基于字典学习光谱解混的绿藻亚像元面积估计
|
张贻然(1999-),女,硕士研究生,主要研究方向为高光谱图像解混。Email : zhangyiran@mail.nankai.edu.cn。 |
Copy editor: 张仙
收稿日期: 2023-10-25
修回日期: 2024-10-28
网络出版日期: 2026-06-03
基金资助
国家自然科学基金项目“基于多目标优化的高光谱遥感图像稀疏解混研究”(62001251)
“多层级域适应高光谱遥感图像分类”(62001252)
中央高校基本科研业务费专项资金(63243074)
Subpixel-level area estimation of green algae based on spectral unmixing in dictionary learning
Received date: 2023-10-25
Revised date: 2024-10-28
Online published: 2026-06-03
近年来,绿潮成为一种全球范围内的重大海洋生态灾害,准确检测和估计绿藻面积具有重要意义。为了在使用低分辨率的卫星影像监测海洋绿潮时能够准确估计绿藻群落覆盖面积,提出一种基于字典学习的高光谱图像绿藻面积估计方法。首先利用在线稳健字典学习求出与未知地物光谱最为接近的端元谱库,然后通过稀疏编码解得绿藻丰度图并计算绿藻覆盖面积。对2016年6月25日和2020年6月21日GOCI传感器获取的光谱图像进行实验,计算得到的当日绿藻覆盖面积与近似实测结果高度接近,误差最小仅有2.15%,相比于基于指数的硬阈值分割的传统算法具有明显优势。所提方法不依赖于纯像元假设,且既不需要提前估计端元数量,也不需要先验光谱信息,就能够有效降低混合像元的影响、提高面积估计精度,实现亚像素水平的绿藻面积高精度估计。
张贻然 , 潘斌 , 徐夏 , 朱俊峰 . 基于字典学习光谱解混的绿藻亚像元面积估计[J]. 自然资源遥感, 2025 , 37(2) : 88 -95 . DOI: 10.6046/zrzyyg.2023349
Green tides have emerged as a significant marine ecological disaster worldwide, rendering the accurate detection and area estimation of green algae crucial. To accurately estimate the coverage area of green algae communities in the monitoring of green tides based on low-resolution satellite images, this study proposed a dictionary learning-based method for estimating the area of green algae using hyperspectral images. The proposed method involves deriving the endmember spectrum database that is closest to the unknown surface feature spectra via online robust dictionary learning, obtaining the abundance map of green algae through sparse coding, and calculating the coverage area of green algae. It was verified through the experiment using the spectral images acquired by the geostationary ocean color imager (GOCI) on June 25, 2016, and June 21, 2020. The experimental results reveal that the calculated coverage areas of green algae on the two days were highly close to the approximate measured results, with a minimum error of only 2.15 %, suggesting that the proposed method outperforms traditional index-based hard thresholding algorithms. Independent of the pure pixel hypothesis, the proposed method can effectively address the mixed pixel problem and enhance area estimation accuracy in the absence of a pre-estimated number of endmembers or prior spectral information, thereby achieving high-precision subpixel-level area estimation of green algae.
表2 不同方法的定量对比结果Tab.2 Quantative results by different methods ( km2) |
| 序号 | 真值 | N-FINDR | NDVI | VB-FAH | IGAG | gTV | SeCoDe | DLSU | ||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.1 | 0 | 0.1 | 0 | 5 | 0 | 0.1 | |||||
| 1 | 1 251.2 | 3 039.2 | 8 700.8 | 4 373.5 | 5 219.5 | 234.3 | 8 700.8 | 6 258.3 | 917.1 | 1 287.1 | 1 278.1 | 375.4 |
| 2 | 2 739.0 | 8 181.5 | 4 147.3 | 5 090.8 | 221.8 | 8 181.5 | 6 414.8 | 398.1 | 1 170.4 | 1 047.5 | 428.3 | |
| 3 | 157.6 | 525.0 | 2 131.8 | 874.3 | 1 481.8 | 16.5 | 2 131.8 | 1 876.0 | 308.0 | 678.9 | 2 077.5 | 123.4 |
| 4 | 1 754.3 | 1 917.3 | 879.8 | 1 323.5 | 26.5 | 1 917.3 | 1 650.8 | 194.0 | 684.7 | 1 256.5 | 162.5 | |
| [1] |
王广策, 王辉, 高山, 等. 绿潮生物学机制研究[J]. 海洋与湖沼, 2020, 51(4):789-808.
|
| [2] |
王宗灵, 傅明珠, 肖洁, 等. 黄海浒苔绿潮研究进展[J]. 海洋学报, 2018, 40(2):1-13.
|
| [3] |
|
| [4] |
|
| [5] |
|
| [6] |
刘锦超, 刘建强, 丁静, 等. HY-1C卫星CZI载荷的黄海绿潮提取研究[J]. 海洋学报, 2022, 44(5):1-11.
|
| [7] |
|
| [8] |
赵尊强, 陈鑫, 刘慧芳, 等. 基于改进FCN网络的GOCI绿潮分类研究[J]. 软件导刊, 2020, 19(3):69-73.
|
| [9] |
潘斌, 张宁, 史振威, 等. 基于高光谱图像解混的海洋绿藻检测算法[J]. 红外与激光工程, 2018, 47(8):0823001.
|
| [10] |
|
| [11] |
|
| [12] |
|
| [13] |
|
| [14] |
|
| [15] |
|
| [16] |
|
| [17] |
宋晓瑞, 赵忠文, 于尧. 一种在线字典学习的高光谱图像盲解混方法[J]. 装备学院学报, 2017, 28(3):21-26.
|
| [18] |
|
| [19] |
|
| [20] |
|
| [21] |
|
| [22] |
|
| [23] |
童旭东. 中国高分辨率对地观测系统重大专项建设进展[J]. 遥感学报, 2016, 20(5):775-780.
|
| [24] |
胡昌苗, 白洋, 唐娉. GF-4序列图像的云自动检测[J]. 遥感学报, 2018, 22(1):132-142.
|
| [25] |
|
| [26] |
|
/
| 〈 |
|
〉 |