Stephen Marsland

Stephen Marsland, Tony Shardlow

Registration of images parameterised by landmarks provides a useful method of describing shape variations by computing the minimum-energy time-dependent deformation field that flows one landmark set to the other. This is sometimes known as the geodesic interpolating spline and can be solved via a Hamiltonian boundary-value problem to give a diffeomorphic registration between images. However, small changes in the positions of the landmarks can produce large changes in the resulting diffeomorphism. We formulate a Langevin equation for looking at small random perturbations of this registration. The Langevin equation and three computationally convenient approximations are introduced and used as prior distributions. A Bayesian framework is then used to compute a posterior distribution for the registration, and also to formulate an average of multiple sets of landmarks.

Stephen R Marsland, Robert I McLachlan, Matthew C Wilkins

We study a class of general purpose linear multisymplectic integrators for Hamiltonian wave equations based on a diamond-shaped mesh. On each diamond, the PDE is discretized by a symplectic Runge--Kutta method. The scheme advances in time by filling in each diamond locally. We demonstrate that this leads to greater efficiency and parallelization and easier treatment of boundary conditions compared to methods based on rectangular meshes. We develop a variety of initial and boundary value treatments and present numerical evidence of their performance. In all cases, the observed order of convergence is equal to or greater than the number of stages of the underlying Runge--Kutta method.

Julius Juodakis, Stephen Marsland

Sound recordings are used in various ecological studies, including acoustic wildlife monitoring. Such surveys require automatic detection of target sound events. However, current detectors, especially those relying on band-limited energy, are severely impacted by wind. The rapid dynamics of this noise invalidate standard noise estimators, and no satisfactory method for dealing with it exists in bioacoustics, where simple training and generalization between conditions are important. We propose to estimate the transient noise level by fitting short-term spectrum models to a wavelet packet representation. This estimator is then combined with log-spectral subtraction to stabilize the background level. The resulting adjusted wavelet series can be analysed by standard energy detectors. We use real monitoring data to tune this workflow, and test it on two acoustic surveys of birds. Additionally, we show how the estimator can be incorporated in a denoising method to restore sound. The proposed noise-robust workflow greatly reduced the number of false alarms in the surveys, compared to unadjusted energy detection. As a result, the survey efficiency (precision of the estimated call density) improved for both species. Denoising was also more effective when using the short-term estimate, whereas standard wavelet shrinkage with a constant noise estimate struggled to remove the effects of wind. In contrast to existing methods, the proposed estimator can adjust for transient broadband noises without requiring additional hardware or extensive tuning to each species. It improved the detection workflow based on very little training data, making it particularly attractive for detection of rare species.

Aram Ter-Sarkisov, Stephen Marsland

There has been a variety of crossover operators proposed for Real-Coded Genetic Algorithms (RCGAs), which recombine values from the same location in pairs of strings. In this article we present a recombination operator for RC- GAs that selects the locations randomly in both parents, and compare it to mainstream crossover operators in a set of experiments on a range of standard multidimensional optimization problems and a clustering problem. We present two variants of the operator, either selecting both bits uniformly at random in the strings, or sampling the second bit from a normal distribution centered at the selected location in the first string. While the operator is biased towards exploitation of fitness space, the random selection of the second bit for swap- ping makes it slightly less exploitation-biased. Extensive statistical analysis using a non-parametric test shows the advantage of the new recombination operators on a range of test functions.

Stephen Marsland, Robert McLachlan

Identifying when different images are of the same object despite changes caused by imaging technologies, or processes such as growth, has many applications in fields such as computer vision and biological image analysis. One approach to this problem is to identify the group of possible transformations of the object and to find invariants to the action of that group, meaning that the object has the same values of the invariants despite the action of the group. In this paper we study the invariants of planar shapes and images under the Möbius group $\mathrm{PSL}(2,\mathbb{C})$, which arises in the conformal camera model of vision and may also correspond to neurological aspects of vision, such as grouping of lines and circles. We survey properties of invariants that are important in applications, and the known Möbius invariants, and then develop an algorithm by which shapes can be recognised that is Möbius- and reparametrization-invariant, numerically stable, and robust to noise. We demonstrate the efficacy of this new invariant approach on sets of curves, and then develop a Möbius-invariant signature of grey-scale images.

Stephen Marsland, Carole J Twining

The statistical analysis of data lying on a differentiable, locally Euclidean, manifold introduces a variety of challenges because the analogous measures to standard Euclidean statistics are local, that is only defined within a neighbourhood of each datapoint. This is because the curvature of the space means that the connection of Riemannian geometry is path dependent. In this paper we transfer the problem to Weitzenböck space, which has torsion, but not curvature, meaning that parallel transport is path independent, and rather than considering geodesics, it is natural to consider autoparallels, which are `straight' in the sense that they follow the local basis vectors. We demonstrate how to generate these autoparallels in a data-driven fashion, and show that the resulting representation of the data is a useful space in which to perform further analysis.

Aram Ter-Sarkisov, Stephen Marsland

In this article a tool for the analysis of population-based EAs is used to derive asymptotic upper bounds on the optimization time of the algorithm solving Royal Roads problem, a test function with plateaus of fitness. In addition to this, limiting distribution of a certain subset of the population is approximated.