Maqola

Shrub Extraction in Arid Regions Based on Feature Enhancement and Transformer Network from High-Resolution Remote Sensing Images

Hao LiuNanjing University of Information Science & Technology, Nanjing 210044, ChinaWenjie ZhangState Key Laboratory of Geo-Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaYong ChengNanjing University of Information Science & Technology, Nanjing 210044, ChinaJiaxin HeNanjing University of Information Science & Technology, Nanjing 210044, ChinaHaoyun ShaoNanjing University of Information Science & Technology, Nanjing 210044, ChinaSen BaiNanjing University of Information Science & Technology, Nanjing 210044, ChinaWei WangSchool of Geography and Ocean Science, Nanjing University, Nanjing 210023, ChinaDi ZhouState Key Laboratory of Integrated Service Networks, Xidian University, Xi’an 710071, ChinaFa ZhuCollege of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaNuriddin SamatovResearch Institute of Environment and Nature Conservation Technologies of the Ministry of Ecology, Environmental Protection, and Climate Change of the Republic of Uzbekistan, Tashkent 100043, UzbekistanBakhtiyor PulatovResearch Institute of Environment and Nature Conservation Technologies, Bunyodkor Ave., Tashkent 100043, UzbekistanAziz InamovTashkent Institute of Irrigation and Agricultural Mechanization Engineers, Tashkent 100043, Uzbekistan

Forestsjournal2025en

ABI

Annotatsiya

The shrubland ecosystems in arid areas are highly sensitive to global climate change and human activities. Accurate extraction of shrubs using computer vision techniques plays an essential role in monitoring ecological balance and desertification. However, shrub extraction from high-resolution GF-2 satellite images remains challenging due to their dense distribution and small size, along with complex background. Therefore, this study introduces a Feature Enhancement and Transformer Network (FETNet) by integrating the Feature Enhancement Module (FEM) and Transformer module (EdgeViT). Correspondently, they can strengthen both global and local features and enable accurate segmentation of small shrubs in complex backgrounds. The ablation experiments demonstrated that incorporation of FEM and EdgeViT can improve the overall segmentation accuracy, with 1.19% improvement of the Mean Intersection Over Union (MIOU). Comparison experiments show that FETNet outperforms the two leading models of FCN8s and SegNet, with the MIOU improvements of 7.2% and 0.96%, respectively. The spatial details of the extracted results indicated that FETNet is able to accurately extract dense, small shrubs while effectively suppressing interference from roads and building shadows in spatial details. The proposed FETNet enables precise shrub extraction in arid areas and can support ecological assessment and land management.

Mavzular

Remote Sensing in Agriculture Remote Sensing and LiDAR Applications Rangeland and Wildlife Management

Identifikatorlar

DOI: 10.3390/f16081288

Iqtiboslar va manbalar

0 ta iqtibos57 ta foydalanilgan manba

Koʻrsatkichlar — AkademScholar · Tez orada