A modified Gaussian mixture background model via spatiotemporal distribution with shadow detection

详细信息    查看全文

• 作者：Haiying Xia ; Shuxiang Song ; Liping He
• 关键词：GMM ; Intelligent video surveillance ; Spatial background model ; Dynamic background ; Shadow detection
• 刊名：Signal, Image and Video Processing
• 出版年：2016
• 出版时间：February 2016
• 年：2016
• 卷：10
• 期：2
• 页码：343-350
• 全文大小：678 KB
• 参考文献：1.Naylor, M., Annotated, C.I.A.: Digital Video for Intelligent Surveillance and Optimized Retrieval. University of Reading and Kingston University, Reading (2003)
  2.Harris, W.J.: The development of IVHS in North America. In: IEEE Vehicle Navigation and Information System Conference Proceedings, Plenary, pp. 3–10 (1994)
  3.Hu, W., Tan, T., Wang, L., Maybank, S.: A survey on visual surveillance of object motion and behaviors. IEEE Trans. SMC 34(3), 334–352 (2004)
  4.Cucchiara, R., Grana, C., Piccardi, M., Prati, A.: Statistic and knowledge-based moving object detection in traffic scenes. In: Proceedings of ITSC2000, pp. 27–32 (2000)
  5.Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2, 246–252 (1999)
  6.Techawatcharapaikul, C, Kaewtrakulpong, P, Siddhichai, S.: Outdoor vehicle and shadow segmentation by temporal edge density information of adjacent frames. In: Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2008. 5th International Conference on 1, 433–436 (2008)
  7.Zivkovic, Z., van der Heijden, F.: Recursive unsupervised learning of finite mixture models. IEEE Trans. Pattern Anal. Mach. Intell. 26(5), 651–656 (2004)CrossRef
  8.Zivkovic, Z: Improved adaptive gaussian mixture model for background subtraction. In: IEEE International Conference on Pattern Recognition (ICPR), vol. 2, Cambridge, UK, pp. 28–31 (2004)
  9.Zivkovic, Z., van der Heijden, F.: Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognit. Lett. 27(7), 773–780 (2006)CrossRef
  10.Bouttefroy, P.L.M., Bouzerdoum, A., Phung, S.L., et al.: On the analysis of background subtraction techniques using Gaussian Mixture Models. In: Acoustics Speech and Signal Processing (ICASSP), IEEE International Conference on, pp. 4042–4045 (2010)
  11.Horng-Horng, L., Jen-Hui, C., Tyng-Luh, L.: Regularized background adaptation: a novel learning rate control scheme for Gaussian mixture modeling. IEEE Trans. Image Process. 20(3), 822–836 (2011)MathSciNet CrossRef
  12.Lee, Chang-Hsing, Hsu, Sheng-Bin, Shih, Jau-Ling, Chou, Chih-Hsun: Continuous birdsong recognition using Gaussian mixture modeling of image shape features. IEEE Trans. Multimedia 15, 454–464 (2013)CrossRef
  13.Duarte-Carvajalino, J.M., Guoshen, Yu., Carin, L., Sapiro, G.: Task-driven, adaptive statistical compressive sensing of Gaussian mixture models. IEEE Trans. Signal Process. 61, 585–600 (2013)MathSciNet CrossRef
  14.Barnich, O., Van Droogenbroeck, M.: ViBe: A powerful random technique to estimate the background in video sequences, In: Proceedings of 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 945–948 (2009)
  15.Van Droogenbroeck, M., Barnich, O.: Visual background extractor. World Intellectual Property Organization, WO 2009/007198, p. 36, (2009)
  16.Barnich, O., Van Droogenbroeck, M.: ViBe: a universal background subtraction algorithm for video sequences. IEEE Trans. Image Process. 20(6), 1709–1724 (2011)MathSciNet CrossRef
  17.Van Droogenbroeck, M., Paquot, O.: ViBe: background subtraction: experiments and improvements for ViBe, In: Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 32–37 (2012)
  18.Seki, M., Wada, T., Fujiwara, H., Sumi, K.: Background subtraction based on cooccurrence of image variations. In: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, Los Alamitos, USA, pp. 65–72 (2003)
  19.Cucchiara, R. et al.: Improving shadow suppression in moving object detection with HSV color information. In: Proceedings of Intelligent Transportation Systems Conference, pp. 334–339 (2001)
  20.Prati, A., Mikic, I., Cucchiara, R.: Detecting moving shadows: formulation, algorithms and evaluation. IEEE Trans. PRMI 25, 918–923 (2003)
  21.Doshi, A, Trivedi, M.: “Hybrid cone-cylinder” codebook model for foreground detection with shadow and highlight suppression. In: Proceeding of IEEE International Conference on Video and Signal Based Surveillance, p. 19 (2006)
  22.Salvador, E., Cavallaro, A., Ebrahimi, T.: Shadow identification and classification using invariant color models. Comput. Vis. Image Underst. 95(2), 238–259 (2004)CrossRef
  23.Jodoin, P.-M., Mignotte, M., Konrad, J.: Statistical background subtraction using spatial cues. IEEE Trans. Circuits Syst. Video Technol. 17, 1758–1763 (2007)
  24.Cucchiara, R., Grana, C., et al.: Detecting moving objects, ghosts, and shadows in video streams. IEEE Trans. Pattern Anal. Mach. Intell. 25(10), 1337–1342 (2003)CrossRef
  25.El Baf, F., Bouwmans, T., Vachon, B.: Fuzzy statistical modeling of dynamic backgrounds for moving object detection in infrared videos. OTCBVS 2009, pp. 60–65, Miami, Florida (2009)
  26. http://​wordpress-jodoin.​dmi.​usherb.​ca/​
  
• 作者单位：Haiying Xia (1)
  Shuxiang Song (1)
  Liping He (1)
  
  1. College of Electronic Engineering, Guangxi Normal University, Guilin, 541004, China
  
• 刊物类别：Engineering
• 刊物主题：Signal,Image and Speech Processing
  Image Processing and Computer Vision
  Computer Imaging, Vision, Pattern Recognition and Graphics
  Multimedia Information Systems
  
• 出版者：Springer London
• ISSN：1863-1711

文摘

This paper proposes a modified Gaussian mixture model designed to improve sensitivity in highly dynamic environments, overcome the low background recovery rate of the traditional Gaussian mixture model (GMM). This model uses spatial information to compensate for time information, and the neighborhood of each pixel is sampled using a random number generation method to complete the spatial background modeling. The time distribution of each pixel is used to model the Gaussian mixture background. For foreground detection, a spatial background model and time background model are both utilized by a fusion decision-making method. We conduct experiments on a dataset consisting of 31 real-world videos. Through a series of comparisons between our improved GMM algorithm, frame difference algorithm, Stauffer and Grimson’s, T2F-MOG and Zivkovic’s, we measure that the average running time of our algorithm is 0.0428 s/frame, faster than T2F-MOG, and the Recall is significantly improved with our method. We conclude that the experimental results show that the proposed algorithm is real time and accurate.