Open AccessWater System Segmentation Method of High Resolution Remote Sensing Image Based on eCognition
Author(s) -
Bei Xue,
Xiao Lin
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1651/1/012162
Subject(s) - segmentation , scale space segmentation , segmentation based object categorization , image segmentation , artificial intelligence , minimum spanning tree based segmentation , computer vision , computer science , scale (ratio) , remote sensing , pattern recognition (psychology) , geology , geography , cartography
High-resolution remote sensing images contain abundant ground object information. In this paper, water system elements are segmented and interpreted based on eCognition platform. Three segmentation methods, multi-scale image segmentation, quadtree segmentation and checkerboard segmentation, and their segmentation principles are introduced. The advantages and disadvantages of different segmentation methods are obtained through experimental analysis, and the optimal segmentation parameters of multi-scale segmentation are obtained by setting different segmentation parameter experiments. This paper is of guiding significance for the interpretation of water system data and the dynamic update of geographical survey elements in later remote sensing images.