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

动态背景下基于光流场分析的运动目标检测算法

崔智高 王华 李艾华 王涛 李辉

引用本文:
Citation:

动态背景下基于光流场分析的运动目标检测算法

崔智高, 王华, 李艾华, 王涛, 李辉

Moving object detection based on optical flow field analysis in dynamic scenes

Cui Zhi-Gao, Wang Hua, Li Ai-Hua, Wang Tao, Li Hui
PDF
导出引用
  • 针对现有动态背景下运动目标检测算法的不足,提出一种基于光流场分析的运动目标检测算法. 首先根据前背景在光流梯度幅值和光流矢量方向上的差异确定目标的大致边界,然后通过点在多边形内部原理获得边界内部的稀疏像素点,最后以超像素为节点,利用混合高斯模型拟合的表观信息和超像素的时空邻域关系构建马尔可夫随机场模型的能量函数,并通过使目标函数能量最小化得到最终的运动目标检测结果. 该算法不需要任何先验假设,能够同时处理动态背景和静态背景两种情况. 多组实验结果表明,本文算法在检测的准确性和处理速度上均优于现有算法.
    To overcome the limitation of existing algorithms for detecting moving objects from the dynamic scenes, a foreground detection algorithm based on optical flow field analysis is proposed. Firstly, the object boundary information is determined by detecting the differences in optical flow gradient magnitude and optical flow vector direction between foreground and background. Then, the pixels inside the objects are obtained based on the point-in-polygon problem from computational geometry. Finally, the superpixels per frame are acquired by over-segmenting method. And taking the superpixels as nodes, the Markov Random field model is built, in which the appearance information fitted by Gaussian Mixture Model is combined with spatiotemporal constraints of each superpixel. The final foreground detection result is obtained by finding the minimum value of the energy function. The proposed algorithm does not need any priori assumptions, and can effectively realize the moving object detection in dynamic and stationary background. The experimental results show that the proposed algorithm is superior to the existing state-of-the-art algorithms in the detection accuracy, robustness and time consuming.
      通信作者: 崔智高, cuizg10@tsinghua.edu.cn
    • 基金项目: 国家自然科学基金(批准号:61501470)资助的课题.
      Corresponding author: Cui Zhi-Gao, cuizg10@tsinghua.edu.cn
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 61501470).
    [1]

    Radke R, Andra S, Kofahi A, Roysam B 2005 IEEE Trans. Image Process. 14 294

    [2]

    Ren Y, Chua C, Ho Y 2003 Mach. Vision Appl. 13 332

    [3]

    Sheikh Y, Javed O, Kanade T 2009 Conference. on Computer Vision and Pattern Recognition(CVPR) Miami, USA, June 20-25, 2009 p1219

    [4]

    Chen L, Zhu S, Li X 2015 International Symposium on Computers Informatics Beijing, China, January 17-18, 2015 p742

    [5]

    Bi G L, Xu Z J, Chen T, Wang J L, Zhang Y S 2015 Acta Phys. Sin. 64 150701 (in Chinese) [毕国玲, 续志军, 陈涛, 王建立, 张延坤 2015 物理学报 64 150701]

    [6]

    Sun S W, Wang Y F, Huang F, Liao H Y 2013 J. Visual. Commun. Image Represent 24 232

    [7]

    Li A H, Cui Z G 2016 Moving Object Detection in Videos (Beijing: Science Press) p15 (in Chinese) [李艾华, 崔智高 2016 视频序列运动目标检测技术 (北京: 科学出版社) 第15页]

    [8]

    Lee Y, Kim J, Grauman K 2011 International Conference on Computer Vision(ICCV) Barcelona, Spain, November 6-13, 2011 p1995

    [9]

    Li W T, Chang H S, Lien K C, Chang H T, Wang Y C 2011 IEEE Trans. Image Proc. 22 2600

    [10]

    Zhang D, Javed O, Shah M 2013 Conference on Computer Vision and Pattern Recognition(CVPR) Oregon, Portland, June 25-27, 2013 p682

    [11]

    Elqursh A, Elgammal A 2012 European Conference on Computer Vision (ECCV) Florence, Italy, October 7-13, 2012 p228

    [12]

    Gao W, Tang Y, Zhu M 2014 Acta Phys Sin. 63 094204 (in Chinese) [高文, 汤洋, 朱明 2014 物理学报 63 094204]

    [13]

    Cui Z G, Li A H, Feng G Y 2015 Journal of Computer-Aided Design Computer Graphics 27 621 (in Chinese) [崔智高, 李艾华, 冯国彦 2015 计算机辅助设计与图形学学报 27 621]

    [14]

    Wang J, Adelson E 1994 IEEE Trans. Image Process. 3 625

    [15]

    Cremers D, Soatto S 2004 Int. J. Comput Vison 62 249

    [16]

    Yoon S, Park S, Kang S 2005 Pattern Recognit. Lett. 26 2221

    [17]

    Adhyapak S, Kehtarnavaz N, Nadin M 2007 J. Electron. Imaging 16 13012

    [18]

    Di S, Mattoccia S, Tombari F 2005 International Workshop on Computer Architecture for Machine Perception Palermo, Italy, July 4-6, 2005 p193

    [19]

    Bouguet J 2001 Intel Corporation 5 10

    [20]

    Brox T, Malik J 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p282

    [21]

    Achanta R, Shaji A, Smith K 2012 IEEE Trans. Pattern Anal. Mach. Intell. 34 2274

    [22]

    Achanta R, Shaji A 2010 EPFL Technical Report 1 149

    [23]

    Vazquez A, Avidan S, Pfister H 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p268

    [24]

    Fulkerson B, Vedaldi A, Soatto S 2009 International Conference on Computer Vision (ICCV) Kyoto, Japan, September 27-October 4, 2009 p670

    [25]

    Boykov Y, Veksler O, Zabih R 2001 IEEE Trans. Pattern Anal. Mach. Intell. 23 1222

    [26]

    Boykov Y, Funka L 2006 Int. J. Comput. Vison. 70 109

    [27]

    Tron R, Vidal R 2007 Conference on Computer Vision and Pattern Recognition (CVPR) Minneapolis, USA, June 18-23 2007 p1

    [28]

    Sand P, Teller S 2008 Int. J. Comput. Vison. 80 72

    [29]

    Goyette N, Jodoin P, Porikil F 2012 Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Providence, Rhode Island, June 16-21, 2012 p1

    [30]

    Cui X, Huang J, Zhang S, Metaxas D 2012 European Conference on Computer Vision (ECCV) Florence, Italy, October 7-13, 2012 p612

    [31]

    Sundaram N, Brox T, Keutzer K 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p438

  • [1]

    Radke R, Andra S, Kofahi A, Roysam B 2005 IEEE Trans. Image Process. 14 294

    [2]

    Ren Y, Chua C, Ho Y 2003 Mach. Vision Appl. 13 332

    [3]

    Sheikh Y, Javed O, Kanade T 2009 Conference. on Computer Vision and Pattern Recognition(CVPR) Miami, USA, June 20-25, 2009 p1219

    [4]

    Chen L, Zhu S, Li X 2015 International Symposium on Computers Informatics Beijing, China, January 17-18, 2015 p742

    [5]

    Bi G L, Xu Z J, Chen T, Wang J L, Zhang Y S 2015 Acta Phys. Sin. 64 150701 (in Chinese) [毕国玲, 续志军, 陈涛, 王建立, 张延坤 2015 物理学报 64 150701]

    [6]

    Sun S W, Wang Y F, Huang F, Liao H Y 2013 J. Visual. Commun. Image Represent 24 232

    [7]

    Li A H, Cui Z G 2016 Moving Object Detection in Videos (Beijing: Science Press) p15 (in Chinese) [李艾华, 崔智高 2016 视频序列运动目标检测技术 (北京: 科学出版社) 第15页]

    [8]

    Lee Y, Kim J, Grauman K 2011 International Conference on Computer Vision(ICCV) Barcelona, Spain, November 6-13, 2011 p1995

    [9]

    Li W T, Chang H S, Lien K C, Chang H T, Wang Y C 2011 IEEE Trans. Image Proc. 22 2600

    [10]

    Zhang D, Javed O, Shah M 2013 Conference on Computer Vision and Pattern Recognition(CVPR) Oregon, Portland, June 25-27, 2013 p682

    [11]

    Elqursh A, Elgammal A 2012 European Conference on Computer Vision (ECCV) Florence, Italy, October 7-13, 2012 p228

    [12]

    Gao W, Tang Y, Zhu M 2014 Acta Phys Sin. 63 094204 (in Chinese) [高文, 汤洋, 朱明 2014 物理学报 63 094204]

    [13]

    Cui Z G, Li A H, Feng G Y 2015 Journal of Computer-Aided Design Computer Graphics 27 621 (in Chinese) [崔智高, 李艾华, 冯国彦 2015 计算机辅助设计与图形学学报 27 621]

    [14]

    Wang J, Adelson E 1994 IEEE Trans. Image Process. 3 625

    [15]

    Cremers D, Soatto S 2004 Int. J. Comput Vison 62 249

    [16]

    Yoon S, Park S, Kang S 2005 Pattern Recognit. Lett. 26 2221

    [17]

    Adhyapak S, Kehtarnavaz N, Nadin M 2007 J. Electron. Imaging 16 13012

    [18]

    Di S, Mattoccia S, Tombari F 2005 International Workshop on Computer Architecture for Machine Perception Palermo, Italy, July 4-6, 2005 p193

    [19]

    Bouguet J 2001 Intel Corporation 5 10

    [20]

    Brox T, Malik J 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p282

    [21]

    Achanta R, Shaji A, Smith K 2012 IEEE Trans. Pattern Anal. Mach. Intell. 34 2274

    [22]

    Achanta R, Shaji A 2010 EPFL Technical Report 1 149

    [23]

    Vazquez A, Avidan S, Pfister H 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p268

    [24]

    Fulkerson B, Vedaldi A, Soatto S 2009 International Conference on Computer Vision (ICCV) Kyoto, Japan, September 27-October 4, 2009 p670

    [25]

    Boykov Y, Veksler O, Zabih R 2001 IEEE Trans. Pattern Anal. Mach. Intell. 23 1222

    [26]

    Boykov Y, Funka L 2006 Int. J. Comput. Vison. 70 109

    [27]

    Tron R, Vidal R 2007 Conference on Computer Vision and Pattern Recognition (CVPR) Minneapolis, USA, June 18-23 2007 p1

    [28]

    Sand P, Teller S 2008 Int. J. Comput. Vison. 80 72

    [29]

    Goyette N, Jodoin P, Porikil F 2012 Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Providence, Rhode Island, June 16-21, 2012 p1

    [30]

    Cui X, Huang J, Zhang S, Metaxas D 2012 European Conference on Computer Vision (ECCV) Florence, Italy, October 7-13, 2012 p612

    [31]

    Sundaram N, Brox T, Keutzer K 2010 European Conference on Computer Vision (ECCV) Crete, Greece, September 5-11, 2010 p438

  • [1] 许明伟, 杜康, 李可, 王飞翔, 肖体乔. 时变复杂背景自由运动目标的高灵敏追迹成像. 物理学报, 2023, 72(15): 150701. doi: 10.7498/aps.72.20230360
    [2] 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
    [3] 贾辉, 罗秀娟, 张羽, 兰富洋, 刘辉, 陈明徕. 透过散射介质对直线运动目标的全光成像及追踪技术. 物理学报, 2018, 67(22): 224202. doi: 10.7498/aps.67.20180955
    [4] 罗佳奇, 段焰辉, 夏振华. 基于自适应本征正交分解混合模型的跨音速流场分析. 物理学报, 2016, 65(12): 124702. doi: 10.7498/aps.65.124702
    [5] 梁潇, 钱志鸿, 田洪亮, 王雪. 基于马尔可夫决策模型的异构无线网络切换选择算法. 物理学报, 2016, 65(23): 236402. doi: 10.7498/aps.65.236402
    [6] 行鸿彦, 张强, 徐伟. 海杂波FRFT域的分形特征分析及小目标检测方法. 物理学报, 2015, 64(11): 110502. doi: 10.7498/aps.64.110502
    [7] 毕国玲, 续志军, 陈涛, 王建立, 张延坤. 基于随机聚类的复杂背景建模与前景检测算法. 物理学报, 2015, 64(15): 150701. doi: 10.7498/aps.64.150701
    [8] 王燕, 邹男, 付进, 梁国龙. 基于倒谱分析的单水听器目标运动参数估计. 物理学报, 2014, 63(3): 034302. doi: 10.7498/aps.63.034302
    [9] 侯旺, 于起峰, 雷志辉, 刘晓春. 基于分块速度域改进迭代运动目标检测算法的红外弱小目标检测. 物理学报, 2014, 63(7): 074208. doi: 10.7498/aps.63.074208
    [10] 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
    [11] 尹文也, 何伟基, 顾国华, 陈钱. 模拟回火马尔可夫链蒙特卡罗全波形分析方法. 物理学报, 2014, 63(16): 164205. doi: 10.7498/aps.63.164205
    [12] 钟剑, 费建芳, 黄思训, 黄小刚, 程小平. 多参数背景场误差模型在散射计资料台风风场反演中的应用. 物理学报, 2013, 62(15): 159302. doi: 10.7498/aps.62.159302
    [13] 谢文贤, 许鹏飞, 蔡力, 李东平. 随机双指数记忆耗散系统的非马尔可夫扩散. 物理学报, 2013, 62(8): 080503. doi: 10.7498/aps.62.080503
    [14] 危卫, 鲁录义, 顾兆林. 风沙运动的电场-流场耦合模型及气固两相流数值模拟. 物理学报, 2012, 61(15): 158301. doi: 10.7498/aps.61.158301
    [15] 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
    [16] 蔡诚俊, 方卯发, 肖兴, 黄江. 非马尔可夫环境下经典场驱动Jaynes-Cummings模型中原子的熵压缩. 物理学报, 2012, 61(21): 210303. doi: 10.7498/aps.61.210303
    [17] 郑力明, 刘颂豪, 王发强. 非马尔可夫环境下原子的几何相位演化. 物理学报, 2009, 58(4): 2430-2434. doi: 10.7498/aps.58.2430
    [18] 费蓉, 崔杜武. 马尔可夫随机过程中移动对象的空间特征分析及近似逼近研究. 物理学报, 2009, 58(8): 5133-5141. doi: 10.7498/aps.58.5133
    [19] 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
    [20] 阮航宇, 陈一新. 具有物理背景的高维Painlevé可积模型. 物理学报, 2001, 50(4): 577-585. doi: 10.7498/aps.50.577
计量
  • 文章访问数:  6409
  • PDF下载量:  320
  • 被引次数: 0
出版历程
  • 收稿日期:  2016-10-21
  • 修回日期:  2017-01-24
  • 刊出日期:  2017-04-05

/

返回文章
返回