-Time Imaging 11(3):172–185
Sigari MH, Fathy M (2008) Real-time background modeling/subtraction using two-layer codebook model. In: Proceedings of the international multiconference of engineers and computer scientists, vol 1
Barnich O, Van Droogenbroeck M (2011) Vibe: a universal background subtraction algorithm for video sequences. IEEE Trans Image Process 20(6):1709–1724
Haque M, Murshed M (2013) Perception-inspired background subtraction. IEEE Trans Circuits Syst Video Technol 23(12):2127–2140
Hofmann M, Tiefenbacher P, Rigoll G (2012) Background segmentation with feedback: the pixel-based adaptive segmenter. In: Proc. IEEE conf. on computer vision and pattern recognition wkshps. IEEE, Piscataway, pp 38–43
Wang H, Suter D (2006) Background subtraction based on a robust consensus method. In: 18th international conference on pattern recognition, 2006. ICPR 2006, vol 1. IEEE, Piscataway, pp 223–226
Guillot C, Taron M, Sayd P, Pham QC, Tilmant C, Lavest J-M (2010) Background subtraction adapted to PTZ cameras by keypoint density estimation. In: Proceedings of the British machine vision conference, p 34-1
Tavakoli HR, Rahtu E, Heikkilä J (2012) Temporal saliency for fast motion detection. In: Asian conference on computer vision. Springer, Berlin, pp 321–326
Hamid R, Sarma AD, DeCoste D, Sundaresan N (2015) Fast approximate matching of videos from hand-held cameras for robust background subtraction. In: 2015 IEEE winter conference on applications of computer vision (WACV). IEEE, Piscataway, pp 294–301
Foresti GL (1998) A real-time system for video surveillance of unattended outdoor environments. IEEE Trans Circuits Syst Video Technol 8(6):697–704
Kalpana Chowdary M, Suparshya Babu S, Susrutha Babu S, Khan H (2013) FPGA implementation of moving object detection in frames by using background subtraction algorithm. In: 2013 International conference on communications and signal processing (ICCSP). IEEE, Piscataway, pp 1032–1036
Lee Y, Kim Y-G, Lee C-H, Kyung C-M (2014) Memory-efficient background subtraction for battery-operated surveillance system. In: The 18th IEEE international symposium on consumer electronics (ISCE 2014). IEEE, Piscataway, pp 1–2
Chan W-K, Chien S-Y (2007) Real-time memory-efficient video object segmentation in dynamic background with multi-background registration technique. In: IEEE 9th workshop on multimedia signal processing, 2007. MMSP 2007. IEEE, Piscataway, pp 219–222
Gujrathi P, Priya RA, Malathi P (2014) Detecting moving object using background subtraction algorithm in FPGA. In: 2014 Fourth international conference on advances in computing and communications (ICACC). IEEE, Piscataway, pp 117–120
Menezes GGS, Silva-Filho AG (2010) Motion detection of vehicles based on FPGA. In: Programmable logic conference (SPL), 2010 VI Southern. IEEE, Piscataway, pp 151–154
Cherian S, Senthil Singh C, Manikandan M (2014) Implementation of real time moving object detection using background subtraction in FPGA. In: 2014 International conference on communications and signal processing (ICCSP). IEEE, Piscataway, pp 867–871
Hiraiwa J, Vargas E, Toral S (2010) An FPGA based embedded vision system for real-time motion segmentation. In: Proceedings of 17th international conference on systems, signals and image processing, Brazil
Abutaleb MM, Hamdy A, Abuelwafa ME, Saad EM (2009) FPGA-based object-extraction based on multimodal σ-δ background estimation. In: 2nd International conference on computer, control and communication, 2009. IC4 2009. IEEE, Piscataway, pp 1–7
Tabkhi H, Sabbagh M, Schirner G (2014) A power-efficient FPGA-based mixture-of-Gaussian (MoG) background subtraction for full-HD resolution. In: Proc. annual int. symp. on field-programmable custom computing machines, pp 241–241
Genovese M, Napoli E (2014) ASIC and FPGA implementation of the gaussian mixture model algorithm for real-time segmentation of high definition video. IEEE Trans Very Large Scale Integr VLSI Syst 22(3):537–547
Genovese M, Napoli E (2013) FPGA-based architecture for real time segmentation and denoising of HD video. J Real-Time Image Process 8(4):389–401
Genovese M, Napoli E, Petra N (2010) OpenCV compatible real time processor for background foreground identification. In: Proc. IEEE int. conf. on microelectronics, pp 467–470
Rodriguez-Gomez R, Fernandez-Sanchez EJ, Diaz J, Ros E (2015) Codebook hardware implementation on FPGA for background subtraction. J Real-Time Image Process 10(1):43–57
Kryjak T, Gorgon M (2013) Real-time implementation of the ViBe foreground object segmentation algorithm. In: Proc. IEEE federated conf. on computer science and information sys., pp 591–596
Kryjak T, Komorkiewicz M, Gorgon M (2013) Hardware implementation of the PBAS foreground detection method in FPGA. In: Proc. IEEE int. conf. mixed design of integrated circuits and sys., pp 479–484
Wang Y, Jodoin P-M, Porikli F, Konrad J, Benezeth Y, Ishwar P (2014) CDnet 2014: an expanded change detection benchmark dataset. In: Proc. IEEE conf. on computer vision and pattern recognition wkshps., pp 387–394
Elgammal A, Duraiswami R, Harwood D, Davis LS (2002) Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proc IEEE 90(7):1151–1163
Goyette N, Jodoin P-M, Porikli F, Konrad J, Ishwar P (2012) Changedetection. net: a new change detection benchmark dataset. In: Proc. IEEE conf. on computer vision and pattern recognition wkshps., pp 1–8
Jiang H, Ardö H, Öwall V (2009) A hardware architecture for real-time video segmentation utilizing memory reduction techniques. IEEE Trans Circuits Syst Video Technol 19(2):226–236
Ratnayake K, Amer A (2014) Embedded architecture for noise-adaptive video object detection using parameter-compressed background modeling. J Real-Time Image Process, pp 1–18
Shen Y, Hu W, Yang M, Liu J, Wei B, Lucey S, Chou CT (2016) Real-time and robust compressive background subtraction for embedded camera networks. IEEE Trans Mobile Comput 15(2):406–418
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Khan, M.U.K., Kyung, CM. (2020). Poisson Mixture Model for High Speed and Low-Power Background Subtraction. In: Liu, Y., Lin, YL., Kyung, CM., Yasuura, H. (eds) Smart Sensors and Systems. Springer, Cham. https://doi.org/10.1007/978-3-030-42234-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-42234-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-42233-2
Online ISBN: 978-3-030-42234-9
eBook Packages: EngineeringEngineering (R0)