Dave Barnes

Fuzzy-rough feature selection aided support vector machines for Mars image classification

This paper presents a novel application of advanced machine learning techniques for Mars terrain image classification. Fuzzy-rough feature selection (FRFS) is adapted and then employed in conjunction with Support Vector Machines (SVMs) to construct image classifiers. These techniques are integrated to address problems in space engineering where the images are of many classes, large-scale, and diverse representational properties. The use of the adapted FRFS allows the induction of low-dimensionality feature sets from feature patterns of a much higher dimensionality. To evaluate the proposed work, K-Nearest Neighbours (KNNs) and decision trees (DTREEs) based image classifiers as well as information gain rank (IGR) based feature selection are also investigated here, as possible alternatives to the underlying machine learning techniques adopted. The results of systematic comparative studies demonstrate that in general, feature selection improves the performance of classifiers that are intended for use in high dimensional domains. In particular, the proposed approach helps to increase the classification accuracy, while enhancing classification efficiency by requiring considerably less features. This is evident in that the resultant SVM-based classifiers which utilise FRFS-selected features generally outperform KNN and DTREE based classifiers and those which use IGR-returned features. The work is therefore shown to be of great potential for on-board or ground-based image classification in future Mars rover missions.

Facilitating efficient Mars terrain image classification with fuzzy-rough feature selection

This paper presents an application study of exploiting fuzzy-rough feature selection (FRFS) techniques in aid of efficient and accurate Mars terrain image classification. The employment of FRFS allows the induction of low-dimensionality feature sets from sample descriptions of feature vectors of a much higher dimensionality. Supported with comparative studies, the work demonstrates that FRFS helps to enhance both the effectiveness and the efficiency of conventional classification systems such as multi-layer perceptrons and K-nearest neighbors, by minimizing redundant and noisy features. This is of particular significance for on-board image classification in future Mars rover missions.

Support vector machine-based classification of rock texture images aided by efficient feature selection

This paper presents a study on rock texture image classification using support vector machines (and also K-nearest neighbours and decision trees) with the aid of feature selection techniques. It offers both unsupervised and supervised methods for feature selection, based on data reliability and information gain ranking respectively. Following this approach, the conventional classifiers which are sensitive to the dimensionality of feature patterns, become effective on classification of images whose pattern representation may otherwise involve a large number of features. The work is successfully applied to complex images. Classifiers built using features selected by either of these methods generally outperform their counterparts that employ the full set of original features which has a dimensionality several folds higher than that of the selected feature subset. This is confirmed by systematic experimental investigations. This study therefore, helps to accomplish challenging image classification tasks effectively and efficiently. In particular, the approach retains the underlying semantics of a selected feature subset. This is very important to ensure that the classification results are understandable by the user.

Combining support vector machines and information gain ranking for classification of mars McMurdo panorama images

This paper presents a novel application of support vector machine (SVM) based classifiers for Mars terrain image classification. SVMs are applied in conjunction with information gain ranking (IGR) that allows the induction of informative feature subsets from sample descriptions of feature vectors of a higher dimensionality. Such an integrated use of IGR and SVMs helps to enhance the effectiveness and efficiency of the classifiers, minimizing redundant and noisy features. This work is supported with comparative studies — the resultant SVM-based classifiers generally outperform MLP and KNN-based classifiers and those which use PCA-returned features.

Haptic communication for mobile robot operations

Teleoperations in hazardous environments are often hampered by the lack of available information regarding the state of the remote robotic device. Typically, ideal camera placements are not possible, and an operator is left with the problem of performing complex manoeuvres in the presence of severe blind‐spots. To address this dilemma, we have been investigating the use of a haptic interface, which not only allows an operator to communicate motion commands to a robot, but also allows the robot to communicate to the operator its motion when performing autonomous collision avoidance. This haptic interface provides total operator control, plus vital information that can be used to decide if and how a robots autonomous operation should be overridden. This paper details our work in this area and presents the results we have obtained from operator/task performance experimentation with this new haptic communication approach.

Robotic experiments with cooperative aerobots and underwater swarms

SciSys has been involved in the development of Planetary Aerobots (arial robots) funded by the European Space Agency for use on Mars and has developed image-based localisation technology as part of the activity. However, it is possible to use Aerobots in a different environment to investigate issues regarding robotics behaviour, such as data handling, limited processing power, and limited sensors. This paper summarises the activity where an Aerobot platform was used to investigate the use of multiple autonomous unmanned underwater vehicles (UUVs) by simulating their movement and behaviour. It reports on the computer simulations and the real-world tests carried out and the lessons learned from these experiments.

Effective Feature Selection for Mars McMurdo Terrain Image Classification

This paper presents a novel study of the classification of large-scale Mars McMurdo panorama image. Three dimensionality reduction techniques, based on fuzzy-rough sets, information gain ranking, and principal component analysis respectively, are each applied to this complicated image data set to support learning effective classifiers. The work allows the induction of low-dimensional feature subsets from feature patterns of a much higher dimensionality. To facilitate comparative investigations, two types of image classifier are employed here, namely multi-layer perceptrons and K-nearest neighbors. Experimental results demonstrate that feature selection helps to increase the classification efficiency by requiring considerably less features, while improving the classification accuracy by minimizing redundant and noisy features. This is of particular significance for on-board image classification in future Mars rover missions.

Integrated field testing of planetary robotics vision processing: the PRoVisG campaign in Tenerife 2011

In order to maximize the use of a robotic probe during its limited lifetime, scientists immediately have to be provided the best achievable visual quality of 3D data products. The EU FP7-SPACE Project PRoVisG (2008-2012) develops technology for the rapid processing and effective representation of visual data by improving ground processing facilities. In September 2011 PRoVisG held a Field Trials campaign in the Caldera of Tenerife to verify the implemented 3D Vision processing mechanisms and to collect various sets of reference data in representative environment. The campaign was strongly supported by the Astrium UK Rover Bridget as a representative platform which allows simultaneous onboard mounting and powering of various vision sensors such as the Aberystwyth ExoMars PanCam Emulator (AUPE). The paper covers the preparation work for such a campaign and highlights the experiments that include standard operations- and science- related components but also data capture to verify specific processing functions. We give an overview of the captured data and the compiled and envisaged processing results, as well as a summary of the test sites, logistics and test assets utilized during the campaign.

An Approach for Matching Desired Non-feature Points on Mars Rock Targets Based on SIFT

In Mars rover missions ExoMars is the forthcoming ESA/NASA 2018 mission, and one of the future goals is to cache rock samples for subsequent return to Earth as part of the Mars Sample Return (MSR) mission. This paper describes some early work with respect to our eventual objective, which is to use a manipulator mounted on a rover to acquire rock samples that are of scientific interest (such as metamorphic rock, sedimentary rock and igneous rock). Subsequently, we would be able to carry out analysis for these rocks by utilizing precise and various instruments on Earth. The current research is comprised of two parts: Target Identification and Non-Feature Points Matching, which are described below.

Developing an autonomous imaging and localisation capability for planetary aerobots

Abstract Balloon based planetary aerobots can be used for a variety of applications such as high resolution imaging and rover guidance. However short to medium term missions of this type will be constrained in terms of power, communications, data storage and processing capability. To be of use, they must be able to localise and manage image data in an autonomous manner, including intelligent prioritisation of images. This paper discusses the development of an intelligent imaging and localisation software package and demonstrator which will help to provide such an autonomous capability.