Moving object detection algorithm based on improved visual background extractor

被引：0
|
作者：
Mo S. [1 ]
Deng X. [1 ]
Wang S. [1 ]
Jiang D. [1 ]
Zhu Z. [2 ]
机构：
[1] College of Electronic Science and Engineering, National University of Defense Technology, Changsha, 410073, Hunan
[2] Unit 61541 of the Chinese People's Liberation Army, Beijing
来源：
| 1600年 / Chinese Optical Society卷 / 36期
关键词：
Adaptive threshold; Dynamic background; Ghost elimination; Machine vision; Moving object detection; Visual background extractor; Visual saliency;
D O I：
10.3788/AOS201636.0615001
中图分类号：
学科分类号：
摘要：
Aiming at the problems of ghost, background turbulence in high frequency, camera jitter and error of background update caused by spatial propagation technique in classic visual background extractor (ViBe) algorithm, an improved ViBe algorithm is proposed. Combined with visual saliency, the new method determines whether the ghost target exists in the background model or not, and adaptively changes the time subsampling factor through the level of ghost for each pixel in the background model, which can improve the rate of ghost elimination. Self-adaptive threshold is adopted in the process of model matching by establishing a blinking degree matrix to judge the high-frequency disturbance level of background, so that the background model is better suitable for the dynamic background. Small object discard and hole filling strategies are added to the new method. It can judge if a foreground pixel is a noise point caused by camera jitter or an error of background update by counting pixel numbers in 24-connected neighboring region of foreground pixels. Therefore, it can improve the robustness of the algorithm. Experiments demonstrate that the improved algorithm is a good way to make up for the deficiency of the original ViBe algorithm. The accuracy and recognition rate are improved greatly. © 2016, Chinese Lasers Press. All right reserved.
引用
收藏
页数：10
相关论文
共 24 条
  • [1] Benezeth Y., Jodoin P., Emile B., Et al., Review and evaluation of commonly-implemented background subtraction algorithms, 19th International Conference on Pattern Recognition, pp. 1-4, (2008)
  • [2] Ding Q., Gu G., Xu F., Et al., Moving target detection on moving camera with the presence of strong parallax, Laser & Optoelectronics Progress, 52, 9, (2015)
  • [3] Jahne B., Digital Image Processing, pp. 7-13, (2000)
  • [4] Piccardi M., Background subtraction techniques: A review, 2004 IEEE International Conference on Systems, Man and Cybernetics, 4, pp. 3099-3104, (2004)
  • [5] Zhuang Z., Zhang C., Yang J., Et al., Investigation on visual background extractor based on gray feature and adaptive threshold, Journal of Electronics & Information Technology, 37, 2, pp. 347-352, (2015)
  • [6] Chen Y., Ren K., Gu G., Et al., Moving object detection based on improved single Gaussian background model, Chinese J Lasers, 41, 11, (2014)
  • [7] Elgammal A., Harwood D., Davis L., Non-parametric Model for Background Subtraction, pp. 751-767, (2000)
  • [8] Elgammal A., Duraiswami R., Harwood D., Et al., Background and foreground modeling using nonparametric kernel density estimation for visual surveillance, Proceedings of the IEEE, 90, 7, pp. 1151-1163, (2002)
  • [9] Tavakkoli A., Nicolescu M., Bebis G., Et al., Non-parametric statistical background modeling for efficient foreground region detection, Machine Vision and Applications, 20, 6, pp. 395-409, (2008)
  • [10] Monari E., Pasqual C., Fusion of background estimation approaches for motion detection in non-static backgrounds, 2007 IEEE Conference on Advanced Video and Signal Based Surveillance, pp. 347-352, (2007)
123