Generalized Laplacian Eigenmaps for Modeling and Tracking Human Motions

This paper presents generalized Laplacian eigenmaps, a novel dimensionality reduction approach designed to address stylistic variations in time series. It generates compact and coherent continuous spaces whose geometry is data-driven. This paper also introduces graph-based particle filter, a novel methodology conceived for efficient tracking in low dimensional space derived from a spectral dimensionality reduction method. Its strengths are a propagation scheme, which facilitates the prediction in time and style, and a noise model coherent with the manifold, which prevents divergence, and increases robustness. Experiments show that a combination of both techniques achieves state-of-the-art performance for human pose tracking in underconstrained scenarios.

Adaptive Fusion Of Particle Filtering And Spatio-Temporal Motion Energy For Human Tracking

Object tracking is an active research area nowadays due to its importance in human computer interface, teleconferencing and video surveillance. However, reliable tracking of objects in the presence of occlusions, pose and illumination changes is still a challenging topic. In this paper, we introduce a novel tracking approach that fuses two cues namely colour and spatio-temporal motion energy within a particle filter based framework. We conduct a measure of coherent motion over two image frames, which reveals the spatio-temporal dynamics of the target. At the same time, the importance of both colour and motion energy cues is determined in the stage of reliability evaluation. This determination helps maintain the performance of the tracking system against abrupt appearance changes. Experimental results demonstrate that the proposed method outperforms the other state of the art techniques in the used test datasets.

Robust visual tracking using structurally random projection and weighted least squares

Sparse representation based visual tracking approaches have attracted increasing interests in the community in recent years. The main idea is to linearly represent each target candidate using a set of target and trivial templates while imposing a sparsity constraint onto the representation coefficients. After we obtain the coefficients using L1-norm minimization methods, the candidate with the lowest error, when it is reconstructed using only the target templates and the associated coefficients, is considered as the tracking result. In spite of promising system performance widely reported, it is unclear if the performance of these trackers can be maximised. In addition, computational complexity caused by the dimensionality of the feature space limits these algorithms in real-time applications. In this paper, we propose a real-time visual tracking method based on structurally random projection and weighted least squares techniques. In particular, to enhance the discriminative capability of the tracker, we introduce background templates to the linear representation framework. To handle appearance variations over time, we relax the sparsity constraint using a weighed least squares (WLS) method to obtain the representation coefficients. To further reduce the computational complexity, structurally random projection is used to reduce the dimensionality of the feature space while preserving the pairwise distances between the data points in the feature space. Experimental results show that the proposed approach outperforms several state-of-the-art tracking methods.

Tracking Change in Northern Ireland Policing: Temporal Phases and Key Themes

Purpose
– The purpose of this paper is to explore and explain the change process in Northern Ireland policing through an analysis of temporally bracketed change phases and key change delivery themes ranging from 1996 to 2012.

Design/methodology/approach
– The research approach adopted is process based, longitudinal and multi-method, utilising “temporal bracketing” to determine phases of change and conjunctural reasoning to unravel the systematic factors interacting over time, within the case.

Findings
– The paper identifies and temporally brackets four phases of change: “Tipping point”; “Implementation, Symbolic Modification and Resistance”; “Power Assisted Steering”; and “A Return to Turbulence”, identifies four themes that emerge from RUC-PSNI experience: the role of adaptive leadership; pace and sequencing of change implementation; sufficient resourcing; and the impact of external agents acting as boundary spanners, and comments on the prominence of these themes through the phases. The paper goes on to reflect upon how these phases and themes inform our understanding of organisational change within policing organisations generally and within politically pressurised transition processes.

Originality/value
– The contribution of the paper lies in the documentation of an almost unique organisational case in an environmentally forced change process. In this it contains lessons for other organisations facing similar, if less extreme challenges and presents an example of intense change analysed longitudinally.

Identification and output tracking control of Hammerstein systems through wireless networks

his paper investigates the identification and output tracking control of a class of Hammerstein systems through a wireless network within an integrated framework and the statistic characteristics of the wireless network are modelled using the inverse Gaussian cumulative distribution function. In the proposed framework, a new networked identification algorithm is proposed to compensate for the influence of the wireless network delays so as to acquire the more precise Hammerstein system model. Then, the identified model together with the model-based approach is used to design an output tracking controller. Mean square stability conditions are given using linear matrix inequalities (LMIs) and the optimal controller gains can be obtained by solving the corresponding optimization problem expressed using LMIs. Illustrative numerical simulation examples are given to demonstrate the effectiveness of our proposed method.

Obsessive-compulsive symptoms and attentional bias: An eye-tracking methodology

Background and objectives: Cognitive models suggest that attentional biases are integral in the maintenance of obsessive-compulsive symptoms (OCS). Such biases have been established experimentally in anxiety disorders; however, the evidence is unclear in Obsessive Compulsive disorder (OCD). In the present study, an eye-tracking methodology was employed to explore attentional biases in relation to OCS.
Methods: A convenience sample of 85 community volunteers was assessed on OCS using the Yale-Brown Obsessive Compulsive Scale-self report. Participants completed an eye-tracking paradigm where they were exposed to OCD, Aversive and Neutral visual stimuli. Indices of attentional bias were derived from the eye-tracking data.
Results: Simple linear regressions were performed with OCS severity as the predictor and eye-tracking measures of the different attentional biases for each of the three stimuli types were the criterion variables. Findings revealed that OCS severity moderately predicted greater frequency and duration of fixations on OCD stimuli, which reflect the maintenance attentional bias. No significant results were found in support of other biases.
Limitations: Interpretations based on a non-clinical sample limit the generalisability of the conclusions, although use of such samples in OCD research has been found to be comparable to clinical populations. Future research would include both clinical and sub-clinical participants.
Conclusions: Results provide some support for the theory of maintained attention in OCD attentional biases, as opposed to vigilance theory. Individuals with greater OCS do not orient to OCD stimuli any faster than individuals with lower OCS, but once a threat is identified, these individuals allocate more attention to OCS-relevant stimuli.

Life history of turbot in Icelandic waters: Intra- and inter-population genetic diversity and otolith tracking of environmental temperatures

The stock structure of turbot was investigated between samples from S-Norway, the Irish Sea and the Kattegat, using 12 microsatellite loci and compared to the turbot caught in Icelandic waters. Highly significant genetic differentiation was observed between samples from Kattegat and other areas. Significant genetic differentiation was also observed between the Irish Sea sample on one hand and Iceland and S-Norway on the other hand. No significant genetic differentiation was observed between Iceland and S-Norway. Otoliths of 25 turbot, age ranging from 3 to 19 years, were subjected to nearly 300 mass spectrometry determinations of stable oxygen and carbon isotopes. Oxygen isotope composition (δ¹⁸O) in the otolith samples was used to estimate ambient temperature at time of otolith accretion, and yielded estimated temperatures experienced by the turbot ranging from 3 to 15°C. Overall, the genetic analysis indicates panmixia between turbot in Icelandic and Norwegian waters. While the extensive migration of larvae between Norway and Iceland is unlikely, passive drift of turbot larva from other areas (e.g. Ireland) cannot be ruled out.