基于激光雷达数据阴影处理和图像融合的地物分类方法

城市可见光图像中高大的建筑和树木造成的阴影及部分树木区域出现的颜色失真问题使得传统的颜色量化方法不能准确描述地物谱差异，最终导致分类精度下降。针对可见光图像中的阴影和颜色失真问题提出了一种改进办法：第一阶段针对阴影导致的被掩盖区域谱信息缺失问题，对阴影区域进行采样、分析，通过双阈值提取阴影区域并以面向对象分类方法获得绿色区域阴影。第二阶段通过融合树木区域在多源信息[激光雷达强度、多次回波的数字表面模型（DSM）]中的差异特征，剔除冗余，获取准确的树木区域，弥补颜色失真使得树木区域提取不完全的缺陷。实验结果与人工获取的真实数据对比显示，该方法与传统的Dempster-Shafer (D-S)证据理论融合方法相比，分类精度有了明显的提高。

Abstract

Shadows caused by tall buildings and trees and color distortion in visible image make that traditional color quantization cannot accurately describe the spectral difference of different objects on the ground. This defect declines classification accuracy finally. In view of shadows and color distortion problem in the lowquality visible image, we put forward an improved method. On the first stage of our algorithm, the problem of missing spectrum information caused by shadows is solved through sampling, analysing, and extracting shaded regions by double-threshold method and then classifying different kinds of shaded regions by object-oriented method. On the second stage, we obtain accurate areas of trees by fusing discriminative information [lidar intensity, digital surface model (DSM)] in order to compensate incomplete extraction caused by color distortion. The experimental results in comparison with ground truth obtained by manual work show that the classification accuracy is improved obviously compared with the results obtained by traditional Dempster-Shafer (D-S) fusing method.

参考文献

[1] 张玉方, 程新文, 欧阳平. 机载lidar 数据处理及其应用综述[J].工程地球物理学报,2008, 5(1): 120-124.

Zhang Yufang, Cheng Xinwen, Ouyang Ping. The data processing technology and application of airborne lidar [J]. Chinese J Engineering Geophysics, 2008, 5(1): 120-124.

[2] 董云升, 刘文清, 刘建国, 等. 激光雷达在城市交通污染中应用研究[J]. 光学学报, 2010, 30(2): 315-320.

Dong Yunsheng, Liu Wenqing, Liu Jianguom, et al.. Application study of lidar in urban traffic pollution [J]. Acta Optica Sinica, 2010, 30(2): 315-320.

[3] 李德仁, 陈晓玲, 蔡晓斌. 空间信息技术用于汶川地震救灾[J]. 遥感学报, 2008, 12(6): 841-850.

Li Deren, Chen Xiaoling, Cai Xiaobin. Space technology used in wenchuan earthquake relief [J]. J Remote Sensing, 2008, 12(6): 841-850.

[4] 吴慧云, 孙振海, 黄志松, 等. 生化战剂激光侦检技术的发展概述[J]. 激光与光电子学进展, 2013, 50(2): 020001.

Wu Huiyun, Sun Zhenhai, Huang Zhisong, et al.. Development of laser warning and detection technology for chemical/biological agents [J]. Laser & Optoelectronics Progress, 2013, 50(2): 020001.

[5] Yang Cao, Hong Wei, Huijie Zhao. An effective approach for land-cover classification from airborne lidar fused with co-registered data [J]. International Journal of Remote Sensing, 2012, 33(18): 5927-5953.

[6] Rafael C Gonzalez, Richard E Woods.数字图像处理[M].阮秋琦,阮宇智译. 北京: 电子工业出版社, 2004. 233-239.

Rafeal C Gonzalez, Richard E Wods. Digital Image Processing [M]. Ruan Qiuqi, Ruan Yuzhi Transl.. Beijing: Publishing House of Electronics Industry, 2004. 233-239.

[7] 余柏蒗, 刘红星, 吴健平. 一种应用机载LiDAR 数据和高分辨率遥感影像提取城市绿地信息的方法[J]. 中国图象图形学报, 2010, 15(5): 782-788.

Yu Bailang, Liu Hongxing, Wu Jianping. A method for urban vegetation classification using airborne LiDAR data and high resolution remote sensing images [J]. Journal of Image and Graphics, 2010, 15(5): 782-788.

[8] 杨俊, 赵忠明. 一种高分辨率遥感影像阴影去除方法[J].武汉大学学报,2008, 33(1): 17-20.

Yang Jun, Zhao Zhongming. A method of shadow elimination from high resolution remote sensing images [J]. Geomatics and Information Science of Wuhan University, 2008, 33(1): 17-20.

[9] 蒲智, 刘萍, 杨辽, 等. 城市绿地信息提取中的遥感影像阴影校正[J]. 北京林业大学学报,2009, 33(2): 80-85.

Pu Zhi, Liu Ping, Yang Liao, et al.. Shadow rectification of remote sensing images in information extraction for urban green space [J]. Journal of Beijing Forestry University, 2009, 33(2): 80-85.

[10] 徐晓昭, 沈兰荪, 刘长江. 颜色校正方法及其在图像处理中的应用[J]. 计算机应用研究,2008, 22(8): 2250-2254.

Xu Xiaozhao, Shen Lansun, Liu Changjiang. Color correction methods and application in image processing [J]. Application Research of Computer, 2008, 22(8): 2250-2254.

[11] Franz Rottensteiner, John Trinder, Simon Clode, et al.. Using the Dempster– Shafer method for the fusion of LIDAR data and multi-spectral images for building detection [J]. Fusion of Remotely Sensed Data over Urban Area, 2005, 6(4): 283-300.

[12] F Samadzadegan, B Bigdeli, M Hahn. Automatic road extraction from lidar data based on classifier fusion [J]. Urban Remote Sensing Event, 2009, 38(3): 231-245.

梁小伟, 杨风暴, 卫红, 李大威. 基于激光雷达数据阴影处理和图像融合的地物分类方法[J]. 激光与光电子学进展, 2014, 51(4): 041006. Liang Xiaowei, Yang Fengbao, Wei Hong, Li Dawei. Land-Cover Classification Based on Dealing with Shadows and Fusing Lidar Data[J]. Laser & Optoelectronics Progress, 2014, 51(4): 041006.

基于激光雷达数据阴影处理和图像融合的地物分类方法下载： 557次

关于本站 Cookie 的使用提示

全站搜索

基于激光雷达数据阴影处理和图像融合的地物分类方法 下载： 557次

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索

基于激光雷达数据阴影处理和图像融合的地物分类方法下载： 557次