Content area
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.
Details
Deep learning;
Image resolution;
Algorithms;
Optimization techniques;
Segmentation;
Rivers;
Remote sensing;
Feature selection;
Hydrology;
Skeleton;
Seasonal variations;
Network topologies;
Machine learning;
Regularization;
River networks;
Topology;
Cluster analysis;
Image filters;
Clustering;
Completeness;
Water resources;
Decision making;
Neural networks;
Discontinuity;
Optimization;
Support vector machines;
Classification;
Image classification;
Methods;
Image quality;
Decision trees;
Water bodies;
Vector quantization;
Resource management
; Cheng, Xuejun 4 ; Yao, Shiming 5 ; Wang, Lihua 4 ; Shi, Sunan 4 ; Xiao, Xiao 4 ; Xie, Xudong 2 1 Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China;
2 School of Geosciences, Yangtze University, Wuhan 430100, China;
3 Hunan Institute of Water Resources and Hydropower Research, Changsha 410007, China;
4 Spatial Information Technology Application Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China;
5 River Research Department, Changjiang River Scientific Research Institute, Changjiang Water Resources Committee, Wuhan 430010, China;