期刊论文

Ma, Hao(mahao_fido@126.com)

中文

武汉大学学报(信息科学版)

1671-8860

2016

41

5

612-616

10.13203/j.whugis20140010

国家自然科学基金（41101407） 湖北省自然科学基金（2014CFB377,2010CDZ005） 华中师范大学中央高校基本科研项目（CCNU15A02001）.

本校为第一机构

针对已有算法在可见光条件下不能完整提取树木或者需要大量人工干预的缺陷,提出了一种基于CIE L*a*b色彩空间的利用冠层与树干空间拓扑关系和关键特征比值的非监督树木分割算法。首先,将RGB转换到CIE L*a*b色彩空间;然后,选择该空间中的关键特征进行Otsu自适应阈值分割;最后,利用数学形态学对分割区域进行去噪,结合冠层与树干的空间拓扑关系和色彩特征比值关系剔除伪树木区域。实验结果表明,本文方法能成功分割出冠层和树干遮挡且自动化程度高,可为近景建筑物三维重建的遮挡区修补提供检测基础。

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 tr...