Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Towards robust night and day place recognition using visible and thermal imaging

The chief challenge facing persistent robotic navigation using vision sensors is the recognition of previously visited locations under different lighting and illumination conditions. The majority of successful approaches to outdoor robot navigation use active sensors such as LIDAR, but the associated weight and power draw of these systems makes them unsuitable for widespread deployment on mobile robots. In this paper we investigate methods to combine representations for visible and long-wave infrared (LWIR) thermal images with time information to combat the time-of-day-based limitations of each sensing modality. We calculate appearance-based match likelihoods using the state-of-the-art FAB-MAP [1] algorithm to analyse loop closure detection reliability across different times of day. We present preliminary results on a dataset of 10 successive traverses of a combined urban-parkland environment, recorded in 2-hour intervals from before dawn to after dusk. Improved location recognition throughout an entire day is demonstrated using the combined system compared with methods which use visible or thermal sensing alone.

A mitochondrial genome phylogeny of termites (Blattodea: Termitoidae) : robust support for interfamilial relationships and molecular synapomorphies define major clades

Despite their ecological significance as decomposers and their evolutionary significance as the most speciose eusocial insect group outside the Hymenoptera, termite (Blattodea: Termitoidae or Isoptera) evolutionary relationships have yet to be well resolved. Previous morphological and molecular analyses strongly conflict at the family level and are marked by poor support for backbone nodes. A mitochondrial (mt) genome phylogeny of termites was produced to test relationships between the recognised termite families, improve nodal support and test the phylogenetic utility of rare genomic changes found in the termite mt genome. Complete mt genomes were sequenced for 7 of the 9 extant termite families with additional representatives of each of the two most speciose families Rhinotermitidae (3 of 7 subfamilies) and Termitidae (3 of 8 subfamilies). The mt genome of the well supported sister group of termites, the subsocial cockroach Cryptocercus, was also sequenced. A highly supported tree of termite relationships was produced by all analytical methods and data treatment approaches, however the relationship of the termites + Cryptocercus clade to other cockroach lineages was highly affected by the strong nucleotide compositional bias found in termites relative to other dictyopterans. The phylogeny supports previously proposed suprafamilial termite lineages, the Euisoptera and Neoisoptera, a later derived Kalotermitidae as sister group of the Neoisoptera and a monophyletic clade of dampwood (Stolotermitidae, Archotermopsidae) and harvester termites (Hodotermitidae). In contrast to previous termite phylogenetic studies, nodal supports were very high for family-level relationships within termites. Two rare genomic changes in the mt genome control region were found to be molecular synapomorphies for major clades. An elongated stem-loop structure defined the clade Polyphagidae + (Cryptocercus + termites), and a further series of compensatory base changes in this stem loop is synapomorphic for the Neoisoptera. The complicated repeat structures first identified in Reticulitermes, composed of short (A-type) and long (B-type repeats) defines the clade Heterotermitinae + Termitidae, while the secondary loss of A-type repeats is synapomorphic for the non-macrotermitine Termitidae.

The iatrogenic reflex and belief that repression can coercively suppress asymmetric coercive violence : does very robust action by the government decrease functional support for insurgents?

Non-state insurgent actors are too weak to compel powerful adversaries to their will, so they use violence to coerce. A principal objective is to grow and sustain violent resistance to the point that it either militarily challenges the state, or more commonly, generates unacceptable political costs. To survive, insurgents must shift popular support away from the state and to grow they must secure it. State actor policies and actions perceived as illegitimate and oppressive by the insurgent constituency can generate these shifts. A promising insurgent strategy is to attack states in ways that lead angry publics and leaders to discount the historically established risks and take flawed but popular decisions to use repressive measures. Such decisions may be enabled by a visceral belief in the power of coercion and selective use of examples of where robust measures have indeed suppressed resistance. To avoid such counterproductive behaviours the cases of apparent 'successful repression' must be understood. This thesis tests whether robust state action is correlated with reduced support for insurgents, analyses the causal mechanisms of such shifts and examines whether such reduction is because of compulsion or coercion? The approach is founded on prior research by the RAND Corporation which analysed the 30 insurgencies most recently resolved worldwide to determine factors of counterinsurgent success. This new study first re-analyses their data at a finer resolution with new queries that investigate the relationship between repression and insurgent active support. Having determined that, in general, repression does not correlate with decreased insurgent support, this study then analyses two cases in which the data suggests repression seems likely to be reducing insurgent support: the PKK in Turkey and the insurgency against the Vietnamese-sponsored regime after their ousting of the Khmer Rouge. It applies 'structured-focused' case analysis with questions partly built from the insurgency model of Leites and Wolf, who are associated with the advocacy of US robust means in Vietnam. This is thus a test of 'most difficult' cases using a 'least likely' test model. Nevertheless, the findings refute the deterrence argument of 'iron fist' advocates. Robust approaches may physically prevent effective support of insurgents but they do not coercively deter people from being willing to actively support the insurgency.

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 nonparametric transforms, namely, 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.

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.

Non-parametric techniques for fast and robust stereo matching

The mining environment presents a challenging prospect for stereo vision. Our objective is to produce a stereo vision sensor suited to close-range scenes consisting mostly of rocks. This sensor should produce a dense depth map within real-time constraints. Speed and robustness are of foremost importance for this application. This paper compares a number of stereo matching algorithms in terms of robustness and suitability to fast implementation. These include traditional area-based algorithms, and algorithms based on non-parametric transforms, notably the rank and census transforms. Our experimental results show that the rank and census transforms are robust with respect to radiometric distortion and introduce less computational complexity than conventional area-based matching techniques.

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.

Comparison of robust criteria for D-optimal design

This study compared the performance of a local and three robust optimality criteria in terms of the standard error for a one-parameter and a two-parameter nonlinear model with uncertainty in the parameter values. The designs were also compared in conditions where there was misspecification in the prior parameter distribution. The impact of different correlation between parameters on the optimal design was examined in the two-parameter model. The designs and standard errors were solved analytically whenever possible and numerically otherwise.

Prosecutorial guidelines for voluntary euthanasia and assisted suicide : autonomy, public confidence and high quality decision-making

This article proposes offence-specific guidelines for how prosecutorial discretion should be exercised in cases of voluntary euthanasia and assisted suicide. Similar guidelines have been produced in England and Wales but we consider them to be deficient in a number of respects, including that they lack a set of coherent guiding principles. In light of these concerns, we outline an approach to constructing alternative guidelines that begins with identifying three guiding principles that we argue are appropriate for this purpose: respect for autonomy, the need for high quality prosecutorial decision-making and the importance of public confidence in that decision-making.

Deformable face ensemble alignment with robust grouped-L1 anchors

Many methods exist at the moment for deformable face fitting. A drawback to nearly all these approaches is that they are (i) noisy in terms of landmark positions, and (ii) the noise is biased across frames (i.e. the misalignment is toward common directions across all frames). In this paper we propose a grouped $\mathcal{L}1$-norm anchored method for simultaneously aligning an ensemble of deformable face images stemming from the same subject, given noisy heterogeneous landmark estimates. Impressive alignment performance improvement and refinement is obtained using very weak initialization as "anchors".

Vertical infrastructure inspection using a quadcopter and shared autonomy control

This paper presents a shared autonomy control scheme for a quadcopter that is suited for inspection of vertical infrastructure — tall man-made structures such as streetlights, electricity poles or the exterior surfaces of buildings. Current approaches to inspection of such structures is slow, expensive, and potentially hazardous. Low-cost aerial platforms with an ability to hover now have sufficient payload and endurance for this kind of task, but require significant human skill to fly. We develop a control architecture that enables synergy between the ground-based operator and the aerial inspection robot. An unskilled operator is assisted by onboard sensing and partial autonomy to safely fly the robot in close proximity to the structure. The operator uses their domain knowledge and problem solving skills to guide the robot in difficult to reach locations to inspect and assess the condition of the infrastructure. The operator commands the robot in a local task coordinate frame with limited degrees of freedom (DOF). For instance: up/down, left/right, toward/away with respect to the infrastructure. We therefore avoid problems of global mapping and navigation while providing an intuitive interface to the operator. We describe algorithms for pole detection, robot velocity estimation with respect to the pole, and position estimation in 3D space as well as the control algorithms and overall system architecture. We present initial results of shared autonomy of a quadrotor with respect to a vertical pole and robot performance is evaluated by comparing with motion capture data.

On robust face recognition via sparse encoding : the good, the bad, and the ugly

In the field of face recognition, Sparse Representation (SR) has received considerable attention during the past few years. Most of the relevant literature focuses on holistic descriptors in closed-set identification applications. The underlying assumption in SR-based methods is that each class in the gallery has sufficient samples and the query lies on the subspace spanned by the gallery of the same class. Unfortunately, such assumption is easily violated in the more challenging face verification scenario, where an algorithm is required to determine if two faces (where one or both have not been seen before) belong to the same person. In this paper, we first discuss why previous attempts with SR might not be applicable to verification problems. We then propose an alternative approach to face verification via SR. Specifically, we propose to use explicit SR encoding on local image patches rather than the entire face. The obtained sparse signals are pooled via averaging to form multiple region descriptors, which are then concatenated to form an overall face descriptor. Due to the deliberate loss spatial relations within each region (caused by averaging), the resulting descriptor is robust to misalignment & various image deformations. Within the proposed framework, we evaluate several SR encoding techniques: l1-minimisation, Sparse Autoencoder Neural Network (SANN), and an implicit probabilistic technique based on Gaussian Mixture Models. Thorough experiments on AR, FERET, exYaleB, BANCA and ChokePoint datasets show that the proposed local SR approach obtains considerably better and more robust performance than several previous state-of-the-art holistic SR methods, in both verification and closed-set identification problems. The experiments also show that l1-minimisation based encoding has a considerably higher computational than the other techniques, but leads to higher recognition rates.

Designing a new robust on-line secondary path modeling technique for feedforward active noise control systems

Several approaches have been introduced in the literature for active noise control (ANC) systems. Since the filtered-x least-mean-square (FxLMS) algorithm appears to be the best choice as a controller filter, researchers tend to improve performance of ANC systems by enhancing and modifying this algorithm. This paper proposes a new version of the FxLMS algorithm, as a first novelty. In many ANC applications, an on-line secondary path modeling method using white noise as a training signal is required to ensure convergence of the system. As a second novelty, this paper proposes a new approach for on-line secondary path modeling on the basis of a new variable-step-size (VSS) LMS algorithm in feed forward ANC systems. The proposed algorithm is designed so that the noise injection is stopped at the optimum point when the modeling accuracy is sufficient. In this approach, a sudden change in the secondary path during operation makes the algorithm reactivate injection of the white noise to re-adjust the secondary path estimate. Comparative simulation results shown in this paper indicate the effectiveness of the proposed approach in reducing both narrow-band and broad-band noise. In addition, the proposed ANC system is robust against sudden changes of the secondary path model.

Management of heterogeneous UAVs through a capability framework of UAV’s functional autonomy

An increased interest in utilising groups of Unmanned Aerial Vehicles (UAVs) with heterogeneous capabilities and autonomy is presenting the challenge to effectively manage such during missions and operations. This has been the focus of research in recent years, moving from a traditional UAV management paradigm of n-to-1 (n operators for one UAV, with n being at least two operators) toward 1-to-n (one operator, multiple UAVs). This paper has expanded on the authors’ previous work on UAV functional capability framework, by incorporating the concept of Functional Level of Autonomy (F-LOA) with two configurations: The lower F-LOA configuration contains sufficient information for the operator to generate solutions and make decisions to address perturbation events. Alternatively, the higher F-LOA configuration presents information reflecting on the F-LOA of the UAV, allowing the operator to interpret solutions and decisions generated autonomously, and decide whether to veto from this decision.