| 基于NMI特征的目标识别与跟踪 |
| |
| 引用本文： | 门蓬涛,张秀彬,张峰,孙志旻,吴炯.基于NMI特征的目标识别与跟踪[J].微计算机信息,2004,20(3):24-26. |
| |
| 作者姓名： | 门蓬涛 张秀彬 张峰 孙志旻 吴炯 |
| |
| 作者单位： | 200030,上海上海交通大学电气工程系 |
| |
| 摘 要： | 本文提出一种全新的图像分割方法——连通线多级切割方法，并在此基础上建立图像NMI特征的目标识别与跟踪算法。文章给出了运用连通线多级切割方法实现阈值求取、图像分割、目标识别与跟踪的技术技巧。通过实验验证了NMI特征的缩放不变性、旋转不变性和平移不变性以及不同物体的NMI特征差异，表明本文算法具有良好的实时性和精确的目标识别与跟踪效果。
|
| 关 键 词： | 图像分割 NMI特征 目标识别 连通线多级切割方法 图像处理 |
| 文章编号： | 1008-0570(2004)03-0024-03 |
| 修稿时间： | 2003年9月23日 |
Target Recognition and Tracking Based on NMI Feature |
| |
| Men,Pengtao Zhang,Xiubin Zhang,Feng Sun,Zhimin Wu,Jiong.Target Recognition and Tracking Based on NMI Feature[J].Control & Automation,2004,20(3):24-26. |
| |
| Authors: | Men Pengtao Zhang Xiubin Zhang Feng Sun Zhimin Wu Jiong |
| |
| Abstract: | In this paper, a new method of Image Segmentation, namely Consecutive Line Multilevel Segmentation, and the algorithm of Target Recognition and Tracking based on Normalized Moment of Inertia (NMI) feature are introduced. The definition of Centre of Mass and NMI feature is proposed and the principle and methods of Threshold calculation, Image segmentation, Target recognition and tracking are presented. Then, the scaling invariability, rotation invariability, translation invariability of NMI feature and the NMI feature difference of various objects are validated by experiment. The experimental results show that the algorithm discussed in this paper is very practical with good real time and accurate effect of Target recognition and tracking. |
| |
| Keywords: | Invariant feature/ Threshold/ OTSU algorithm/ Image segmentation/ NMI feature/ Target recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
