顾及局部特征的图像短直线优化方法研究  

Research on Image Short-line Optimization Method Considering Local Features

作　　者：李靖 王晨安 LI Jing

机构地区：[1]河海大学地球科学与工程学院,江苏南京211100

出　　处：《地理空间信息》2019年第1期115-118,125,共5页Geospatial Information

基　　金：国家自然科学基金资助项目(41101374);水利部公益性行业科研专项经费资助项目(201201025)

摘　　要：由于各种线段检测算法误差以及相片噪声、遮挡物等因素的影响,导致图像线特征要素出现断裂、重叠、连续间断线段等情况。目前的解决方法主要是以线段的自身属性为阈值判断,并利用先验经验辅助判断。提出了一种顾及局部特征的优化删减短直线特征要素的方法,以提高现有算法的自动化水平;同时从整体角度出发,引入局部整体方向的概念来改进现有算法。Due to the errors of various line segment detection algorithms and the effects of image noise, occluder and other factors, the resulting feature lines of the image lines are broken, overlapped, and continuously broken line segments. The current solution is mainly based on the judgment of the threshold of the line segment’s own attributes, and will be judged by prior experience. In this paper, we proposed a method for optimizing and deleting short-line feature elements which taking into account the local features, to improve the automation level of the current algorithms. At the same time, from the overall perspective, we introduced the concept of local overall direction to improve the current algorithms.

关 键 词：统计直方图 端点搜索 对角线合并 局部特征 直线段检测 LSD 

分 类 号：P23[天文地球—摄影测量与遥感]