Mangrove forest mapping from object-oriented multi-feature ensemble classification using Sentinel-2 images

被引:1
|
作者
Zhang, Han [1 ]
Xia, Qing [1 ]
Dai, Shuo [1 ]
Zheng, Qiong [1 ]
Zhang, Yunfei [1 ]
Deng, Xingsheng [1 ]
机构
[1] Changsha Univ Sci & Technol, Sch Traff & Transportat Engn, Changsha, Peoples R China
基金
中国国家自然科学基金;
关键词
Sentinel-2; images; an enhanced mangrove spectral index; multi-features; object-oriented segmentation; spectral reflectance signature; INDEX; CONSERVATION; CHINA;
D O I
10.3389/fmars.2023.1243116
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Accurate mapping of mangrove forests is crucial for understanding their ecosystem function and developing effective management policies. However, the absence of an operational multi-feature fusion approach and an ensemble classification system restricts the achievement of this goal. This study aims to develop an object-oriented multi-feature ensemble classification scheme (OMEC). First, an enhanced mangrove spectral index (EMSI) is established by analyzing the spectral reflectance differences between mangrove forests and other land cover types. Sentinel-2 images are segmented into objects using the multi-resolution segmentation method. Then, spectral, textural, and geometric features are extracted, and these features (including EMSI) are inputted into the nearest neighbor classifier to implement mangrove classification. The experiment was conducted in three typical mangrove areas in China using Sentinle-2 images. The results demonstrate that EMSI exhibits good spectral separability for mangroves and performs well in the ensemble classification scheme. The overall accuracy of mangrove classification exceeds 90%, with a Kappa coefficient greater than 0.88. The object-oriented multi-feature ensemble classification scheme significantly improves accuracy and exhibits excellent performance. The method enhances the accuracy of mangrove classification, enriches the approach to mangrove remote sensing interpretation, and offers data support and scientific references for the restoration, management, and protection of coastal wetlands.
引用
收藏
页数:15
相关论文
共 50 条
  • [1] A Comparison of Gaofen-2 and Sentinel-2 Imagery for Mapping Mangrove Forests Using Object-Oriented Analysis and Random Forest
    Zhang, Rong
    Jia, Mingming
    Wang, Zongming
    Zhou, Yaming
    Wen, Xin
    Tan, Yue
    Cheng, Lina
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2021, 14 : 4185 - 4193
  • [2] Object-Oriented Change Detection for Multi-source Images Using Multi-Feature Fusion
    Zhang, Baoming
    Lu, Jun
    Guo, Haitao
    Xu, Junfeng
    Zhao, Chuan
    [J]. 2016 THIRD INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND PATTERN RECOGNITION (AIPR), 2016,
  • [3] Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images
    Zhang, Lei
    Gong, Zhaoning
    Wang, Qiwei
    Jin, Diandian
    Wang, Xing
    [J]. Yaogan Xuebao/Journal of Remote Sensing, 2019, 23 (02): : 313 - 326
  • [4] A Multi-Feature Augmentation CNN Model for Crop Classification Based on Sentinel-2 Remote Sensing Images
    Zheng, Zhiqiang
    Lv, Wei
    Weng, Zhi
    Wang, Lixin
    [J]. BASIC & CLINICAL PHARMACOLOGY & TOXICOLOGY, 2021, 128 : 59 - 59
  • [5] A NEW MULTI-FEATURE APPROACH TO OBJECT-ORIENTED CHANGE DETECTION BASED ON FUZZY CLASSIFICATION
    Du, Xuejiao
    Zhang, Chao
    Yang, Jianyu
    Su, Wei
    [J]. INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2012, 18 (08): : 1063 - 1073
  • [6] Mangrove forests mapping using Sentinel-1 and Sentinel-2 satellite images
    Alireza Sharifi
    Shilan Felegari
    Aqil Tariq
    [J]. Arabian Journal of Geosciences, 2022, 15 (20)
  • [7] Mangrove Species Classification from Unmanned Aerial Vehicle Hyperspectral Images Using Object-Oriented Methods Based on Feature Combination and Optimization
    Ye, Fankai
    Zhou, Baoping
    [J]. SENSORS, 2024, 24 (13)
  • [8] Early identification of crop types using Sentinel-2 satellite images and an incremental multi-feature ensemble method (Case study: Shahriar, Iran)
    Rahmati, Amir
    Zoej, Mohammad Javad Valadan
    Dehkordi, Alireza Taheri
    [J]. ADVANCES IN SPACE RESEARCH, 2022, 70 (04) : 907 - 922
  • [9] Object-oriented Classification and QuickBird Multi-spectral Imagery in Forest Density Mapping
    Jayakumar, S.
    Ramachandran, A.
    Lee, Jung Bin
    Heo, Joon
    [J]. KOREAN JOURNAL OF REMOTE SENSING, 2007, 23 (03) : 153 - 160
  • [10] Object-Oriented Crop Classification Using Time Series Sentinel Images from Google Earth Engine
    Xue, Hanyu
    Xu, Xingang
    Zhu, Qingzhen
    Yang, Guijun
    Long, Huiling
    Li, Heli
    Yang, Xiaodong
    Zhang, Jianmin
    Yang, Yongan
    Xu, Sizhe
    Yang, Min
    Li, Yafeng
    [J]. REMOTE SENSING, 2023, 15 (05)