Please wait a minute...
浙江大学学报(工学版)
J4  2010, Vol. 44 Issue (1): 124-130    DOI: 10.3785/j.issn.1008-973X.2010.01.022
电子、通信与自动控制技术     
基于先验形状信息和水平集方法的车辆检测
赵璐,于慧敏
（浙江大学 信息与电子工程学系,浙江 杭州 310027）
Vehicle detection based on shape priors and level set
ZHAO Lu, YU Hui-min
(Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China)
 全文: PDF 
摘要：

针对交通视频检测应用,提出一种基于先验形状信息和主动轮廓模型的运动车辆检测方法.算法首先利用颜色信息和边缘信息检测并去除车辆阴影,提取车辆的初始轮廓；为了改善车辆轮廓的提取精度,在进一步的车辆分割中引入车辆形状的先验知识,用水平集符号距离图像的隐含表示建立车辆的先验形状模型,并以先验的车辆形状模型作为约束构造出主动轮廓能量函数；将第一步获得的车辆轮廓作为车辆分割演化曲线的初始轮廓,采用变分法求解能量函数的极小值,利用形状配准和水平集方法演化车辆的分割曲线,得到准确的运动车辆轮廓.将该方法应用于实际采集的交通视频,获得了很好的测试结果.
关键词： 车辆检测;  水平集;  先验形状;  形状配准;  阴影检测    
Abstract:

 A moving vehicle detection method based on the prior shape knowledge and active contour method was proposed for the application of traffic video detection. First, the shadow was eliminated for obtaining the initial contour of the vehicle using the color and edge information. Then, an implicit shape model with level set signed distant image was built to improve the accuracy of vehicle contour pick-up, and an active contour energy function with the restriction of the existing shape priors was constructed. The obtained vehicle contour was set to initial contour of the vehicle segmentation evolvement contour, and then the minimal value of the energy function could be found by variational method.The precise contour of the vehicle was obtained by applying the shape alignment and level set method to evolving the initial contour. Experimental results of real traffic sequences proved the good effectiveness of the proposed method．
Key words: vehicle detection    level set    shape priors    shape alignment    shadow detection
出版日期: 2010-02-04
:  TP 391.41  
基金资助:

 国家自然科学基金资助项目（60872069）；航天基金资助项目.
通讯作者: 于慧敏，男，教授，博导.     E-mail: yhm2005@zju.edu.cn
作者简介: 赵璐（1970-），女，浙江杭州人，硕士生，从事视频/图像处理与分析研究.
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
赵璐
于慧敏

引用本文:

赵璐, 于慧敏. 基于先验形状信息和水平集方法的车辆检测[J]. J4, 2010, 44(1): 124-130.

DIAO Lu, XU Hui-Min. Vehicle detection based on shape priors and level set. J4, 2010, 44(1): 124-130.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2010.01.022    或    http://www.zjujournals.com/xueshu/eng/CN/Y2010/V44/I1/124

［1］ STAUFFER C, GRIMSON W E L. Adaptive background mixture models for real-time tracking ［C］∥ Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE, 1999: 246-252．
［2］ CUCCHIARA R, GRANA C, PICCARDI M, et al. Detecting moving objects, ghosts, and shadows in video streams ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(10): 1337-1342．
［3］ ELGAMMAL A, DURAISWAMI R, HARWOOD D, et al. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance ［J］. Proceedings of the IEEE, 2002, 90(7): 1151-1163．
［4］ WANG Y, LOE K F, WU J K. A dynamic conditional random field model for foreground and shadow segmentation ［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(2): 279-289．
［5］ 陈睿,邓宇,向世明,等. 结合强度和边界信息的非参数前景/背景分割方法［J］. 计算机辅助设计与图形学学报, 2005, 17(6): 1278-1284．
CHEN Rui, DENG Yu, XIANG Shi-ming, et al. A non-parametric foreground/background segmentation method by fusion of intensity and edge feature ［J］. Journal of Computer-Aided Design and Computer Graphics, 2005, 17(6): 1278-1284．
［6］ CASELLES V, KIMMEL R, SAPIRO G. Geodesic active contours ［J］. International Journal of Computer Vision, 1997, 22(1): 61-79．
［7］ XU Yi, YU Hui-min. Contour-based motion segmentation using few priors ［C］∥ International Conference on Signal Processing. Beijing: IEEE, 2006: 1376-1379．
［8］ 于慧敏,徐艺,刘继忠,等. 基于水平集的多运动目标时空分割与跟踪［J］. 中国图象图形学报, 2007, 12(7): 1218-1223．
YU Hui-min, XU Yi, LIU Ji-zhong, et al. A spatiotemporal multiple moving objects segmentation and tracking with level set ［J］. Journal of Image and Graphics, 2007, 12(7): 1218-1223．
［9］ 于慧敏,尤育赛. 基于水平集的多运动目标检测和分割［J］. 浙江大学学报：工学版, 2007, 41(3): 412-417．
YU Hui-min, YOU Yu-sai. Detecting and segmenting multiple moving objects using level-set method ［J］. Journal of Zhejiang University: Engineering Science, 2007, 41(3): 412-417．
［10］ COOTES T F, TAYLOR C J, COOPER D H, et al. Active shape models-their training and application ［J］. Computer Vision and Image Understanding, 1995, 61(1): 38-59．
［11］ LEVENTON M E, GRIMSON W E L, FAUGERAS O. Statistical shape influence in geodesic active contours ［C］∥ Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos: IEEE, 2000: 316-323．
［12］ ROUSSON M, PARAGIOS N. Shape priors for level set representations ［C］∥ Proceedings of the European Conference on Computer Vision. Berlin: Springer- Verlag, 2002: 78-92．
［13］ ROUSSON M, PARAGIOS N. Prior knowledge, level set representations & visual grouping ［J］. International Journal of Computer Vision, 2008, 76(3): 231-243．
［14］ OSHER S, SETHIAN J. Fronts propagating with curvature dependent speed: algorithms based on the Hamilton-Jacobi formulation ［J］. Journal of Computational Physics, 1988, 79(1): 12-49．
［15］ OTSU N. A threshold selection method from gray-level histograms ［J］. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66．
［16］ WHITAKER R, BREEN D, MUSETH K. A level-set approach to 3D reconstruction from range data ［J］. International Journal of Computer Vision, 1998, 29(3): 203-231.
[1] 胡祝华, 赵瑶池, 程杰仁, 彭金莲. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报(工学版), 2014, 48(8): 1488-1495.
[2] 程健, 项志宇, 于海滨, 刘济林. 城市复杂环境下基于三维激光雷达实时车辆检测[J]. 浙江大学学报(工学版), 2014, 48(12): 2101-2106.
[3] 叶芳芳,许力,杜鉴豪,杨洁. 以头部为基准的人体轮廓模型[J]. J4, 2011, 45(7): 1175-1180.
[4] 江俊, 李培玉, 唐任仲. 基于水平集的转炉出钢图像钢渣检测方法[J]. J4, 2011, 45(2): 222-227.
[5] 计时鸣, 翁晓星, 谭大鹏. 基于水平集方法的软性磨粒两相流场特性分析[J]. J4, 2011, 45(12): 2222-2228.
[6] 谢强军, 侯迪波, 黄平捷, 张光新, 周泽魁. 基于半隐差分的单参数水平集快速分割[J]. J4, 2010, 44(8): 1496-1501.
[7] 孔丁科, 汪国昭. 用于图像分割的边界保持局部拟合模型[J]. J4, 2010, 44(12): 2236-2240.
[8] 刘佳 于慧敏. 基于水平集的运动目标检测和速度估算[J]. J4, 2009, 43(2): 244-249.
[9] 刁现芬 陈思平 吴佩娜 梁长虹 汪元美. 三维窄带水平集算法在内耳分割中的应用[J]. J4, 2007, 41(6): 919-924.
[10] 于慧敏 尤育赛. 基于水平集的多运动目标检测和分割[J]. J4, 2007, 41(3): 412-417.
[11] 刁现芬 陈思平 梁长虹 汪元美. 基于阈值区间的水平集算法在耳蜗分割中的应[J]. J4, 2006, 40(2): 262-266.
[12] 冯志林 尹建伟 刘洋 李旭东 董金祥. Allen-Cahn水平集的提花织物图像去噪研究[J]. J4, 2005, 39(2): 185-189.
[13] 潘翔. 基于彩色信息和边缘特征的运动阴影检测[J]. J4, 2004, 38(4): 389-391.