Outlier and target detection in aerial hyperspectral imagery: a comparison of traditional and percentage occupancy hit or miss transform techniques

Abstract

The use of aerial hyperspectral imagery for the purpose of remote sensing is a rapidly growing research area. Currently, targets are generally detected by looking for distinct spectral features of the objects under surveillance. For example, a camouflaged vehicle, deliberately designed to blend into background trees and grass in the visible spectrum, can be revealed using spectral features in the near-infrared spectrum. This work aims to develop improved target detection methods, using a two-stage approach, firstly by development of a physics-based atmospheric correction algorithm to convert radiance into reflectance hyperspectral image data and secondly by use of improved outlier detection techniques. In this paper the use of the Percentage Occupancy Hit or Miss Transform is explored to provide an automated method for target detection in aerial hyperspectral imagery.

Potential of UV and SWIR hyperspectral imaging for determination of levels of phenolic flavour compounds in peated barley malt

“…In the past, applications of HSI are in the field of remote sensing such as precision agriculture (Datt, McVicar, Van Niel, Jupp, & Pearlman, 2003) , land cover analysis (Tong Qiao, Ren, Sun, Zheng, & Marshall, 2014) or military target detection (Manolakis & Shaw, 2002;Young, Marshall, & Gray, 2016). Due to recent advances in imaging technology in the last decades, HSI became more popular for lab-based applications such as food quality monitoring (Marshall, Kelman, Qiao, Murray, & Zabalza, 2015;Sun, 2010), medical applications (Lu & Fei, 2014) and even artwork inspection (Polak et al, 2016).…”

Hyperspectral image reconstruction using Multi-colour and Time-multiplexed LED illumination

“…In addition to the traditional applications of Hyperspectral Imaging (HSI) in remote sensing [1][2][3], the recent and rapid rise of interest for HSI was focused on various industrial applications, such as food quality monitoring [4][5][6], counterfeit detection [7] and artwork authentication [8,9]. Conventional HSI systems are, however, very cost intensive and require relatively complicated operation.…”