Fast and robust stereo matching algorithms for mining automation

The mining environment, being complex, irregular and time varying, presents a challenging prospect for stereo vision. The objective is to produce a stereo vision sensor suited to close-range scenes consisting primarily of rocks. This sensor should be able to produce a dense depth map within real-time constraints. Speed and robustness are of foremost importance for this investigation. A number of area based matching metrics have been implemented, including the SAD, SSD, NCC, and their zero-meaned versions. The NCC and the zero meaned SAD and SSD were found to produce the disparity maps with the highest proportion of valid matches. The plain SAD and SSD were the least computationally expensive, due to all their operations taking place in integer arithmetic, however, they were extremely sensitive to radiometric distortion. Non-parametric techniques for matching, in particular, the rank and the census transform, have also been investigated. The rank and census transforms were found to be robust with respect to radiometric distortion, as well as being able to produce disparity maps with a high proportion of valid matches. An additional advantage of both the rank and the census transform is their amenability to fast hardware implementation.

A generic implementation framework for stereo matching algorithms

Traditional area-based matching techniques make use of similarity metrics such as the Sum of Absolute Differences(SAD), Sum of Squared Differences (SSD) and Normalised Cross Correlation (NCC). Non-parametric matching algorithms such as the rank and census rely on the relative ordering of pixel values rather than the pixels themselves as a similarity measure. Both traditional area-based and non-parametric stereo matching techniques have an algorithmic structure which is amenable to fast hardware realisation. This investigation undertakes a performance assessment of these two families of algorithms for robustness to radiometric distortion and random noise. A generic implementation framework is presented for the stereo matching problem and the relative hardware requirements for the various metrics investigated.

Suitability of non-parametric stereo matching algorithms for mining automation

The mining environment, being complex, irregular and time varying, presents a challenging prospect for stereo vision. For this application, speed, reliability, and the ability to produce a dense depth map are of foremost importance. This paper assesses the suitability of a number of matching techniques for use in a stereo vision sensor for close range scenes consisting primarily of rocks. These include traditional area-based matching metrics, and non-parametric transforms, in particular, the rank and census transforms. Experimental results show that the rank and census transforms exhibit a number of clear advantages over area-based matching metrics, including their low computational complexity, and robustness to certain types of distortion.

Fast and robust stereo matching algorithms for mining automation

The mining environment, being complex, irregular and time varying, presents a challenging prospect for stereo vision. For this application, speed, reliability, and the ability to produce a dense depth map are of foremost importance. This paper evaluates a number of matching techniques for possible use in a stereo vision sensor for mining automation applications. Area-based techniques have been investigated because they have the potential to yield dense maps, are amenable to fast hardware implementation, and are suited to textured scenes. In addition, two non-parametric transforms, namely, the rank and census, have been investigated. Matching algorithms using these transforms were found to have a number of clear advantages, including reliability in the presence of radiometric distortion, low computational complexity, and amenability to hardware implementation.

Hybrid game evolutionary algorithm for mission path planning of aerial survey tasks

The aim of this paper is to implement a Game-Theory based offline mission path planner for aerial inspection tasks of large linear infrastructures. Like most real-world optimisation problems, mission path planning involves a number of objectives which ideally should be minimised simultaneously. The goal of this work is then to develop a Multi-Objective (MO) optimisation tool able to provide a set of optimal solutions for the inspection task, given the environment data, the mission requirements and the definition of the objectives to minimise. Results indicate the robustness and capability of the method to find the trade-off between the Pareto-optimal solutions.

An evolutionary computation approach to three-dimensional path planning for unmanned aerial vehicles with tactical and kinematic constraints

This paper presents a novel evolutionary computation approach to three-dimensional path planning for unmanned aerial vehicles (UAVs) with tactical and kinematic constraints. A genetic algorithm (GA) is modified and extended for path planning. Two GAs are seeded at the initial and final positions with a common objective to minimise their distance apart under given UAV constraints. This is accomplished by the synchronous optimisation of subsequent control vectors. The proposed evolutionary computation approach is called synchronous genetic algorithm (SGA). The sequence of control vectors generated by the SGA constitutes to a near-optimal path plan. The resulting path plan exhibits no discontinuity when transitioning from curve to straight trajectories. Experiments and results show that the paths generated by the SGA are within 2% of the optimal solution. Such a path planner when implemented on a hardware accelerator, such as field programmable gate array chips, can be used in the UAV as on-board replanner, as well as in ground station systems for assisting in high precision planning and modelling of mission scenarios.

Bayesian algorithms with applications

Advances in algorithms for approximate sampling from a multivariable target function have led to solutions to challenging statistical inference problems that would otherwise not be considered by the applied scientist. Such sampling algorithms are particularly relevant to Bayesian statistics, since the target function is the posterior distribution of the unobservables given the observables. In this thesis we develop, adapt and apply Bayesian algorithms, whilst addressing substantive applied problems in biology and medicine as well as other applications. For an increasing number of high-impact research problems, the primary models of interest are often sufficiently complex that the likelihood function is computationally intractable. Rather than discard these models in favour of inferior alternatives, a class of Bayesian "likelihoodfree" techniques (often termed approximate Bayesian computation (ABC)) has emerged in the last few years, which avoids direct likelihood computation through repeated sampling of data from the model and comparing observed and simulated summary statistics. In Part I of this thesis we utilise sequential Monte Carlo (SMC) methodology to develop new algorithms for ABC that are more efficient in terms of the number of model simulations required and are almost black-box since very little algorithmic tuning is required. In addition, we address the issue of deriving appropriate summary statistics to use within ABC via a goodness-of-fit statistic and indirect inference. Another important problem in statistics is the design of experiments. That is, how one should select the values of the controllable variables in order to achieve some design goal. The presences of parameter and/or model uncertainty are computational obstacles when designing experiments but can lead to inefficient designs if not accounted for correctly. The Bayesian framework accommodates such uncertainties in a coherent way. If the amount of uncertainty is substantial, it can be of interest to perform adaptive designs in order to accrue information to make better decisions about future design points. This is of particular interest if the data can be collected sequentially. In a sense, the current posterior distribution becomes the new prior distribution for the next design decision. Part II of this thesis creates new algorithms for Bayesian sequential design to accommodate parameter and model uncertainty using SMC. The algorithms are substantially faster than previous approaches allowing the simulation properties of various design utilities to be investigated in a more timely manner. Furthermore the approach offers convenient estimation of Bayesian utilities and other quantities that are particularly relevant in the presence of model uncertainty. Finally, Part III of this thesis tackles a substantive medical problem. A neurological disorder known as motor neuron disease (MND) progressively causes motor neurons to no longer have the ability to innervate the muscle fibres, causing the muscles to eventually waste away. When this occurs the motor unit effectively ‘dies’. There is no cure for MND, and fatality often results from a lack of muscle strength to breathe. The prognosis for many forms of MND (particularly amyotrophic lateral sclerosis (ALS)) is particularly poor, with patients usually only surviving a small number of years after the initial onset of disease. Measuring the progress of diseases of the motor units, such as ALS, is a challenge for clinical neurologists. Motor unit number estimation (MUNE) is an attempt to directly assess underlying motor unit loss rather than indirect techniques such as muscle strength assessment, which generally is unable to detect progressions due to the body’s natural attempts at compensation. Part III of this thesis builds upon a previous Bayesian technique, which develops a sophisticated statistical model that takes into account physiological information about motor unit activation and various sources of uncertainties. More specifically, we develop a more reliable MUNE method by applying marginalisation over latent variables in order to improve the performance of a previously developed reversible jump Markov chain Monte Carlo sampler. We make other subtle changes to the model and algorithm to improve the robustness of the approach.

Detecting conversing groups of chatters : a model, algorithms, and tests

Chatrooms, for example Internet Relay Chat, are generally multi-user, multi-channel and multiserver chat-systems which run over the Internet and provide a protocol for real-time text-based conferencing between users all over the world. While a well-trained human observer is able to understand who is chatting with whom, there are no efficient and accurate automated tools to determine the groups of users conversing with each other. A precursor to analysing evolving cyber-social phenomena is to first determine what the conversations are and which groups of chatters are involved in each conversation. We consider this problem in this paper. We propose an algorithm to discover all groups of users that are engaged in conversation. Our algorithms are based on a statistical model of a chatroom that is founded on our experience with real chatrooms. Our approach does not require any semantic analysis of the conversations, rather it is based purely on the statistical information contained in the sequence of posts. We improve the accuracy by applying some graph algorithms to clean the statistical information. We present some experimental results which indicate that one can automatically determine the conversing groups in a chatroom, purely on the basis of statistical analysis.

Adaptive dynamic path re-planning RRT algorithms with game theory for UAVs

The main aim of this paper is to describe an adaptive re-planning algorithm based on a RRT and Game Theory to produce an efficient collision free obstacle adaptive Mission Path Planner for Search and Rescue (SAR) missions. This will provide UAV autopilots and flight computers with the capability to autonomously avoid static obstacles and No Fly Zones (NFZs) through dynamic adaptive path replanning. The methods and algorithms produce optimal collision free paths and can be integrated on a decision aid tool and UAV autopilots.

Four new avian mitochondrial genomes help get to basic evolutionary questions in the late cretaceous

Good phylogenetic trees are required to test hypotheses about evolutionary processes. We report four new avian mitochondrial genomes, which together with an improved method of phylogenetic analysis for vertebrate mt genomes give results for three questions in avian evolution. The new mt genomes are: magpie goose (Anseranas semipalmata), an owl (morepork, Ninox novaeseelandiae); a basal passerine (rifleman, or New Zealand wren, Acanthisitta chloris); and a parrot (kakapo or owl-parrot, Strigops habroptilus). The magpie goose provides an important new calibration point for avian evolution because the well-studied Presbyornis fossils are on the lineage to ducks and geese, after the separation of the magpie goose. We find, as with other animal mitochondrial genomes, that RY-coding is helpful in adjusting for biases between pyrimidines and between purines. When RY-coding is used at third positions of the codon, the root occurs between paleognath and neognath birds (as expected from morphological and nuclear data). In addition, passerines form a relatively old group in Neoaves, and many modern avian lineages diverged during the Cretaceous. Although many aspects of the avian tree are stable, additional taxon sampling is required.

Cryptic diversity and evolutionary relationships among Australian closed-forest Melomys (Rodentia: Muridae) and related Australo-Papuan mosaic-tailed rats

This thesis investigates patterns of evolution in a group of native Australo-Papuan rodents. Past climatic change and associated sea level fluctuations, and fragmentation of wet forests in eastern Australia has facilitated rapid radiation, diversification and speciation in this group. This study adds to our understanding of the evolution of Australia’s rainforest fauna and describes the evolutionary relationships of a new genus of Australian rodent.

Evolutionary genetics and human assisted movement of a globally invasive pest (Russian wheat aphid : Diuraphis noxia)

This PhD study has examined the population genetics of the Russian wheat aphid (RWA, Diuraphis noxia), one of the world’s most invasive agricultural pests, throughout its native and introduced global range. Firstly, this study investigated the geographic distribution of genetic diversity within and among RWA populations in western China. Analysis of mitochondrial data from 18 sites provided evidence for the long-term existence and expansion of RWAs in western China. The results refute the hypothesis that RWA is an exotic species only present in China since 1975. The estimated date of RWA expansion throughout western China coincides with the debut of wheat domestication and cultivation practices in western Asia in the Holocene. It is concluded that western China represents the limit of the far eastern native range of this species. Analysis of microsatellite data indicated high contemporary gene flow among northern populations in western China, while clear geographic isolation between northern and southern populations was identified across the Tianshan mountain range and extensive desert regions. Secondly, this study analyzed the worldwide pathway of invasion using both microsatellite and endosymbiont genetic data. Individual RWAs were obtained from native populations in Central Asia and the Middle East and invasive populations in Africa and the Americas. Results indicated two pathways of RWA invasion from 1) Syria in the Middle East to North Africa and 2) Turkey to South Africa, Mexico and then North and South America. Very little clone diversity was identified among invasive populations suggesting that a limited founder event occurred together with predominantly asexual reproduction and rapid population expansion. The most likely explanation for the rapid spread (within two years) from South Africa to the New World is by human movement, probably as a result of the transfer of wheat breeding material. Furthermore, the mitochondrial data revealed the presence of a universal haplotype and it is proposed that this haplotype is representative of a wheat associated super-clone that has gained dominance worldwide as a result of the widespread planting of domesticated wheat. Finally, this study examined salivary gland gene diversity to determine whether a functional basis for RWA invasiveness could be identified. Peroxidase DNA sequence data were obtained for a selection of worldwide RWA samples. Results demonstrated that most native populations were polymorphic while invasive populations were monomorphic, supporting previous conclusions relating to demographic founder effects in invasive populations. Purifying selection most likely explains the existence of a universal allele present in Middle Eastern populations, while balancing selection was evident in East Asian populations. Selection acting on the peroxidase gene may provide an allele-dependent advantage linked to the successful establishment of RWAs on wheat, and ultimately their invasion potential. In conclusion, this study is the most comprehensive molecular genetic investigation of RWA population genetics undertaken to date and provides significant insights into the source and pathway of global invasion and the potential existence of a wheat-adapted genotype that has colonised major wheat growing countries worldwide except for Australia. This research has major biosecurity implications for Australia’s grain industry.

Pseudo-marginal algorithms with multiple CPUs

The emergence of pseudo-marginal algorithms has led to improved computational efficiency for dealing with complex Bayesian models with latent variables. Here an unbiased estimator of the likelihood replaces the true likelihood in order to produce a Bayesian algorithm that remains on the marginal space of the model parameter (with latent variables integrated out), with a target distribution that is still the correct posterior distribution. Very efficient proposal distributions can be developed on the marginal space relative to the joint space of model parameter and latent variables. Thus psuedo-marginal algorithms tend to have substantially better mixing properties. However, for pseudo-marginal approaches to perform well, the likelihood has to be estimated rather precisely. This can be difficult to achieve in complex applications. In this paper we propose to take advantage of multiple central processing units (CPUs), that are readily available on most standard desktop computers. Here the likelihood is estimated independently on the multiple CPUs, with the ultimate estimate of the likelihood being the average of the estimates obtained from the multiple CPUs. The estimate remains unbiased, but the variability is reduced. We compare and contrast two different technologies that allow the implementation of this idea, both of which require a negligible amount of extra programming effort. The superior performance of this idea over the standard approach is demonstrated on simulated data from a stochastic volatility model.

Dynamic robot path planning using an enhanced simulated annealing approach

Evolutionary computation is an effective tool for solving optimization problems. However, its significant computational demand has limited its real-time and on-line applications, especially in embedded systems with limited computing resources, e.g., mobile robots. Heuristic methods such as the genetic algorithm (GA) based approaches have been investigated for robot path planning in dynamic environments. However, research on the simulated annealing (SA) algorithm, another popular evolutionary computation algorithm, for dynamic path planning is still limited mainly due to its high computational demand. An enhanced SA approach, which integrates two additional mathematical operators and initial path selection heuristics into the standard SA, is developed in this work for robot path planning in dynamic environments with both static and dynamic obstacles. It improves the computing performance of the standard SA significantly while giving an optimal or near-optimal robot path solution, making its real-time and on-line applications possible. Using the classic and deterministic Dijkstra algorithm as a benchmark, comprehensive case studies are carried out to demonstrate the performance of the enhanced SA and other SA algorithms in various dynamic path planning scenarios.

The linking of plate tectonics and evolutionary divergence

It is exciting to be living at a time when the big questions in biology can be investigated using modern genetics and computing [1]. Bauzà-Ribot et al.[2] take on one of the fundamental drivers of biodiversity, the effect of continental drift in the formation of the world’s biota 3 and 4, employing next-generation sequencing of whole mitochondrial genomes and modern Bayesian relaxed molecular clock analysis. Bauzà-Ribot et al.[2] conclude that vicariance via plate tectonics best explains the genetic divergence between subterranean metacrangonyctid amphipods currently found on islands separated by the Atlantic Ocean. This finding is a big deal in biogeography, and science generally [3], as many other presumed biotic tectonic divergences have been explained as probably due to more recent transoceanic dispersal events [4]. However, molecular clocks can be problematic 5 and 6 and we have identified three issues with the analyses of Bauzà-Ribot et al.[2] that cast serious doubt on their results and conclusions. When we reanalyzed their mitochondrial data and attempted to account for problems with calibration 5 and 6, modeling rates across branches 5 and 7 and substitution saturation [5], we inferred a much younger date for their key node. This implies either a later trans-Atlantic dispersal of these crustaceans, or more likely a series of later invasions of freshwaters from a common marine ancestor, but either way probably not ancient tectonic plate movements.