计算机科学 ›› 2020, Vol. 47 ›› Issue (10): 174-179.doi: 10.11896/jsjkx.190800014
王恰, 戚湧
WANG Qia, QI Yong
摘要: 针对城市道路交通视频难以直接提取交通背景,导致前景目标检测不准确的问题,提出了一种基于帧间差分和统计直方图的交通视频背景建模方法。一个好的背景建模方法有利于后续目标检测及跟踪任务的良好开展。所提方法首先利用帧间差分法提取视频中每帧的大致运动区域作为前景运动目标,再利用统计直方图获得图像的灰度值分布状态,进行背景图像的估计,从而提取出高整洁度、低噪声点的背景图像。与已有背景建模方法的对比实验结果表明,无论是在普通交通场景,还是在车辆行驶缓慢的典型交通场景中,所提方法都可以提取出与真实背景相似匹配度更高的背景图像。
中图分类号:
[1]LIU H,ZHAO F M,CHEN W D.A moving object detection and tracking method based on adaptive background image[J].Journal of Naval Aeronautical And Astronautical University,2012,27(1):15-18. [2]COLLINS R,LIPTON A,KANADE T,et al.A system for video surveillance and monitoring:VSAM final report[R].America:Carnegie Mellon University,Technical Report:CMU-RI-TR-00-12,2000. [3]JAYABALAN E,KRISHNAN D A,PUGAZENDI R.Nonrigid object tracking in aerial videos by combined snaked and optical flow technique[J].Computer Graphics,Imaging and Visualisation,2007,21(6):388-396. [4]ZHANG Y S.Research on moving objects detection and tracking based on background subtraction with illumination robustness [D].Chengdu:Southwest Jiaotong University,2011. [5]LEE B,HEDLEY M.Background Estimation for Video Surveillance [C]//Image and vision computing New Zealand,2002:315-320. [6]WANG J J.A Traffic Video Background Extraction Algorithm based on Image Content Sensitivity[D].Qingdao:Ocean University of China,2011. [7]STAUFFER C,GRIMASON W E L.Adaptive background mixture models for real-time tracking[C]//Proceedings of the Computer Society Conference on Computer Vision and Pattern Recongnition.IEEE,1999:246-252. [8]KAEWTRKULPONG P,BOWDEN R.An improved adaptive background mixture model for real-time tracking with shadow detection[C]//Proceedings of the 2th European Workshop in Advanced Video Based Surveillance Systems,Providence.USA:Kluwer Academic Publishers,2001:1-5. [9]ZIVKOVIC Z,VAN DER HEIJDEN F.Efficient adaptive density estimation per image pixel for the task of background subtraction[J].Pattern Recognition Letters,2006,27(7):773-780. [10]LEE D S.Effective Gaussian mixture learning for video back-ground subtraction[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(5):827-832. [11]POWER P W,SCHOONEES J A.Understanding backgroundmixture models for foreground segmentation[C]//Proceedings of Image and Vision Computing New Zealand:Auckland University Press.2002:267-271. [12]LI W H,HE L X,NI Hong-yin.Algorithm on video-based dual background modeling[J].Application Research of Computers,2014,31(2):629-632. [13]JIN J,DANG J W,WANG Y P,et al.Region spatiogram in color names for background modeling [J].Journal of Image and Graphics,2019,24(5):714-723. [14]MARQUES O,KALVA H,FURHT B,et al.Neural NetworkApproach to Background Modeling for Video Object Segmentation[J].IEEE Transactions on Neural Networks,2007,18(6):1614-1627. [15]CAI X,HAN G,WANG J K.Background Subtraction Based on Pulse Coupled Neural Network[J].Applied Mechanics and Materials,2015,3682(1403):293-296. [16]BRAHAM M,VAN DROOGENBROECK M.Deep background subtraction with scene-specific convolutional neural networks [C]//Proceedings of 2016 International Conference on System,Singals and Image Processing.Bratislava,Slovakia:IEEE,2016:1-4. [17]OYAMA K,KRUMM J.Wallflower:Principles and practice of background maintenance[C]//Proceedings of ICCV.1999:255-265. [18]ZHANG X R,LEI G W,A Background Subtraction Algorithms of Object Detection Based on Hirstogram[J].Network and Computer Security,2010(2):45-47. |
[1] | 钱基德, 陈斌, 钱基业, 赵恒军, 陈刚. 基于机器视觉的液晶屏Mura缺陷检测方法 Machine Vision Based Inspection Method of Mura Defect for LCD 计算机科学, 2018, 45(6): 296-300. https://doi.org/10.11896/j.issn.1002-137X.2018.06.052 |
[2] | 高飞,丰敏强,汪敏倩,卢书芳,肖刚. 基于热点区域定义的人数统计方法研究 Research on People Counting Based on Hot Area 计算机科学, 2017, 44(Z6): 173-178. https://doi.org/10.11896/j.issn.1002-137X.2017.6A.040 |
[3] | 张文雅,徐华中,罗杰. 基于ViBe的复杂背景下的运动目标检测 Moving Objects Detection under Complex Background Based on ViBe 计算机科学, 2017, 44(9): 304-307. https://doi.org/10.11896/j.issn.1002-137X.2017.09.057 |
[4] | 李飞,张小洪,赵晨丘,鄢萌. 自适应的SILTP算法在运动车辆检测中的研究 Vehicle Detection Research Based on Adaptive SILTP Algorithm 计算机科学, 2016, 43(6): 294-297. https://doi.org/10.11896/j.issn.1002-137X.2016.06.058 |
[5] | 蒋泳森,肖泉,王守觉. 基于矢量方向特征的非参数动态背景建模 Non-parametric Dynamic Background Modeling Based on Direction Feature of Vector 计算机科学, 2016, 43(3): 291-295. https://doi.org/10.11896/j.issn.1002-137X.2016.03.054 |
[6] | 田合雷,丁胜,于长伟,周立. 基于目标检测及跟踪的视频摘要技术研究 Research of Video Abstraction Based on Object Detection and Tracking 计算机科学, 2016, 43(11): 297-299. https://doi.org/10.11896/j.issn.1002-137X.2016.11.057 |
[7] | 安国成,张凤军. 利用检测特征空间的目标实时跟踪 Target Tracking Based on Feature Space of Detection 计算机科学, 2013, 40(Z11): 309-313. |
[8] | 金鑫,梁雪春,袁晓龙. 复杂情况下的多目标跟踪统计技术 Multi-target Tracking Statistical Techniques in Complex Case 计算机科学, 2013, 40(6): 268-271. |
[9] | 郑河荣,褚一平,潘翔. 参数自适应的条件随机场视频分割方法 Adaptive Parameters Conditional Random Field Video Segmentation Algorithm 计算机科学, 2010, 37(5): 254-256. |
[10] | 王路 王磊 卓晴 王文渊. 基于二维主成分分析的运动目标检测 计算机科学, 2008, 35(8): 206-207. |
|