Hyperspectral Target Detection Methods Based on Statistical Information: The Key Problems and the Corresponding Strategies

Abstract

Target detection is an important area in the applications of hyperspectral remote sensing. Due to the full use of information of the target and background, target detection algorithms based on the statistical characteristics of an image are always occupy a dominant position in the field of hyperspectral target detection. From the perspective of statistical information, we firstly presented detailed discussions on the key factors affecting the target detection results, including data origin, target size, spectral variability of target, and the number of bands. Further, we gave the corresponding strategies for several common situations in the practical target detection applications.

Keywords

• hyperspectral
• target detection
• target size
• spectral variability
• band selection
• CEM