Unsupervised tree occlusion removal for close-range building images under condition of visible light

被引：0

作者：

Li C. ^{[1
,2
]}

Ma H. ^{[3
]}

Dong C. ^{[4
]}

机构：

[1] Hubei Province Key Laboratory for Geographical Process Analysing & Modelling, Central China Normal University, Wuhan

[2] College of Urban and Environmental Science, Central China Normal University, Wuhan

[3] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan

[4] School of Mathematics and Statistics, Central China Normal University, Wuhan

来源：

Ma, Hao (mahao_fido@126.com) | 1600年 / Editorial Board of Medical Journal of Wuhan University卷 / 41期

基金：

中国国家自然科学基金;

关键词：

Building images; CIE L*a*b color space; Image segmentation; Topological relationship; Vegetation occlusion;

D O I：

10.13203/j.whugis20140010

中图分类号：

学科分类号：

摘要：

A new approach based on spatial relationships and key features ratio in CIE L*a*b color space is proposed for vegetation extraction to solve current problems in tree occlusion removal algorithms for visible light images, such as incompletely detected tree areas and mass human-computer interaction. First, the color space of an image is transformed from RGB to CIE L*a*b. Second, the classic Otsu method was used to segment the L channel and a channel image. Finally, morphology modification; the spatial topological relationship between crown and trunk and key feature ratio, were applied to acquire the final vegetation areas. Experimental results show that the proposed algorithm can successfully remove vegetation occlusions (i.e. canopies and trunks) with a high level of automation. This study can pave the way for occluded image repair and 3D reconstruction of close-range building images. © 2016, Wuhan University All right reserved.

引用

页码：612 / 616

页数：4