The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Articles | Volume XLII-3/W3
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W3, 195–200, 2017
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-3/W3, 195–200, 2017

  20 Oct 2017

20 Oct 2017


Q. Wang, Y. Gu, T. Liu, H. Liu, and X. Jin Q. Wang et al.
  • Dept. of Information Engineering, Harbin Institute of Technology, Harbin, 150001, China

Keywords: Class-pair-guided, Classification, Heterogeneous features (HFs), Light detection and ranging (LiDAR), Multispectral images (MSI), Multiple kernel learning (MKL)

Abstract. In recent years, many studies on remote sensing image classification have shown that using multiple features from different data sources can effectively improve the classification accuracy. As a very powerful means of learning, multiple kernel learning (MKL) can conveniently be embedded in a variety of characteristics. The conventional combined kernel learned by MKL can be regarded as the compromise of all basic kernels for all classes in classification. It is the best of the whole, but not optimal for each specific class. For this problem, this paper proposes a class-pair-guided MKL method to integrate the heterogeneous features (HFs) from multispectral image (MSI) and light detection and ranging (LiDAR) data. In particular, the one-against-one strategy is adopted, which converts multiclass classification problem to a plurality of two-class classification problem. Then, we select the best kernel from pre-constructed basic kernels set for each class-pair by kernel alignment (KA) in the process of classification. The advantage of the proposed method is that only the best kernel for the classification of any two classes can be retained, which leads to greatly enhanced discriminability. Experiments are conducted on two real data sets, and the experimental results show that the proposed method achieves the best performance in terms of classification accuracies in integrating the HFs for classification when compared with several state-of-the-art algorithms.