基本信息:
- 专利标题： 一种基于稀疏表示的冠层植物高光谱图像分类方法
- 专利标题（英）：Canopy plant hyperspectral image classification method based on sparse representation
- 申请号：CN201910916938.0 申请日：2019-09-26
- 公开(公告)号：CN110751144A 公开(公告)日：2020-02-04
- 发明人： 徐平 , 马凤娟 , 陈秉强 , 薛凌云 , 赵晓东 , 孔亚广 , 陈张平 , 邹洪波 , 张帆
- 申请人： 杭州电子科技大学
- 申请人地址： 浙江省杭州市下沙高教园区2号大街
- 专利权人： 杭州电子科技大学
- 当前专利权人： 杭州电子科技大学
- 当前专利权人地址： 浙江省杭州市下沙高教园区2号大街
- 代理机构： 杭州君度专利代理事务所
- 代理人： 朱亚冠
- 主分类号： G06K9/20
- IPC分类号： G06K9/20 ; G06K9/62
The invention discloses a canopy plant hyperspectral image classification method based on sparse representation. According to the method, a new weighted sparse representation model is introduced, andany spectrum in hyperspectral data is represented as a linear combination of a plurality of atoms in a pre-trained dictionary. The sparse representation of any spectrum is represented as a sparse vector whose non-zero value corresponds to the weight of the selected training sample. A sparse vector is recovered by solving a sparse constraint optimization problem, and a class label of a test samplecan be directly determined. Concepts of correlation coefficients and threshold values are introduced, the model gives different weight values to adjacent spectrums according to the correlation betweenthe adjacent spectrums and the current spectrum, so that the constraint degree of different spectrums in a neighborhood to the current spectrum is changed, and the change remarkably improves the classification of the spectrums at the junctions of different objects.
公开/授权文献:
- CN110751144B 一种基于稀疏表示的冠层植物高光谱图像分类方法 公开/授权日：2022-07-08
IPC结构图谱:
| G | 物理 |
| --G06 | 计算；推算；计数 |
| ----G06K | 数据识别；数据表示；记录载体；记录载体的处理 |
| ------G06K9/00 | 用于阅读或识别印刷或书写字符或者用于识别图形，例如，指纹的方法或装置 |
| --------G06K9/20 | .图像捕获 |