Richard J. Murphy

Learn More
The use of hyperspectral imagery for robotics is predicted to increase as costs of sensors decline. A library of spectra can be used to map hyperspectral data to identify objects by comparing their reflectance signature to known materials. In this paper, methods used to build the spectral library to map geology on mine faces are described. The library(More)
—Hyperspectral data acquired from field-based platforms present new challenges for their analysis, particularly for complex vertical surfaces exposed to large changes in the geometry and intensity of illumination. The use of hyperspectral data to map rock types on a vertical mine face is demonstrated, with a view to providing real-time information for(More)
A new method is presented which combines a deterministic analytical method and a probabilistic measure to classify rock types on the basis of their hyperspectral curve shape. This method is a supervised learning algorithm using Gaussian Processes (GPs) and the Observation Angle Dependent (OAD) covariance function. The OAD covariance function makes use of(More)
Hyperspectral sensors provide a powerful tool for non-destructive analysis of rocks. While classification of spectrally distinct materials can be performed by traditional methods, identification of different rock types or grades composed of similar materials remains a challenge because spectra are in many cases similar. In this paper, we investigate the(More)
Hyperspectral imagery is used to map the distribution of iron and separate iron ore from shale (a waste product) on a vertical mine face in an open-pit mine in the Pilbara, Western Australia. Vertical mine faces have complex surface geometries which cause large spatial variations in the amount of incident and reflected light. Methods used to analyse imagery(More)
The use of hyperspectral data is limited, in part, by increased spectral noise, particularly at the extremes of the wavelength ranges sensed by scanners. We apply Gaussian Processes (GPs) as a preprocessing step prior to extracting mineralogical information from the image using automated feature extraction. GPs are a probabilistic machine learning technique(More)
Intertidal ecosystems have primarily been studied using field-based sampling; remote sensing offers the ability to collect data over large areas in a snapshot of time that could complement field-based sampling methods by extrapolating them into the wider spatial and temporal context. Conventional remote sensing tools (such as satellite and aircraft imaging)(More)
—Several environmental and sensor effects make the determination of the wavelength position of absorption features in the visible near infrared (VNIR) (400–1200 nm) from hyperspec-tral imagery more difficult than from nonimaging spectrometers. To evaluate this, we focus on the ferric iron crystal field absorption, located at about 900 nm (F 900), because it(More)
Feature selection is an important step in hyperspectral analysis using machine learning for many applications, in particular to avoid the curse of dimensionality when there is limited available ground truth. This paper presents an approach to select hyperspectral bands using boosting. Boosting decision trees is an efficient and accurate classification(More)