Optics and Precision Engineering, Volume. 31, Issue 21, 3156(2023)
Target detection using spectral unmixing
Figures & Tables(13)
Fig. 1. Flowchart of optimized weighted CEM target detection algorithm using spectral unmixing
Table 1. AUC of different algorithms in experiment 1
View tableView in ArticleTable 1. AUC of different algorithms in experiment 1
算 法 模拟-端元1 模拟-端元2 模拟-端元3 模拟-端元4 圣地亚哥 迷彩车辆 平均值 CEM 0.866 4 0.792 0 0.809 6 0.992 0 0.871 8 0.951 1 0.880 5 基于SAM的加权CEM 0.916 3 0.783 9 0.835 6 0.996 2 0.990 5 0.998 4 0.920 2 基于丰度系数的加权CEM 0.921 2 0.830 2 0.860 9 0.996 3 0.987 0 0.982 0 0.929 6 基于光谱解混合的加权CEM 0.921 2 0.825 1 0.859 2 0.996 2 0.993 7 0.998 0 0.932 2
Table 2. AUC of different algorithms in experiment2
View tableView in ArticleTable 2. AUC of different algorithms in experiment2
高光谱数据 SAM（si'） 丰度系数（qi'） SAM+丰度系数（（qi'+
si'）/2）
模拟-端元1 0.875 5 0.963 9 0.959 7 模拟-端元2 0.533 8 0.901 8 0.859 9 模拟-端元3 0.667 3 0.794 7 0.824 8 模拟-端元4 0.995 7 0.996 6 0.996 2 圣地亚哥 0.979 3 0.992 3 0.997 2 迷彩车辆 0.997 8 0.971 0 0.998 1 平 均 0.841 6 0.936 7 0.939 3
Table 3. AUC of this algorithm
View tableView in ArticleTable 3. AUC of this algorithm
高光谱数据 加权CEM SAM+丰度系数（（qi’+ si’）/2） 本文算法 模拟-端元1 0.921 2 0.959 7 0.966 9 模拟-端元2 0.825 1 0.859 9 0.877 4 模拟-端元3 0.859 2 0.824 8 0.873 7 模拟-端元4 0.996 2 0.996 2 0.996 3 圣地亚哥 0.993 7 0.997 2 0.997 5 迷彩车辆 0.998 0 0.998 1 0.998 4 平均 0.932 2 0.939 3 0.951 7
Tools
Get Citation
Copy Citation Text
Lei ZHANG, Kai QIAO, Yinhua WU, Siyuan LI. Target detection using spectral unmixing[J]. Optics and Precision Engineering, 2023, 31(21): 3156
Paper Information
Category:
Received: Jun. 21, 2023
Accepted: --
Published Online: Jan. 5, 2024
The Author Email: WU Yinhua (yinhuawoo@163.com)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20