基于子空间划分和视觉可识别度的波段选择方法研究  

Research on Band Selection Method Based on Subspace Division and Visual Recognition

作　　者：金椿柏 杨桄[1] 卢珊 陈强[1,3] 郑南[1] JIN Chun-bai;YANG Guang;LU Shan;CHEN Qiang;ZHENG Nan(Aviation University Air Force,Changchun 130022,China;School of Geographical Science,Northeast Normal University,Changchun 130024,China;Unit 93116 of PLA,Shenyang 110000,China)

机构地区：[1]空军航空大学,吉林长春130022 [2]东北师范大学地理科学学院,吉林长春130024 [3]中国人民解放军93116部队,辽宁沈阳110000

出　　处：《光谱学与光谱分析》2023年第5期1582-1588,共7页Spectroscopy and Spectral Analysis

基　　金：国家自然科学基金项目(41971290)资助。

摘　　要：面对日益丰富的机载、星载高光谱传感器,及其相伴增多的高光谱数据,产生的数据量过大、波段冗余等问题一直是高光谱图像处理、解译的重难点。同时,利用高光谱遥感技术揭露伪装目标,也一直是现代遥感应用技术研究要点。在探测得到海量的地物光谱数据、具有冗余的光谱信息,设计恰当的数据降维技术具有至关重要的作用。降维处理的主要方法中的波段选择方法,其不但可以使图像数据的光谱信息在不失真的条件下实现数据降维,还能在其基础上对伪装目标及其背景实现精确区分,是当今利用高光谱技术进行军事应用的重要技术手段,同时也是国内外众多学者的研究热点。利用各类指标计算波段间的不同表现,并依据其参数选取代表性强的波段用于地物识别或分类来检验方法的优劣是目前比较常用的研究方式,但是面向特殊地物,如植被伪装目标的特定波段选择方法方面的实验研究现仍较少。研究选取绿色钢板、绿色伪装网、绿色假草皮,置于含有绿色健康植被、湿润裸地、干燥裸地的背景环境中,通过模拟真实环境中的伪装目标和背景地物进行波段选择及分类实验验证。首先通过分析光谱曲线,选取显著特征波段;其次结合根据波段间相关系数划分的子空间进行波段筛选;然后依据地物目标的图像亮度建立视觉模型,最终得到具有相对独立性和最佳可识别度的波段选择集合。并在支持向量机分类器和马氏距离分类器中同两种常用算法选择波段结果与全波段组合进行分类实验对比,实验发现所提出方法的波段选择结果相对于常用算法和全波段组合,分类精度和速度均有所提高。其中,相较于应用全波段进行分类,在两类分类器的分类结果,总体分类精度分别提高4.559 2%和2.364 8%, Kappa系数分别提高0.059 4和0.031 2,分类时间减少6.83 s。实验证明该方法能�In the face of the increasingly abundant airborne and spaceborne hyperspectral sensors and the accompanying increase in hyperspectral data,the problems of excessive data volume and band redundancy have always been the major difficulties in hyperspectral image processing and interpretation.At the same time,the use of hyperspectral remote sensing technology to reveal camouflaged targets has always been the key point of modern remote sensing application technology research.In detecting massive spectral data of ground objects and redundant spectral information,the design of appropriate data dimensionality reduction technology plays a vital role.The band selection method among the main methods of dimensionality reduction processing can not only reduce the spectral information of the image data without distortion but also accurately distinguish the camouflaged target and its background based on it.Today,hyperspectral technology is an important technical means for military applications,and it is also a research hotspot for many scholars at home and abroad.It is a commonly used research method to use various indicators to calculate the different performances between the bands and to select the most representative bands according to their parameters for feature identification or classification to test the pros and cons of the method.However,few experimental studies still exist on specific band selection methods for special features,such as vegetation camouflage targets.In the study,green steel plates,green camouflage nets,and green fake turf were selected and placed in a background environment containing healthy green vegetation,wet bare ground,and dry,bare ground.Band selection and classification experiments were carried out by simulating camouflage targets and background objects in the real environment.First,analyze the spectral curve,and select a significant feature band.Secondly,the band screening is performed based on the sub-space divided according to the phase relationship between the band.The visual model is then

关 键 词：植被伪装 相关系数 子空间划分 可识别度 分类精度 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]