文献类型：期刊文献

英文题名：Mangrove Extraction Algorithm Based on Orthogonal Matching Filter-Weighted Least Squares

作者：Li, Yongze[1];Ma, Jin[1];Fu, Dongyang[1];Yuan, Jiajun[1];Liu, Dazhao[1]

机构：[1]Guangdong Ocean Univ, Sch Elect & Informat Engn, Zhanjiang 524088, Peoples R China

年份：2024

卷号：24

期号：22

外文期刊名：SENSORS

收录：SCI-EXPANDED(收录号：WOS:001366068800001)、、EI(收录号：20244817452293)、Scopus(收录号：2-s2.0-85210241259)、WOS

基金：This research was funded by the National Key Research and Development Program of China under grant (2022YFC3103101), the Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory (GML2021GD0809), the National Natural Science Foundation of China (No. 42206187), and the Key Projects of the Guangdong Education Department (2023ZDZX4009).

语种：英文

外文关键词：mangroves; target extraction; GF-6 remote sensing images; edge detection

外文摘要：High-precision extraction of mangrove areas is a crucial prerequisite for estimating mangrove area as well as for regional planning and ecological protection. However, mangroves typically grow in coastal and near-shore areas with complex water colors, where traditional mangrove extraction algorithms face challenges such as unclear region segmentation and insufficient accuracy. To address this issue, in this paper we propose a new algorithm for mangrove identification and extraction based on Orthogonal Matching Filter-Weighted Least Squares (OMF-WLS) target spectral information. This method first selects GF-6 remote sensing images with less cloud cover, then enhances mangrove feature information through preprocessing and band extension, combining whitened orthogonal subspace projection with the whitened matching filter algorithm. Notably, this paper innovatively introduces Weighted Least Squares (WLS) filtering technology. WLS filtering precisely processes high-frequency noise and edge details in images using an adaptive weighting matrix, significantly improving the edge clarity and overall quality of mangrove images. This innovative approach overcomes the bottleneck of traditional methods in effectively extracting edge information against complex water color backgrounds. Finally, Otsu's method is used for adaptive threshold segmentation of GF-6 remote sensing images to achieve target extraction of mangrove areas. Our experimental results show that OMF-WLS improves extraction accuracy compared to traditional methods, with overall precision increasing from 0.95702 to 0.99366 and the Kappa coefficient rising from 0.88436 to 0.98233. In addition, our proposed method provides significant improvements in other metrics, demonstrating better overall performance. These findings can provide more reliable technical support for the monitoring and protection of mangrove resources.