搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于随机聚类的复杂背景建模与前景检测算法

毕国玲 续志军 陈涛 王建立 张延坤

引用本文:
Citation:

基于随机聚类的复杂背景建模与前景检测算法

毕国玲, 续志军, 陈涛, 王建立, 张延坤

Complex background model and foreground detection based on random aggregation

Bi Guo-Ling, Xu Zhi-Jun, Chen Tao, Wang Jian-Li, Zhang Yan-Kun
PDF
导出引用
  • 为了构建鲁棒的背景模型和提高前景目标检测的准确性, 综合考虑同一位置的像素点在时间上的关联性和与其相邻像素的空间关联性, 基于经典的ViBe算法中的随机聚类思想提出了一种复杂背景建模和前景检测方法. 利用样本一致性原理, 采用前n帧序列图像得到初始化背景, 避免了Ghost现象的发生; 根据实际复杂背景的动态反馈获取自适应聚类阈值和自适应更新阈值进行随机聚类, 从而实现了对动态背景的适应性; 通过全局扰动阈值和局部像素级判断阈值的结合, 实现了对光照缓慢变化、快速变化以及突然变化的免疫性, 准确地分割前景目标. 对多组数据集的测试结果表明, 本文算法较大地提高了背景模型对动态背景、光照变化及相机抖动的复杂背景的适应性和鲁棒性. 算法还能很好地适用于红外图像检测运动目标的场合, 扩展了本算法的应用范围. 在没有进行任何图像预处理和形态学后处理情况下, 得到的原始前景检测精度优于其他对比算法.
    In order to build a robust background model and improve the accuracy of the foreground object detection, we give a comprehensive consideration on the same location pixels of the relevance of time and the correlation of space with its adjacent pixels; and based on the classic ViBe of random algorithm ideas, a kind of complex background model and foreground detection method is proposed. Using the first n series of images to initialize the background model with the sample consistency principle, we can avoid the appearance of the “Ghost” phenomenon; and get the difference between each pixel and its multiple sample value in the background model, and then compute the sum and the average. The average shows the dynamic degree of the background point which is the corresponding pixel background of dynamic feedback information. We get the adaptive clustering threshold and adaptive updating threshold with the dynamic feedback to make random clusters realize the adaptability to dynamic background and combine the global disturbance threshold with the local pixel level judgment threshold to implement the immunity of illumination with slow changes, fast changes or sudden changes, so that we can segment the prospect target accurately. By selecting neighborhood pixels to update the neighborhood background randomly in terms of spatial information dissemination mechanism, a good detection effect is obtained in the case of camera shake. Through multiple sets of test data, experimental results show that this algorithm can significantly improve the adaptability and robustness of the background model such as dynamic backgrounds, illumination changes, and camera shake. The algorithm can well apply to the occasion of moving targets in infrared image detection, and expand its application range. Without any image preprocessing and morphological post-processing, the original detection accuracy of foreground is superior to other algorithms.
    • 基金项目: 国家科技重大专项(批准号: 2012ZX04001-011)和国家自然科学基金(批准号: 60977001) 资助的课题.
    • Funds: Project supported by the National Science and Technology Major Project of the Ministry of Science and Technology of China (Grant No. 2012ZX04001-011), and the National Natural Science Foundation of China (Grant No. 60977001).
    [1]

    Barron J, Fleet D 1994 Int. J. Comp. Vis. 12 42

    [2]

    Meier T, Ngun K N 1999 IEEE Trans. Circuits Sys. Video Techn. 9 1190

    [3]

    Fujiyoshi H, Lipton A 1998 Proc. IEEE 98 15

    [4]

    Chen X M, Liao J, Li B, Chen Q M 2014 Optics and Precision Engineering 22 2545 (in Chinese) [陈星明, 廖娟, 李勃, 陈启美 2014 光学精密工程 22 2545]

    [5]

    Zhao X D, Liu P, Tang X L, Liu J F 2011 Acta Automatica Sinica 37 915 (in Chinese) [赵旭东, 刘鹏, 唐降龙, 刘家锋 2011 自动化学报 37 915]

    [6]

    He S H, Yang S Q, Shi A G, Li T W 2009 Chin. Phys. Sin. 58 794 (in Chinese) [何四华, 杨绍清, 石爱国, 李天伟 2009 物理学报 58 794]

    [7]

    Jin Z L, Han J, Zhang Y, Bai L F 2014 Chin. Phys Sin. 63 069501 (in Chinese) [金左轮, 韩静, 张毅, 柏连发 2014 物理学报 63 069501]

    [8]

    Xing H Y, Qi Z D, Xu W 2012 Chin. Phys Sin. 61 240504 (in Chinese) [行鸿彦, 祁峥东, 徐伟 2012 物理学报 61 240504]

    [9]

    Zivkovic Z 2004 Proceedings of the 17th International Conference on IEEE, August 23-26, 2004 p28

    [10]

    Maddalena L, Petrosino A 2008 IEEE Transactions on Image Processing 17 1168

    [11]

    Kim K, Chalidabhongse T H, Harwood D 2005 Realtime Imaging 11 172

    [12]

    Godbehere A B, Matsukawa A, Goldberg K 2012 American Control Conference (ACC) on Montreal, QC, June 27-29 2012 p4305

    [13]

    Wang H Z, David S 2006 Proceedings of the 18th International Conference on Pattern Recognition Hong Kong, August 2-6, 2006 p223

    [14]

    Barnich O, Van Droogenbroeck M 2011 Image Processing, IEEE 20 1709

    [15]

    YU Y, Cao M W, Yue F 2014 Chinese Journal of Scientific Instrument 35 924 (in Chinese) [余烨, 曹明伟, 岳峰 2014 仪器仪表学报 35 924]

    [16]

    Su Y Z, Li A H, Jiang K, Jin G Z 2014 Journal of Computer-Aided Design & Computer Graphics 26 232 (in Chinese) [苏延召, 李艾华, 姜柯, 金广智 2014 计算机辅助设计与图形学学报 26 232]

    [17]

    Yuan H Z, Li G, Yang J, Gao Z S 2012 Journal of Sichuan University 44 156 (in Chinese) [袁红照, 李纲, 杨军, 高志升 2012 四川大学学报 44 156]

    [18]

    Li X, Xu G L, Cheng Y H, Wang B, Tian Y P, Li K Y 2014 Jisuanji Yu Xiandaihua 3 89 (in Chinese) [李旭, 徐贵力, 程月华, 王彪, 田裕鹏, 李开宇 2014 计算机与现代化 3 89]

    [19]

    Goyette N, Jodoin P, Porikli F 2012 Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on Providence, RI, June 16-21, 2012 p1

  • [1]

    Barron J, Fleet D 1994 Int. J. Comp. Vis. 12 42

    [2]

    Meier T, Ngun K N 1999 IEEE Trans. Circuits Sys. Video Techn. 9 1190

    [3]

    Fujiyoshi H, Lipton A 1998 Proc. IEEE 98 15

    [4]

    Chen X M, Liao J, Li B, Chen Q M 2014 Optics and Precision Engineering 22 2545 (in Chinese) [陈星明, 廖娟, 李勃, 陈启美 2014 光学精密工程 22 2545]

    [5]

    Zhao X D, Liu P, Tang X L, Liu J F 2011 Acta Automatica Sinica 37 915 (in Chinese) [赵旭东, 刘鹏, 唐降龙, 刘家锋 2011 自动化学报 37 915]

    [6]

    He S H, Yang S Q, Shi A G, Li T W 2009 Chin. Phys. Sin. 58 794 (in Chinese) [何四华, 杨绍清, 石爱国, 李天伟 2009 物理学报 58 794]

    [7]

    Jin Z L, Han J, Zhang Y, Bai L F 2014 Chin. Phys Sin. 63 069501 (in Chinese) [金左轮, 韩静, 张毅, 柏连发 2014 物理学报 63 069501]

    [8]

    Xing H Y, Qi Z D, Xu W 2012 Chin. Phys Sin. 61 240504 (in Chinese) [行鸿彦, 祁峥东, 徐伟 2012 物理学报 61 240504]

    [9]

    Zivkovic Z 2004 Proceedings of the 17th International Conference on IEEE, August 23-26, 2004 p28

    [10]

    Maddalena L, Petrosino A 2008 IEEE Transactions on Image Processing 17 1168

    [11]

    Kim K, Chalidabhongse T H, Harwood D 2005 Realtime Imaging 11 172

    [12]

    Godbehere A B, Matsukawa A, Goldberg K 2012 American Control Conference (ACC) on Montreal, QC, June 27-29 2012 p4305

    [13]

    Wang H Z, David S 2006 Proceedings of the 18th International Conference on Pattern Recognition Hong Kong, August 2-6, 2006 p223

    [14]

    Barnich O, Van Droogenbroeck M 2011 Image Processing, IEEE 20 1709

    [15]

    YU Y, Cao M W, Yue F 2014 Chinese Journal of Scientific Instrument 35 924 (in Chinese) [余烨, 曹明伟, 岳峰 2014 仪器仪表学报 35 924]

    [16]

    Su Y Z, Li A H, Jiang K, Jin G Z 2014 Journal of Computer-Aided Design & Computer Graphics 26 232 (in Chinese) [苏延召, 李艾华, 姜柯, 金广智 2014 计算机辅助设计与图形学学报 26 232]

    [17]

    Yuan H Z, Li G, Yang J, Gao Z S 2012 Journal of Sichuan University 44 156 (in Chinese) [袁红照, 李纲, 杨军, 高志升 2012 四川大学学报 44 156]

    [18]

    Li X, Xu G L, Cheng Y H, Wang B, Tian Y P, Li K Y 2014 Jisuanji Yu Xiandaihua 3 89 (in Chinese) [李旭, 徐贵力, 程月华, 王彪, 田裕鹏, 李开宇 2014 计算机与现代化 3 89]

    [19]

    Goyette N, Jodoin P, Porikli F 2012 Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on Providence, RI, June 16-21, 2012 p1

  • [1] 徐艳, 王培光, 杨青, 董江涛. 时空相关多通道聚类的运动目标检测. 物理学报, 2019, 68(16): 164203. doi: 10.7498/aps.68.20190161
    [2] 崔智高, 王华, 李艾华, 王涛, 李辉. 动态背景下基于光流场分析的运动目标检测算法. 物理学报, 2017, 66(8): 084203. doi: 10.7498/aps.66.084203
    [3] 苏理云, 孙唤唤, 王杰, 阳黎明. 混沌噪声背景下微弱脉冲信号的检测及恢复. 物理学报, 2017, 66(9): 090503. doi: 10.7498/aps.66.090503
    [4] 赵欣慰, 金韬, 池灏, 曲嵩. 不同光照条件下水下成像背景光的建模与研究. 物理学报, 2015, 64(10): 104201. doi: 10.7498/aps.64.104201
    [5] 胡进峰, 张亚璇, 李会勇, 杨淼, 夏威, 李军. 基于最优滤波器的强混沌背景中谐波信号检测方法研究. 物理学报, 2015, 64(22): 220504. doi: 10.7498/aps.64.220504
    [6] 行鸿彦, 张强, 徐伟. 混沌海杂波背景下的微弱信号检测混合算法. 物理学报, 2015, 64(4): 040506. doi: 10.7498/aps.64.040506
    [7] 行鸿彦, 朱清清, 徐伟. 一种混沌海杂波背景下的微弱信号检测方法. 物理学报, 2014, 63(10): 100505. doi: 10.7498/aps.63.100505
    [8] 高文, 汤洋, 朱明. 复杂背景下目标检测的级联分类器算法研究. 物理学报, 2014, 63(9): 094204. doi: 10.7498/aps.63.094204
    [9] 行鸿彦, 程艳燕, 徐伟. 基于广义窗函数和最小二乘支持向量机的混沌背景下微弱信号检测. 物理学报, 2012, 61(10): 100506. doi: 10.7498/aps.61.100506
    [10] 高仕龙, 钟苏川, 韦鹍, 马洪. 基于混沌和随机共振的微弱信号检测. 物理学报, 2012, 61(18): 180501. doi: 10.7498/aps.61.180501
    [11] 行鸿彦, 祁峥东, 徐伟. 基于选择性支持向量机集成的海杂波背景中的微弱信号检测. 物理学报, 2012, 61(24): 240504. doi: 10.7498/aps.61.240504
    [12] 行鸿彦, 龚平, 徐伟. 海杂波背景下小目标检测的分形方法. 物理学报, 2012, 61(16): 160504. doi: 10.7498/aps.61.160504
    [13] 王丹, 金小峥. 可调聚类系数加权无标度网络建模及其拥塞问题研究. 物理学报, 2012, 61(22): 228901. doi: 10.7498/aps.61.228901
    [14] 袁艳, 孙成明, 黄锋振, 赵慧洁, 王潜. 深空背景下空间目标紫外特性建模方法研究. 物理学报, 2011, 60(8): 089501. doi: 10.7498/aps.60.089501
    [15] 行鸿彦, 金天力. 基于对偶约束最小二乘支持向量机的混沌海杂波背景中的微弱信号检测. 物理学报, 2010, 59(1): 140-146. doi: 10.7498/aps.59.140
    [16] 孙成明, 袁艳, 张修宝. 深空背景下空间目标红外特性建模方法研究. 物理学报, 2010, 59(10): 7523-7530. doi: 10.7498/aps.59.7523
    [17] 行鸿彦, 徐 伟. 混沌背景中微弱信号检测的神经网络方法. 物理学报, 2007, 56(7): 3771-3776. doi: 10.7498/aps.56.3771
    [18] 姜 斌, 王宏强, 黎 湘, 郭桂蓉. 海杂波背景下的目标检测新方法. 物理学报, 2006, 55(8): 3985-3991. doi: 10.7498/aps.55.3985
    [19] 李 月, 路 鹏, 杨宝俊, 赵雪平. 用一类特定的双耦合Duffing振子系统检测强色噪声背景中的周期信号. 物理学报, 2006, 55(4): 1672-1677. doi: 10.7498/aps.55.1672
    [20] 李 月, 杨宝俊, 石要武. 色噪声背景下微弱正弦信号的混沌检测. 物理学报, 2003, 52(3): 526-530. doi: 10.7498/aps.52.526
计量
  • 文章访问数:  4896
  • PDF下载量:  302
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-02-06
  • 修回日期:  2015-03-19
  • 刊出日期:  2015-08-05

/

返回文章
返回