全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

OPTICS聚类与目标区域概率模型的多运动目标跟踪

DOI: 10.11834/jig.20151108

Keywords: 计算机视觉,图像处理,多运动目标跟踪,移动背景,聚类

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的针对多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题,本文提出了一种基于OPTICS聚类与目标区域概率模型的方法。方法首先引入了Harris-Sift特征点检测,完成相邻帧特征点匹配,提高了特征点跟踪精度和鲁棒性;再根据各运动目标与背景运动向量不同这一点,引入了改进后的OPTICS加注算法,在构建的光流图上聚类,从而准确的分离出背景,得到各运动目标的估计区域;对每个运动目标建立一个独立的目标区域概率模型(OPM),随着检测帧数的迭代更新,以得到运动目标的准确区域。结果多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题通过本文方法得到了很好地解决,Harris-Sift特征点提取、匹配时间仅为Sift特征的17%。在室外复杂环境下,本文方法的平均准确率比传统背景补偿方法高出14%,本文方法能从移动背景中准确分离出运动目标。结论实验结果表明,该算法能满足实时要求,能够准确分离出运动目标区域和背景区域,且对相机运动、旋转,场景亮度变化等影响因素具有较强的鲁棒性。

References

[1]  Wang L F. Detection algorithm of moving objects based on sift featuresmatching and dynamic updating background model[J].Computer Applications and Software.2010,27(2):267-270.[王亮芬.基于SIFT特征匹配和动态更新背景模型的运动目标检测算法[J].计算机应用与软件,2010,27(2):267-270.]
[2]  Li Y, Wang S, Ding X. Eye/eyes tracking based on a unified deformable template and particle filtering[J]. Pattern Recognition Letters, 2010, 31(11):1377-1387.
[3]  Hu W, Tan T, Wang L, Maybank S. A survey on visual surveillance of object motion and behaviors[J]. IEEE Trans. on Syst. Man Cyber.-C 2004, 34(3):334-352.
[4]  Yuan F, Xia G S, Sahbi H, et al. Mid-level features and spatio-temporal context for activity recognition[J]. Pattern Recognition, 2012, 45(12):4182-4191.
[5]  LI G, Yan F. Moving object detection based on SIFT features matching and K-means clustering[J]. Journal of Computer Applications, 2012,32(10):2824-2826.[李广,冯燕.基于SIFT特征匹配与K-均值聚类的运动目标检测[J]. 计算机应用,2012,32(10):2824-2826.]
[6]  Messing R, Pal C, Kautz H. Activity recognition using the velocity histories of tracked keypoints[C]//Proceedings of ICCV. Kyoto, Japan:IEEE Press, 2009:104-111.
[7]  Wright J, Yang A Y, Ganesh A, et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227.
[8]  Wang J, Chen Z, Wu Y. Action recognition with multiscale spatio-temporal contexts[C]//Proceedings of CVPR. Providence, USA:IEEE Press, 2011:3185-3192.
[9]  Mital A, Paragios N. Motion-based Background Subtraction Using Adaptive Kernel Density Estimation[J]. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. 2:302-309.
[10]  Sun S W, Huang F, Liao H M. Data-Driven foreground object detection from a non-stationary camera[C]//Proceedings of the 20th International conference on Pattern Recognition (ICPR), 2010,41(7):3053-3056 .
[11]  Jiman K, Guensu Y, Daijin K.Moving Object Detection Under free-moving camera[C]//Proceedings of the 17th IEEE International Conference Image Processing. Hong Kong, China:IEEE, 2010:4669-4672.
[12]  Wang X H, Cheng J Q, Han Y. Improved checkerboard corner detection algorithm based on the Harris[J].Electronic Measurement Technology.2013,36(10):51-54.[王晓辉,程健庆,韩瑜.基于Harris的棋盘格角点检测改进算法[J]. 电子测量技术. 2013,36(10):51-54.]
[13]  Xu J J, Zhang Y, Zhang H . Fast image registration algorithm based on improved Harris-SIFT descriptor[J]. Journal of Electronic Measurement and Instrumentation, 2015, 29(1):48-54.[许佳佳,张叶,张赫.基于改进Harris-SIFT算子的快速图像配准算法[J].电子测量与仪器学报,2015,29(1):48-54.]
[14]  Cheng D Z, Li Y J, Yu R X. Image matching method based on improved SIFT algorithm[J]. Computer Simulation, 2011,28(7):285-289.[程德志,李言俊,余瑞星. 基于改进SIFT算法的图像匹配方法[J]. 计算机仿真,2011,28(7):285-289.]
[15]  Liu X J, Yang J, Sun J W. Image registration approach based on SIFT[J]. Infrared and Laser Engineering, 2008,37(1):156-160.[刘小军,杨杰,孙坚伟,等. 基于SIFT的图像配准方法[J]. 红外与激光工程,2008,37(1):156-160.]
[16]  Zeng Y L, Xu H B. OPTICS-plus for text clustering[J]. Computer Applications and Software, 2010,27(2):267-270 .[曾依灵, 许洪波,白硕.改进的OPTICS算法及其在文本聚类中的应用[J].计算机应用与软件,2010,27(2):267-270.]

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133