颜色-空间特征联合分布的无人机可见光遥感图像土地覆盖分类  

Land Cover Classification of UAV Visible Remote Sensing Based on Joint Distribution of Color-Spatial Feature

作　　者：曾雨双 曾绍华[1,2] 袁立 龙颖[4] Zeng Yushuang;Zeng Shaohua;Yuan Li;Long Ying(College of Computer and Information Science,Chongqing Normal University,Chongqing 401331,China;Chongqing Research Center on Engineer Technology of Digital Agricultural&Services,Chongqing 401331,China;College of Information Engineering,Chongqing Electric Power College,Chongqing 400053,China;College of Intelligent Information Engineering,Chongqing Aerospace Polytechnic College,Chongqing 400022,China)

机构地区：[1]重庆师范大学计算机与信息科学学院,重庆401331 [2]重庆市数字农业服务工程技术研究中心,重庆401331 [3]重庆电力高等专科学校信息工程学院,重庆400053 [4]重庆航天职业技术学院智能信息工程学院,重庆400022

出　　处：《激光与光电子学进展》2024年第24期231-243,共13页Laser & Optoelectronics Progress

基　　金：重庆市自然科学基金重点项目(CSTB2022NSCQ-LZX0081);重庆市科技局科技预见与制度创新项目(CSTB2023TFII-OFX0020);重庆市高校创新研究群体项目(CXQT20015)。

摘　　要：无人机可见光遥感图像因其获取的便捷性和低成本,被广泛应用于农业资源统计。在土地覆盖分类中,为了获取更具代表性的无人机可见光遥感图像特征,实现精准分类,本文提出颜色-空间特征联合分布土地覆盖分类算法。首先,构造黄金矩形地块指数,从标记地块中选择采样地块,并为所选地块构建对数螺线,选择训练样本;然后应用颜色特征基准点、邻域像素计算差分信息,提取每个样本点的颜色-空间联合特征;再依据Jensen不等式及模糊最大似然分类思想构建联合特征的目标函数,迭代求解各样本点的多维混合威布尔分布;最后,定义与多维混合威布尔分布相对应的相似性测度,实现各待测样本点的分类。实验结果表明:本文算法总体分类精度达到98.6%,优于局部二值模式、灰度共生矩阵、随机森林算法和ResNet、VGG网络,证明该算法是有效的。Due to their ease of access and low cost,unmanned aerial vehicle(UAV)visible remote sensing images have been widely used for the statistical analysis of agricultural resources.To obtain more representative features of UAV visible remote sensing images and achieve accurate land-cover classification,a land-cover classification algorithm based on the joint distribution of color-spatial features is proposed.First,the index of the golden rectangular patch is defined to select patches for sampling from the labeled data.Based on the golden rectangles of the selected patches,a logarithmic spiral was constructed to choose the training samples.Color feature reference points and neighborhood pixels were then applied to calculate the difference information and extract the color-space joint feature for each sample.Subsequently,the objective function of the joint feature is constructed using Jensen's inequality and fuzzy classification maximum likelihood.Next,the multidimensional mixed Weibull distribution of each sample is solved using several iterations.Finally,a similarity measure corresponding to the multidimensional mixed Weibull distribution was defined to classify each sample under analysis.Experimental results show that the overall accuracy of the proposed algorithm reaches 98.6%,which is better than that of local binary pattern,gray level cooccurrence matrix,random forest,ResNet,and VGG,proving the effectiveness of the proposed algorithm.

关 键 词：遥感 无人机可见光影像 土地覆盖分类 颜色-空间联合特征信息 混合威布尔分布 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]