Multiple Kernel Sparse Representation for Airborne LiDAR Data Classification
Multiple Kernel Sparse Representation for Airborne LiDAR Data Classification
复制标题
DOI：
10.1109/tgrs.2016.2619384
复制
发表时间：
2017-02
影响因子：
8.2
通讯作者：
Yanfeng Gu;Qingwang Wang;Bingqian Xie
中科院分区：
文献类型：
--
作者：
Yanfeng Gu;Qingwang Wang;Bingqian Xie
为了有效地学习从原始LiDAR点云数据中提取的异质特征用于土地覆盖分类，提出了一种多核稀疏表示分类框架。在MKSRC中，将多核学习(MKL)嵌入稀疏表示分类(SRC)中。在分类之前，首先从原始的LiDAR点云数据中提取异质特征。这些要素包含来自不同维度的有用信息，包括单点要素和相邻要素。在特征提取的基础上，一方面将MKL合理地集成到SRC中，即在稀疏表示过程中利用每个异质特征分别构造的不同基核。在此基础上，将联合稀疏性模型引入MKSRC框架，提出了多核联合SRC(MKJSRC)。另一方面，为了更有效地确定MKSRC和MKJSRC中的基核，提出了改进的核对齐(IKA)方法。在三个真实的机载激光雷达数据集上进行了实验。实验结果表明，MKSRC和MKJSRC框架能够有效地学习LiDAR点云分类的异质特征，性能优于其他基于稀疏表示的分类器和最新的MKL算法。此外，与现有的核对齐方法相比，提出的IKA有助于更好地确定MKSRC和MKJSRC中基核的“最优”权值。
To effectively learn heterogeneous features extracted from raw LiDAR point cloud data for landcover classification, a multiple kernel sparse representation classification (MKSRC) framework is proposed in this paper. In the MKSRC, multiple kernel learning (MKL) is embedded into sparse representation classification (SRC). The heterogeneous features are first extracted from the raw LiDAR point cloud data before classification. These features contain useful information from different dimensions, including single point features and neighbor features. Based on feature extraction, on the one hand, MKL is reasonably integrated into the SRC, namely, different base kernels that are constructed with each heterogeneous feature separately are utilized in the process of sparse representation. Furthermore, joint sparsity model is also introduced into the MKSRC framework and multiple kernel joint SRC (MKJSRC) is then proposed. On the other hand, improved kernel alignment (IKA) methods are proposed to more effectively determine the weights of base kernels in both of MKSRC and MKJSRC. Experiments are conducted on three real airborne LiDAR data sets. The experimental results demonstrate that MKSRC and MKJSRC frameworks can effectively learn the heterogeneous features for LiDAR point cloud classification and outperforms the other state-of-the-art sparse representation-based classifiers and the recent MKL algorithm. Moreover, the proposed IKA is helpful to better determine the “optimal” weights of the base kernels in both MKSRC and MKJSRC than in the existing kernel alignment method.