Combining Global Features and Local Interoperability Optimization Method for Extracting and Connecting Fine Rivers

Сохранить в:
Библиографические подробности
Опубликовано в::Remote Sensing vol. 17, no. 5 (2025), p. 742
Главный автор: Xu, Jian
Другие авторы: Gao, Xianjun, Wang, Zaiai, Li, Guozhong, Luan, Hualong, Cheng, Xuejun, Yao, Shiming, Wang, Lihua, Shi, Sunan, Xiao, Xiao, Xie, Xudong
Опубликовано:
MDPI AG
Предметы:
Online-ссылка:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

MARC

LEADER 00000nab a2200000uu 4500
001 3176397449
003 UK-CbPIL
022 |a 2072-4292 
024 7 |a 10.3390/rs17050742  |2 doi 
035 |a 3176397449 
045 2 |b d20250101  |b d20251231 
084 |a 231556  |2 nlm 
100 1 |a Xu, Jian  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); State Key Laboratory of Water Resources Engineering and Management, Wuhan University, Wuhan 430072, China 
245 1 |a Combining Global Features and Local Interoperability Optimization Method for Extracting and Connecting Fine Rivers 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Due to the inherent limitations in remote sensing image quality, seasonal variations, and radiometric inconsistencies, river extraction based on remote sensing image classification often results in omissions. These challenges are particularly pronounced in the detection of narrow and complex river networks, where fine river features are frequently underrepresented, leading to fragmented and discontinuous water body extraction. To address these issues and enhance both the completeness and accuracy of fine river identification, this study proposes an advanced fine river extraction and optimization method. Firstly, a linear river feature enhancement algorithm for preliminary optimization is introduced, which combines Frangi filtering with an improved GA-OTSU segmentation technique. By thoroughly analyzing the global features of high-resolution remote sensing images, Frangi filtering is employed to enhance the river linear characteristics. Subsequently, the improved GA-OTSU thresholding algorithm is applied for feature segmentation, yielding the initial results. In the next stage, to preserve the original river topology and ensure stripe continuity, a river skeleton refinement algorithm is utilized to retain critical skeletal information about the river networks. Following this, river endpoints are identified using a connectivity domain labeling algorithm, and the bounding rectangles of potential disconnected regions are delineated. To address discontinuities, river endpoints are shifted and reconnected based on structural similarity index (SSIM) metrics, effectively bridging gaps in the river network. Finally, nonlinear water optimization combined K-means clustering segmentation, topology and spectral inspection, and small-area removal are designed to supplement some missed water bodies and remove some non-water bodies. Experimental results demonstrate that the proposed method significantly improves the regularization and completeness of river extraction, particularly in cases of fine, narrow, and discontinuous river features. The approach ensures more reliable and consistent river delineation, making the extracted results more robust and applicable for practical hydrological and environmental analyses. 
653 |a Accuracy 
653 |a Deep learning 
653 |a Image resolution 
653 |a Algorithms 
653 |a Optimization techniques 
653 |a Segmentation 
653 |a Rivers 
653 |a Remote sensing 
653 |a Feature selection 
653 |a Hydrology 
653 |a Skeleton 
653 |a Seasonal variations 
653 |a Network topologies 
653 |a Machine learning 
653 |a Regularization 
653 |a River networks 
653 |a Topology 
653 |a Cluster analysis 
653 |a Image filters 
653 |a Clustering 
653 |a Completeness 
653 |a Water resources 
653 |a Decision making 
653 |a Neural networks 
653 |a Discontinuity 
653 |a Optimization 
653 |a Support vector machines 
653 |a Classification 
653 |a Image classification 
653 |a Methods 
653 |a Image quality 
653 |a Decision trees 
653 |a Water bodies 
653 |a Vector quantization 
653 |a Resource management 
700 1 |a Gao, Xianjun  |u School of Geosciences, Yangtze University, Wuhan 430100, China; <email>2024720538@yangtzeu.edu.cn</email> 
700 1 |a Wang, Zaiai  |u Hunan Institute of Water Resources and Hydropower Research, Changsha 410007, China; <email>wangzaiai0457@163.com</email> 
700 1 |a Li, Guozhong  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); Wuhan Smart Watershed Engineering Technology Research Center, Changjiang River Scientific Research Institute, Wuhan 430010, China 
700 1 |a Luan, Hualong  |u River Research Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>luanhualong@126.com</email> (H.L.); <email>yzhshymq@163.com</email> (S.Y.); Key Laboratory of River and Lake Regulation and Flood Control in the Middle and Lower Reaches of the Changjiang River, Ministry of Water Resources, Wuhan 430010, China 
700 1 |a Cheng, Xuejun  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); Wuhan Smart Watershed Engineering Technology Research Center, Changjiang River Scientific Research Institute, Wuhan 430010, China 
700 1 |a Yao, Shiming  |u River Research Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>luanhualong@126.com</email> (H.L.); <email>yzhshymq@163.com</email> (S.Y.); Key Laboratory of River and Lake Regulation and Flood Control in the Middle and Lower Reaches of the Changjiang River, Ministry of Water Resources, Wuhan 430010, China 
700 1 |a Wang, Lihua  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); Wuhan Smart Watershed Engineering Technology Research Center, Changjiang River Scientific Research Institute, Wuhan 430010, China 
700 1 |a Shi, Sunan  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); Wuhan Smart Watershed Engineering Technology Research Center, Changjiang River Scientific Research Institute, Wuhan 430010, China 
700 1 |a Xiao, Xiao  |u Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China; <email>xujian@mail.crsri.cn</email> (J.X.); <email>liguozhong@mail.crsri.cn</email> (G.L.); <email>chengxj@mail.crsri.cn</email> (X.C.); <email>wanglihua@mail.crsri.cn</email> (L.W.); <email>shisunan@mail.crsri.cn</email> (S.S.); <email>xiaoxiao@mail.crsri.cn</email> (X.X.); Wuhan Smart Watershed Engineering Technology Research Center, Changjiang River Scientific Research Institute, Wuhan 430010, China 
700 1 |a Xie, Xudong  |u School of Geosciences, Yangtze University, Wuhan 430100, China; <email>2024720538@yangtzeu.edu.cn</email> 
773 0 |t Remote Sensing  |g vol. 17, no. 5 (2025), p. 742 
786 0 |d ProQuest  |t Advanced Technologies & Aerospace Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3176397449/abstract/embedded/09EF48XIB41FVQI7?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3176397449/fulltextwithgraphics/embedded/09EF48XIB41FVQI7?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3176397449/fulltextPDF/embedded/09EF48XIB41FVQI7?source=fedsrch