高光谱遥感影像与高程数据融合方法综述  

A review of fusion methods of hyperspectral and LiDAR images

作　　者：杜星乾 侯艳杰 唐轶[4] DU Xing-qian;HOU Yan-jie;TANG Yi(Key Laboratory of Spectral Imaging Technology CAS,Xi’an Institute of Optics and Precision Mechanics,Chinese Academy of Sciences,Xi’an,Shaanxi 710119,China;University of Chinese Academy of Sciences,Beijing 100049,China;Taiyuan Satellite Launch Center,Taiyuan 030027,China;School of Mathematics and Computer Science,Yunnan Minzu University,Kunming 650500,China)

机构地区：[1]中国科学院西安光学精密机械研究所光谱成像技术重点实验室,陕西西安710119 [2]中国科学院大学,北京100049 [3]太原卫星发射中心,山西太原030027 [4]云南民族大学数学与计算机科学学院,云南昆明650500

出　　处：《云南民族大学学报（自然科学版）》2020年第1期47-58,共12页Journal of Yunnan Minzu University:Natural Sciences Edition

基　　金：国家自然科学基金(61462096,61866040,61561053).

摘　　要：高光谱遥感和激光雷达(light detection and ranging,LiDAR)是2种常见的遥感手段,各自具有不同的特点.高光谱图像能够很好地表征地物的光谱信息,反映出其材料、质地等特点,而激光雷达能够高效、精确地获取地面的高程数据.将这两种数据结合,能够优势互补,对地物实现更加精确的智能探测与识别,在植被分析、城市规划、气候建模等领域均有应用.为了更好地了解该领域目前的研究现状,把握未来发展方向,对近年来的高光谱影像和激光雷达数据融合方法进行了整理,按照基于形态学特征和深度学习的两大类分别进行介绍,总结这这些方法的特点.最后,对未来的发展方向进行了展望,分析了该领域未来的发展趋势.Hyperspectral imagery(HSI)and light detection and ranging(LiDAR)are two common methods of remote sensing with different characteristics.HSI can well represent the spectral information of land cover,containing the material,texture and other characteristics of the targets,while LiDAR is able to acquire the elevation data of the land cover efficiently and accurately.The integration of both types of remote sensing data leads to more accurate intelligent detection and recognition of land cover,which is already applied in the fields of vegetation analysis,urban planning and climate modeling.In order to better understand the current research status and the future development orientation in this field,this paper gives an incisive analysis of the HSI and LiDAR data fusion methods in recent years according to two major categories based on morphological features and deep learning.Finally,it predicts its future development orientation.

关 键 词：高光谱遥感 激光雷达 数据融合 深度学习 形态学特征 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]