Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Does DE need a C? A proposal for a DE curriculum

The vision of a digital earth (DE) is continuously evolving, and the next-generation infrastructures, platforms and applications are being implemented. In this article, we attempt to initiate a debate within the DE and with affine communities about 'why' a digital earth curriculum (DEC) is needed, 'how' it should be developed, and 'what' it could look like. It is impossible to do justice to the Herculean effort of DEC development without extensive consultations with the broader community. We propose a frame for the debate (what, why, and how of a DEC) and a rationale for and elements of a curriculum for educating the coming generations of digital natives and indicate possible realizations. We particularly argue that a DEC is not a déjà vu of classical research and training agendas of geographic information science, remote sensing, and similar fields by emphasizing its unique characteristics.

Pore accessibility by methane and carbon dioxide in coal as determined by neutron scattering

Contrast-matching ultrasmall-angle neutron scattering (USANS) and small-angle neutron scattering (SANS) techniques were used for the first time to determine both the total pore volume and the fraction of the pore volume that is inaccessible to deuterated methane, CD4, in four bituminous coals in the range of pore sizes between ∼10 Å and ∼5 μm. Two samples originated from the Illinois Basin in the U.S.A., and the other two samples were commercial Australian bituminous coals from the Bowen Basin. The total and inaccessible porosity were determined in each coal using both Porod invariant and the polydisperse spherical particle (PDSP) model analysis of the scattering data acquired from coals both in vacuum and at the pressure of CD4, at which the scattering length density of the pore-saturating fluid is equal to that of the solid coal matrix (zero average contrast pressure). The total porosity of the coals studied ranged from 7 to 13%, and the volume of pores inaccessible to CD4 varied from ∼13 to ∼36% of the total pore volume. The volume fraction of inaccessible pores shows no correlation with the maceral composition; however, it increases with a decreasing total pore volume. In situ measurements of the structure of one coal saturated with CO2 and CD4 were conducted as a function of the pressure in the range of 1−400 bar. The neutron scattering intensity from small pores with radii less than 35 Å in this coal increased sharply immediately after the fluid injection for both gases, which demonstrates strong condensation and densification of the invading subcritical CO2 and supercritical methane in small pores.

Practical aspects of frequency-domain identification of dynamic models of marine structures from hydrodynamic data

The motion response of marine structures in waves can be studied using finite-dimensional linear-time-invariant approximating models. These models, obtained using system identification with data computed by hydrodynamic codes, find application in offshore training simulators, hardware-in-the-loop simulators for positioning control testing, and also in initial designs of wave-energy conversion devices. Different proposals have appeared in the literature to address the identification problem in both time and frequency domains, and recent work has highlighted the superiority of the frequency-domain methods. This paper summarises practical frequency-domain estimation algorithms that use constraints on model structure and parameters to refine the search of approximating parametric models. Practical issues associated with the identification are discussed, including the influence of radiation model accuracy in force-to-motion models, which are usually the ultimate modelling objective. The illustration examples in the paper are obtained using a freely available MATLAB toolbox developed by the authors, which implements the estimation algorithms described.

Object tracking via non-Euclidean geometry : a Grassmann approach

A robust visual tracking system requires an object appearance model that is able to handle occlusion, pose, and illumination variations in the video stream. This can be difficult to accomplish when the model is trained using only a single image. In this paper, we first propose a tracking approach based on affine subspaces (constructed from several images) which are able to accommodate the abovementioned variations. We use affine subspaces not only to represent the object, but also the candidate areas that the object may occupy. We furthermore propose a novel approach to measure affine subspace-to-subspace distance via the use of non-Euclidean geometry of Grassmann manifolds. The tracking problem is then considered as an inference task in a Markov Chain Monte Carlo framework via particle filtering. Quantitative evaluation on challenging video sequences indicates that the proposed approach obtains considerably better performance than several recent state-of-the-art methods such as Tracking-Learning-Detection and MILtrack.

Matching image sets via adaptive multi convex hull

Traditional nearest points methods use all the samples in an image set to construct a single convex or affine hull model for classification. However, strong artificial features and noisy data may be generated from combinations of training samples when significant intra-class variations and/or noise occur in the image set. Existing multi-model approaches extract local models by clustering each image set individually only once, with fixed clusters used for matching with various image sets. This may not be optimal for discrimination, as undesirable environmental conditions (eg. illumination and pose variations) may result in the two closest clusters representing different characteristics of an object (eg. frontal face being compared to non-frontal face). To address the above problem, we propose a novel approach to enhance nearest points based methods by integrating affine/convex hull classification with an adapted multi-model approach. We first extract multiple local convex hulls from a query image set via maximum margin clustering to diminish the artificial variations and constrain the noise in local convex hulls. We then propose adaptive reference clustering (ARC) to constrain the clustering of each gallery image set by forcing the clusters to have resemblance to the clusters in the query image set. By applying ARC, noisy clusters in the query set can be discarded. Experiments on Honda, MoBo and ETH-80 datasets show that the proposed method outperforms single model approaches and other recent techniques, such as Sparse Approximated Nearest Points, Mutual Subspace Method and Manifold Discriminant Analysis.

Dictionary learning and sparse coding on Grassmann manifolds : an extrinsic solution

Recent advances in computer vision and machine learning suggest that a wide range of problems can be addressed more appropriately by considering non-Euclidean geometry. In this paper we explore sparse dictionary learning over the space of linear subspaces, which form Riemannian structures known as Grassmann manifolds. To this end, we propose to embed Grassmann manifolds into the space of symmetric matrices by an isometric mapping, which enables us to devise a closed-form solution for updating a Grassmann dictionary, atom by atom. Furthermore, to handle non-linearity in data, we propose a kernelised version of the dictionary learning algorithm. Experiments on several classification tasks (face recognition, action recognition, dynamic texture classification) show that the proposed approach achieves considerable improvements in discrimination accuracy, in comparison to state-of-the-art methods such as kernelised Affine Hull Method and graph-embedding Grassmann discriminant analysis.

Improved image set classification via joint sparse approximated nearest subspaces

Existing multi-model approaches for image set classification extract local models by clustering each image set individually only once, with fixed clusters used for matching with other image sets. However, this may result in the two closest clusters to represent different characteristics of an object, due to different undesirable environmental conditions (such as variations in illumination and pose). To address this problem, we propose to constrain the clustering of each query image set by forcing the clusters to have resemblance to the clusters in the gallery image sets. We first define a Frobenius norm distance between subspaces over Grassmann manifolds based on reconstruction error. We then extract local linear subspaces from a gallery image set via sparse representation. For each local linear subspace, we adaptively construct the corresponding closest subspace from the samples of a probe image set by joint sparse representation. We show that by minimising the sparse representation reconstruction error, we approach the nearest point on a Grassmann manifold. Experiments on Honda, ETH-80 and Cambridge-Gesture datasets show that the proposed method consistently outperforms several other recent techniques, such as Affine Hull based Image Set Distance (AHISD), Sparse Approximated Nearest Points (SANP) and Manifold Discriminant Analysis (MDA).

Characterisation of the micro-architecture of direct writing melt electrospun tissue engineering scaffolds using diffusion tensor and computed tomography microimaging

This article describes the first steps toward comprehensive characterization of molecular transport within scaffolds for tissue engineering. The scaffolds were fabricated using a novel melt electrospinning technique capable of constructing 3D lattices of layered polymer fibers with well - defined internal microarchitectures. The general morphology and structure order was then determined using T 2 - weighted magnetic resonance imaging and X - ray microcomputed tomography. Diffusion tensor microimaging was used to measure the time - dependent diffusivity and diffusion anisotropy within the scaffolds. The measured diffusion tensors were anisotropic and consistent with the cross - hatched geometry of the scaffolds: diffusion was least restricted in the direction perpendicular to the fiber layers. The results demonstrate that the cross - hatched scaffold structure preferentially promotes molecular transport vertically through the layers ( z - axis), with more restricted diffusion in the directions of the fiber layers ( x – y plane). Diffusivity in the x – y plane was observed to be invariant to the fiber thickness. The characteristic pore size of the fiber scaffolds can be probed by sampling the diffusion tensor at multiple diffusion times. Prospective application of diffusion tensor imaging for the real - time monitoring of tissue maturation and nutrient transport pathways within tissue engineering scaffolds is discussed.

Follow the leader if you can, hedge if you must

Follow-the-Leader (FTL) is an intuitive sequential prediction strategy that guarantees constant regret in the stochastic setting, but has poor performance for worst-case data. Other hedging strategies have better worst-case guarantees but may perform much worse than FTL if the data are not maximally adversarial. We introduce the FlipFlop algorithm, which is the first method that provably combines the best of both worlds. As a stepping stone for our analysis, we develop AdaHedge, which is a new way of dynamically tuning the learning rate in Hedge without using the doubling trick. AdaHedge refines a method by Cesa-Bianchi, Mansour, and Stoltz (2007), yielding improved worst-case guarantees. By interleaving AdaHedge and FTL, FlipFlop achieves regret within a constant factor of the FTL regret, without sacrificing AdaHedge’s worst-case guarantees. AdaHedge and FlipFlop do not need to know the range of the losses in advance; moreover, unlike earlier methods, both have the intuitive property that the issued weights are invariant under rescaling and translation of the losses. The losses are also allowed to be negative, in which case they may be interpreted as gains.

The eight variable homogeneous degree three bent functions

We determine the affine equivalence classes of the eight variable degree three homogeneous bent functions using a new algorithm. Our algorithm applies to general bent functions and can systematically determine the automorphism groups. We provide a partial verification of the enumeration of eight variable degree three homogeneous bent functions obtained by Meng et al. We determine the affine equivalence classes of these functions.

kmth price sealed-bid auctions with general independent values and equilibrium linear mark-ups

A generalised bidding model is developed to calculate a bidder’s expected profit and auctioners expected revenue/payment for both a General Independent Value and Independent Private Value (IPV) kmth price sealed-bid auction (where the mth bidder wins at the kth bid payment) using a linear (affine) mark-up function. The Common Value (CV) assumption, and highbid and lowbid symmetric and asymmetric First Price Auctions and Second Price Auctions are included as special cases. The optimal n bidder symmetric analytical results are then provided for the uniform IPV and CV models in equilibrium. Final comments concern implications, the assumptions involved and prospects for further research.

Improved fabrication of melt electrospun tissue engineering scaffolds using direct writing and advanced electric field control

Direct writing melt electrospinning is an additive manufacturing technique capable of the layer-by-layer fabrication of highly ordered 3d tissue engineering scaffolds from micron-diameter fibres. The utility of these scaffolds, however, is limited by the maximum achievable height of controlled fibre deposition, beyond which the structure becomes increasingly disordered. A source of this disorder is charge build-up on the deposited polymer producing unwanted coulombic forces. In this study we introduce a novel melt electrospinning platform with dual voltage power supplies to reduce undesirable charge effects and improve fibre deposition control. We produced and characterised several 90° cross-hatched fibre scaffolds using a range of needle/collector plate voltages. Fibre thickness was found to be sensitive only to overall potential and invariant to specific tip/collector voltage. We also produced ordered scaffolds up to 200 layers thick (fibre spacing 1 mm, diameter 40 μm) and characterised structure in terms of three distinct zones; ordered, semi-ordered and disordered. Our in vitro analysis indicates successful cell attachment and distribution throughout the scaffolds, with little evidence of cell death after seven days. This study demonstrates the importance of electrostatic control for reducing destabilising polymer charge effects and enabling the fabrication of morphologically suitable scaffolds for tissue engineering.

Automated sensory data alignment for environmental and epidermal change monitoring

In this paper we present research adapting a state of the art condition-invariant robotic place recognition algorithm to the role of automated inter- and intra-image alignment of sensor observations of environmental and skin change over time. The approach involves inverting the typical criteria placed upon navigation algorithms in robotics; we exploit rather than attempt to fix the limited camera viewpoint invariance of such algorithms, showing that approximate viewpoint repetition is realistic in a wide range of environments and medical applications. We demonstrate the algorithms automatically aligning challenging visual data from a range of real-world applications: ecological monitoring of environmental change, aerial observation of natural disasters including flooding, tsunamis and bushfires and tracking wound recovery and sun damage over time and present a prototype active guidance system for enforcing viewpoint repetition. We hope to provide an interesting case study for how traditional research criteria in robotics can be inverted to provide useful outcomes in applied situations.

Scale adaptive tracking using mean shift and efficient feature matching

The mean shift tracker has achieved great success in visual object tracking due to its efficiency being nonparametric. However, it is still difficult for the tracker to handle scale changes of the object. In this paper, we associate a scale adaptive approach with the mean shift tracker. Firstly, the target in the current frame is located by the mean shift tracker. Then, a feature point matching procedure is employed to get the matched pairs of the feature point between target regions in the current frame and the previous frame. We employ FAST-9 corner detector and HOG descriptor for the feature matching. Finally, with the acquired matched pairs of the feature point, the affine transformation between target regions in the two frames is solved to obtain the current scale of the target. Experimental results show that the proposed tracker gives satisfying results when the scale of the target changes, with a good performance of efficiency.