|
|
论文:2017,Vol:35,Issue(1):133-137 |
|
|
引用本文： |
|
|
张君昌, 周艳玲, 万锦锦. 融合超像素与动态图匹配的视频跟踪[J]. 西北工业大学学报 |
|
|
Zhang Junchang, Zhou Yanling, Wan Jinjin. Video Tracking Method Jointing Superpixel and Dynamic Graph Matching[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 融合超像素与动态图匹配的视频跟踪 |
|
| 张君昌1,2, 周艳玲1, 万锦锦2 |
|
1. 西北工业大学 电子信息学院, 陕西 西安 710129;
2. 光电控制技术重点实验室, 河南 洛阳 471000 |
| 摘要: |
| 针对视频跟踪过程中目标的形变、遮挡、旋转和背景干扰问题，提出一种融合超像素与动态图匹配的视频跟踪方法。首先，采用融合局部熵特征的简单线性迭代聚类（simple linear iterative clustering，SLIC）方法经聚类分析生成超像素集合，使生成的超像素边缘贴合度更好。其次，采用图像分割（graph cuts）方法生成候选目标超像素集合，并融合在线支持向量机学习算法（online SVM learning algorithm，LASVM）分类预测结果，使前景与背景分离的准确度更高。然后，充分利用目标的几何结构信息构建基于图模型的相似度矩阵，解决目标的形变和遮挡问题。理论分析与仿真结果表明：相比现有其他视频跟踪方法，新方法对跟踪过程中的遮挡和形变情况具有较强的鲁棒性，对一定程度的背景干扰和旋转问题跟踪效果良好。 |
| 关键词:
目标追踪
信息融合
简单线性迭代聚类
超像素
图像分割
|
|
| Video Tracking Method Jointing Superpixel and Dynamic Graph Matching |
|
| Zhang Junchang1,2, Zhou Yanling1, Wan Jinjin2 |
|
1. School of Electronics Information, Northwestern Polytechnical University, Xi'an 710072, China;
2. Science and Technology on Electro-Optic Control Laboratory, Luoyang 471000, China |
| Abstract: |
| Focusing on the problem of target deformation, occlusion, rotation and background interference, a video tracking method jointing superpixels and dynamic graph matching was proposed in this paper. Firstly, superpixels were generated by the simple linear iterative clustering analysis method integrating the local entropy feature, so that we can get superpixels that the edge fit better. Secondly, the candidate target superpixels was generated by graph cuts method, in which the LASVM classifier was combined with the graph guts method in order to make the separation of foreground and background more accurately. Thirdly, when the graph modle was constructed, we make full use of the geometric information of the target to solve the problem of the occlusion and deformation effectively. Meanwhile, the constraints were introduced to reduce the dimension of the affinity matrix, so that the computational complexity was reduced. Theoretical analysis and simulation results show that our method has strong robustness and better tracking accuracy when deals with the occlusion and deformation, and the proposed method is good in dealing with the target rotation and a certain degree of background interference, compared with currently other video tracking methods. |
| Key words:
target tracking
information fusion
simple linear iterative clustering
superpixels
graph cuts
|
|
| 收稿日期: 2016-09-19
修回日期:
|
| DOI: |
| 基金项目: 光电控制技术重点实验室和航空科学基金（2016515303）资助 |
| 通讯作者:
Email： |
| 作者简介: 张君昌(1969-),西北工业大学副教授、光电控制技术重点实验室客座研究人员,主要从事信号处理与无线通信研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Xu Yanming. An Improved Mean-Shift Moving Object Detection and Tracking Algorithm Based on Segmentation and Fusion Mechanism[C]//IEEE Conference on Systems Process and Control, 2013:224-229
[2] Li Ning, Zhang Dan, Gu Xiaorong, et al. An Improved Mean Shift Algorithm for Moving Object tracking[C]//IEEE Conference on Electrical and Computer Engineering, 2015:1425-1429
[3] Yuan Jun, Tang Shuming, Wang Fei, Zhang Hong. A Robust Road Segmentation Method Based on Graph Cut with Learnable Neighboring Link Weights[C]//IEEE Conference on Intelligent Transportation Systems, 2014:1644-1649
[4] Antoine Bordes, Seyda Ertekin, Jason Weston, et al. Fast Kernel Classifiers with Online and Active Learning[J]. Journal of Machine Learning Research, 2005, 6(3):1579-1619
[5] Egozi A, Keller Y, Guterman H. A Probabilistic Approach to Spectral Graph Matching[J]. IEEE Trans on Pattern Analysis & Machine Intelligence, 2013, 35(1):18-27
[6] Cai Z, Wen L, Lei Z, et al. Robust Deformable and Occluded Object Tracking with Dynamic Graph[J]. IEEE Trans on Image Processing, 2014, 23(12):5497-509 |
|
|
|
相关文献: |
|
|
1．苏坡, 杨建华, 薛忠.基于超像素的多模态MRI脑胶质瘤分割[J]. 西北工业大学学报, 2014,32(3): 417-422 |
|
|
|
|
|
|
