多模跟踪技术在轮式侦察车图像处理器的应用

郝志成; 高文

多模跟踪技术在轮式侦察车图像处理器的应用

郝志成¹,
高文^1,2

1.
中国科学院长春光学精密机械与物理研究所,吉林长春 130033;
2.
中国科学院研究生院,北京 100039

基金项目:

中国科学院二期创新工程基金资助项目(No.C50Top2)

详细信息

作者简介:
郝志成(1978-),男,辽宁大石桥人,副研究员,主要从事数字图像处理及模式识别等方面的研究。 E-mail:hzc972513@tom.com 高文(1985-),女,黑龙江人,博士研究生,主要从事视频图像跟踪与目标识别方面的研究。 E-mail:cwenzi@126.com

郝志成(1978-),男,辽宁大石桥人,副研究员,主要从事数字图像处理及模式识别等方面的研究。 E-mail:hzc972513@tom.com 高文(1985-),女,黑龙江人,博士研究生,主要从事视频图像跟踪与目标识别方面的研究。 E-mail:cwenzi@126.com

中图分类号: TP391.41; TJ81
计量
- 文章访问数: 3721
- HTML全文浏览量: 412
- PDF下载量: 1165
- 被引次数: 0
出版历程
- 收稿日期: 2011-07-21
- 修回日期: 2011-08-23
- 刊出日期: 2011-10-25

Application of multi-pattarn tracking technique in image processor of wheel type scout car

HAO Zhi-cheng¹,
GAO Wen^1,2

1.
Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun 130033, China;
2.
Graduate University of Chinese Academy of Sciences, Beijing 100039, China

摘要

摘要: 为解决目标旋转形变、遮挡、光照变化等目标跟踪的难题,对粒子滤波和尺度不变特征变换(SIFT)算法进行了改进,结合两种算法提出了决策主导模式的多模跟踪技术。该技术采用粒子滤波预测目标位置进行粗定位,SIFT特征匹配进行精定位的方法,在解决上述难题上有很好的鲁棒性。将该技术应用于轮式侦察车图像处理器,并进行了各种实验验证,结果证明了提出算法的有效性。
- 多模跟踪技术 /
- 目标跟踪 /
- 粒子滤波 /
- 尺度不变特征变换 /
- 轮式侦察车
Abstract: As variety illumination, deformation and rotation of targets and many other complicated conditions are always hard to be cracked in target tracking, this paper researches and improves particle filtering and Scale Invariant Feature Transform(SIFT) algorithms. By combined with the two algorithms, it proposes a multi-pattern tracking technique, which adopts a particle filter to predict target position and then chooses SIFT character matching to get the accurate position of an object. This target tracking is quite robust and has applied to an image processor in a artillery wheel type scout car. Experiments has been performed in many aspects and results prove it is accetable and effective.
- multi-model tracking technique /
- target tracking /
- particle filtering /
- Scale Invariant Feature Transform(SIFT) /
- wheel type scout car

HTML全文

参考文献(1)

[1] 王选贺,刘济林. 基于核密度估计的遮挡人体跟踪[J]. 浙江大学学报(工学版) ,2011,45(3):412-418. WANG X H,LIU J L. Tracking human under occlusion based on kernel density estimation[J]. J. Zhejiang University(Engineering Science),2011,45(3):412-418.(in Chinese) [2] 赵丰,汤磊,陈国友,等. RBPF粒子滤波在目标跟踪中的应用研究[J]. 计算机工程 ,2011,37(3):149-151. ZHAO F,TANG L,CHEN G Y,et al.. Research on application of RBPF in target tracking[J]. Computer Eng.,2011,37(3):149-151.(in Chinese) [3] 陈爱华,孟勃,朱明,等. 多模式融合的目标跟踪算法[J]. 光学精密工程 ,2009,17(1):185-190. CHEN A H,MENG B,ZHU M,et al.. Multi-pattern fusion algorithm for target tracking[J]. Opt. Precision Eng.,2009,14(9):1745-1749.(in Chinese) [4] 薛陈,朱明,陈爱华. 鲁棒的基于改进Mean-shift的目标跟踪[J]. 光学精密工程 ,2010,18(1):234-239. XUE CH,ZHU M,CHEN A H. Robust object tracking based on improved Mean-shift algorithm[J]. Opt. Precision Eng.,2010,18(1):234-239.(in Chinese) [5] 李焱,陈涛,曹立华,等. 舰载光电设备跟踪掠海目标的控制[J]. 光学精密工程 ,2010,18(4):935-942. LI Y,CHEN T,CAO L H,et al.. Control of ship-based optoelectronic equipment for tracking near-sea targets[J]. Opt. Precision Eng.,2010,18(4):935-942.(in Chinese) [6] 周斌,王军政,沈伟. 基于组合带宽均值迁移的快速目标跟踪[J]. 光学精密工程 ,2010,18(10):2297-2305. ZHOU B, WANG J ZH,SHEN W. Fast object tracking with multi-bandwidth Mean Shift[J]. Opt. Precision Eng.,2010,18(10):2297-2305.(in Chinese) [7] 苑玮琦,董茜,桑海峰. 基于方向梯度极值的手形轮廓跟踪算法[J]. 光学精密工程 ,2010,18(7):1675-1683. YUAN W Q,DONG Q,SANG H F. Hand shape contour tracking method based on directional gradient extremum[J]. Opt. Precision Eng.,2010,18(7):1675-1683.(in Chinese) [8] 李忠海,王莉,崔建国. 基于Camshift和Particle Filter的小目标跟踪算法[J]. 计算机工程与应用 ,2011,47(9):192-195,199. LI ZH H,WANG L,CUI J G. Weak aerial target tracking algorithm based on camshift and particle filter[J]. Computer Eng. Appl.,2011,47(9):192-195.(in Chinese) [9] 蔺海峰,马宇峰,殷璇,等. 基于SIFT特征的抗遮挡目标跟踪算法[J]. 计算机工程 ,2011,37(4):198-200. LIN H F,MA Y F,YIN X,et al.. Anti-occlusion object tracking algorithm based on SIFT feature[J]. Computer Eng.,2011,37(4):198-200.(in Chinese) [10] 朱向军,毛剑飞,鲍卫兵. 基于达芬奇技术的智能视频监控终端的开发[J]. 电信科学 ,2011(2):100-104. ZHU X J,MAO J F,BAO W B. Development of intelligent visual surveillance device based on davinci[J]. Telecom Sci.,2011(2):100-104.(in Chinese) [11] LOWE D G. Object recognition from local scale-invariant features. The 7th International Conference on Computer Vision,Kerkyra,Greece,20-27 Sept.1999:1150-1157. [12] LOWE D G. Distinctive iImage features from scale-invariant keypoints[J]. International J. Computer Vision,2004,60(2):91-110. [13] COMANIEIU D,MEER P. Distribution free decomposition of multivariate data[J]. Pattem Anal. Appl.,1999,2(1):22-30. [14] MURRAY D W,BUXTON B E. Scene segmentation from visual motion using global optimization[J]. IEEE T. Pattern Anal.,1987,9:220-228. [15] MARKANDEY V,REID A,WANG S. Motion estimation for moving target detection[J]. IEEE T. Aero. Elec. Sys.,1996,32(3):866-874. [16] STAUFFER C,GRIMSON E. Learning patterns of activity using real time tracking[J]. IEEE T. Pattern Anal.,2000,22(8):747-757. [17] KALMAN R E. A new approach to linear filtering and prediction problems[J]. Transaction ASME-J. Basic Eng.,1960,82(Series D):35-45. [18] GORDON N J,SALMOND D J,SMITH A F M. Novel approach to nonlinear and non-Gaussian bayesian state estimation[J]. IEEE Proceedings-F,1993,140(2):107-113. [19] ISARD M, BLAKE A. Condensation-conditional density propagation for visual tracking[J]. International J. Computer Vision,1998,29(1):5-28. [20] 孟勃,朱明. 采用EM算法对粒子滤波跟踪算法进行改进[J]. 中国图象图形学报 ,2009,14(9):1745-1749. MENG B,ZHU M. The application of EM algorithm to improve particle filter[J]. J. Image and Graphics,2009,14(9):1745-1749.(in Chinese) [21] MIKOLAJCZYK K,SCHMID C. A performance evaluation of local descriptors[J]. IEEE T. Pattern Anal.,2005,27(10):1615-1630. [22] BAY H,TUYTELAARS T,GOOL L V. SURF:Speeded up robust features[J]. Computer Vision and Image Understanding,2006,110(3):346-359.

施引文献

附加信息(0)

访问统计