An Evaluation of Visualization Techniques for Remotely Sensed Hyperspectral Imagery

Abstract

Displaying the abundant information contained in a remotely sensed hyperspectral image is a challenging problem. Currently no approach can satisfactorily render the desired information at arbitrary levels of detail. This chapter discusses user studies on several approaches for representing the information contained in hyperspectral information. In particular, we compared four visualization methods: grayscale side-by-side display (GRAY), hard visualization (HARD), soft visualization (SOFT), and double-layer visualization (DBLY). We designed four tasks to evaluate these techniques in their effectiveness at conveying global and local information in an effort to provide empirical guidance for better visual analysis methods. We found that HARD is less effective for global pattern display and conveying local detailed information. GRAY and SOFT are effective and comparable for showing global patterns, but are less effective for revealing local details. Finally, DBLY visualization is efficient in conveying local detailed information and is as effective as GRAY and SOFT for global pattern depiction.