| 基于聚类技术的三维舰船模型特征库研究 |
| |
| 引用本文： | 于吉红,白晓明,郭宁.基于聚类技术的三维舰船模型特征库研究[J].应用光学,2012,33(2):260-264. |
| |
| 作者姓名： | 于吉红 白晓明 郭宁 |
| |
| 作者单位： | 1.海军航空工程学院 指挥系,山东 烟台 264001;2.海军航空工程学院 兵器科学与技术系,山东 烟台 264001;3. 海军航空工程学院 控制工程系,山东 烟台 264001 |
| |
| 摘 要： | 存贮目标所有的视点图像，建立完备的特征库，或者提取能够抵抗视点变化的不变特征，是三维目标识别的常用方法。这两种方案都存在不足：要么特征库规模庞大，识别过程计算量大，识别效率低；要么难以找到鲁棒的识别特征。结合两种方案研究了基于聚类技术建立三维舰船模型特征库的方法。利用仿射传播聚类方法无需事先指定聚类中心的优点，将其应用于两型舰船模型的视点空间聚类。通过提取视点图像的Hu矩特征，进行了仿真实验，给出了聚类结果的有效性分析。
|
| 关 键 词： | 目标识别 视点空间 无监督聚类 仿射传播聚类 |
| 收稿时间： | 2011/8/11 |
Features of 3D naval vessel models using clustering technology |
| |
| YU Ji-Hong
,
BAI Xiao-Ming
,
GUO Ning.Features of 3D naval vessel models using clustering technology[J].Journal of Applied Optics,2012,33(2):260-264. |
| |
| Authors: | YU Ji-Hong BAI Xiao-Ming GUO Ning |
| |
| Affiliation: | 1.Department of Command, Naval Aeronautical and Astronautical University, Yantai 264001, China;
2.Department of Ordnance Science and Technology, NAAU, Yantai 264001, China;
3.Department of Control Engineering, NAAU, Yantai 264001, China |
| |
| Abstract: | Creating a sufficient feature base for all of the viewpoints or extracting an invariable feature of different viewpoints are the common methods for 3D target recognition. They share the shortcomings of big size feature base, enormous computation and low recognition rate. It is almost impossible to find the recognition feature of robustness. The method for establishing the 3D naval vessel models feature base with clustering technology was studied. The affinity propagation (AP)clustering algorithm requires no initializing cluster centers and it is suitable to cluster view points space. Experiment of AP was done using computer based on the Hu moments, and the clustering results validied the method by Silhouette index. |
| |
| Keywords: | target recognition view points space unsupervised clustering affinity propagation clustering |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《应用光学》浏览原始摘要信息 |
|
点击此处可从《应用光学》下载全文 |
|
