基于尖τ型DS证据理论的机载LiDAR地物分类方法

A land-cover classification method for airborne LiDAR based on sharp DS evidence theory

针对机载激光雷达扫描与测距系统(LiDAR)应用于复杂地物分类场景时难以兼顾高精度和实时性的局限,提出一种基于尖τ型信任分配函数的LiDAR数据快速地物分类方法。首先,在基本DS证据理论的基础上引入模糊集理论,根据不同地物特性构建尖τ型信任分配函数以及模糊类别,对不同特征数据进行信任分配和融合决策;其次,利用圆形区域均值滤波对源数据噪声和分类过程中引入的噪声进行处理;最后,采用两组不同LiDAR数据集对该方法进行实验。实验结果表明,该方法分类精度达到88.50%以上,运行时间小于0.28s。

Aiming at the limitation of high accuracy and real-time performance when the airborne lidar scanning and ranging system(LiDAR)is used in complex terrain classification scenes,a fast terrain classification method based on LiDAR data based on the tipτtrust distribution function is proposed.Firstly,the fuzzy set theory is introduced on the basis of the basic DS evidence theory,and the sharpτtrust assignment function and fuzzy category are constructed according to the characteristics of different features,and the trust assignment and fusion decision-making of different feature data are carried out.Secondly,the source data noise and the noise introduced in the classification process are processed.Finally,two different LiDAR data sets are used to experiment with the method.Experimental results show that the classification accuracy of this method is above 88.50%,and the running time is less than 0.28 s.