Line Segment Optimization Algorithm for High Resolution Optical Remote Sensing Image Based on Geometric and Texture Constraints

作     者：Jiguang DAI Yue GU Guang JIN Lei ZHU Jiguang DAI;Yue GU;Guang JIN;Lei ZHU

作者机构：School of GeomaticsLiaoning Technical UniversityFuxin 123000China Liaoning Aulutong Tech.LTDShenyang 110006China Huludao Hongyue Group CompanyHuludao 125003China 

出 版 物：《Journal of Geodesy and Geoinformation Science》 (测绘学报（英文版）)

年 卷 期：2020年第3卷第3期

页      面：115-127页

学科分类：0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理] 

基　　金：National Natural Science Foundation of China(No.41271374) Key Natural Science Plan Fund of Liaoning Province(No.20170520141) Public Welfare Research Fund of Liaoning Provincial(No.20170003) Liaoning Provincial Department of Education Project Services Local Project(No.LJ2019FL008)。 

主　　题：optimization line segment constraint 

摘      要：Aiming at the problem that high-resolution optical remote sensing image,lines are prone to fracture,and a line segment optimization algorithm is proposed in this paper.Firstly,the line segment is regarded as a way to express the contour of the ground object,and the laws of line segment fracture from two aspects of geometric features and texture features are analyzed;Secondly,the line segment optimization algorithm is proposed.It takes the results of detecting line segments as the processing primitives,determines the initial optimized line segment according to the length of the line segment,establishes the tracking rectangular region and geometric constraint model for the fractured line segments,builds a dynamic optimization model,and gives a complete line optimization process.Through the analysis of experimental results of multiple actual scenes and different types of remote sensing images,it is shown that this algorithm can not only solve the problem of line segment fracture caused by terrain occlusion,edge blurring,and edge serration,but also comparing with other methods,the proposed algorithm has great advantages in optimizing line length and restraining over extraction problem.