|
|||||
|
|
| 基于支持向量机的目标跟踪研究 | |
| 引用本文： | 张谢华,路梅,田敏. 基于支持向量机的目标跟踪研究[J]. 计算机工程与设计, 2011, 32(12): 4210-4212,4245 |
| 作者姓名： | 张谢华 路梅 田敏 |
| 作者单位： | 1. 徐州师范大学现代教育技术中心,江苏徐州221116;中国矿业大学信电学院,江苏徐州221008 2. 徐州师范大学计算机科学与技术学院,江苏徐州,221116 3. 同济大学电子与信息工程学院宽带无线通信与多媒体实验室,上海,201804 |
| 基金项目： | 徐州师范大学自然科学基金项目 |
| 摘 要： | 把目标跟踪看作为目标和背景在时序上的分类问题来进行处理,选择支持向量机作为分类器,完成相应的目标跟踪任务。在跟踪过程中,采用扰动前景区域和按步长抽取背景的方法得到数量相当的正负样本;建立图像的积分直方图索引,通过索引之间的加减快速获取区域边缘和纹理特征向量;将新样本集合与前期获取的支持向量混合起来一并训练,实现分类器的在线更新。用经典图像序列进行实验,实验结果表明,该算法具有良好的跟踪效果。 |
| 关 键 词： | 支持向量机 目标跟踪 积分直方图 特征向量 在线更新 |
Study of object tracking based on support vector machine |
|
| ZHANG Xie-hua,LU Mei,TIAN Min. Study of object tracking based on support vector machine[J]. Computer Engineering and Design, 2011, 32(12): 4210-4212,4245 | |
| Authors: | ZHANG Xie-hua LU Mei TIAN Min |
| Affiliation: | ZHANG Xie-hua1,2,LU Mei3,TIAN Min4(1.Morden Education Technology Center,Xuzhou Normal University,Xuzhou 221116,China,2.College of Information Electronic and Engineering Institute,China University of Mining and Technology,Xuzhou 221008,3.College of Computer Science and Technology,4.Broadband Wireless Communication and Multimedia Laboratory,College of Electronics and Information,Tongji University,Shanghai 201804,China) |
| Abstract: | Considering object tracking as a classify problem on time series signal,support vector machine(SVM) is selected here as the classifier to complete the task.During the process of object tracking,a relative large number of positive and negative samples are gained by the way of disturbing the foreground region and sampling the background region by steps.Building the index of integral histograms,the edge features and texture features are rapidly extracted by fast calculating on the index.On-line updating the SV... |
| Keywords: | SVM object tracking integral histogram eigenvectors on-line updating |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |