Advances in Hyperspectral Image Processing Techniques

18Collaborative Classification Based on Hyperspectral Images

Junping Zhang¹, Xiaochen Lu², and Tong Li³

¹School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin, China

²School of Information Science and Technology, Donghua University, Shanghai, China

³Satellite Application Division, Shanghai Institute of Satellite Engineering, Shanghai, China

18.1 Introduction

Over the past decades, land‐cover classification has become a main topic in hyperspectral (HS) remote‐sensing applications. HS image enables a detailed separation of similar ground materials due to its high spectral resolution. However, the low spatial resolution, mixed pixels, and the “the same object but different spectrum” and “the same spectrum but different objects” phenomena bring challenging problems to analysis of HS data. With the availability of multiple‐source image data from operational earth observation satellites, the demand for a higher classification accuracy of remotely sensed images has encouraged an increasing usage of distinct characteristic information collected from different sources. Combining these multiple‐source data is believed to offer strengthened capabilities for land‐cover classification than the single HS image type [1, 2].

In remote‐sensing area, panchromatic (PAN) image is possibly one of the most widely used data sources, because of its very high spatial resolution and relatively low‐cost accessibility. And, PAN image usually presents much more details ...