Non-rigid object tracking in complex scenes

A recently proposed colour based tracking algorithm has been established to track objects in real circumstances [Zivkovic, Z., Krose, B. 2004. An EM-like algorithm for color-histogram-based object tracking. In: Proc, IEEE Conf. on Computer Vision and Pattern Recognition, pp. 798-803]. To improve the performance of this technique in complex scenes, in this paper we propose a new algorithm for optimally adapting the ellipse outlining the objects of interest. This paper presents a Lagrangian based method to integrate a regularising component into the covariance matrix to be computed. Technically, we intend to reduce the residuals between the estimated probability distribution and the expected one. We argue that, by doing this, the shape of the ellipse can be properly adapted in the tracking stage. Experimental results show that the proposed method has favourable performance in shape adaption and object localisation.

Can diversity amongst learners improve online object tracking?

We present a novel analysis of the state of the art in object tracking with respect to diversity found in its main component, an ensemble classifier that is updated in an online manner. We employ established measures for diversity and performance from the rich literature on ensemble classification and online learning, and present a detailed evaluation of diversity and performance on benchmark sequences in order to gain an insight into how the tracking performance can be improved. © Springer-Verlag 2013.

Characterisation of electrospun polystyrene scaffolds for three-dimensional in vitro biological studies

The purpose of this study was to produce a well-characterised electrospun polystyrene scaffold which could be used routinely for three-dimensional (3D) cell culture experimentation. A linear relationship (p<0.01p<0.01) between three principal process variables (applied voltage, working distance and polymer concentration) and fibre diameter was reliably established enabling a mathematical model to be developed to standardise the electrospinning process. Surface chemistry and bulk architecture were manipulated to increase wetting and handling characteristics, respectively. X-ray photoelectron spectroscopy (XPS) confirmed the presence of oxygen-containing groups after argon plasma treatment, resulting in a similar surface chemistry to treated tissue culture plastic. The bulk architecture of the scaffolds was characterised by scanning electron microscopy (SEM) to assess the alignment of both random and aligned electrospun fibres, which were calculated to be 0.15 and 0.66, respectively. This compared to 0.51 for collagen fibres associated with native tissue. Tensile strength and strain of approximately of 0.15 MPa and 2.5%, respectively, allowed the scaffolds to be routinely handled for tissue culture purposes. The efficiency of attachment of smooth muscle cells to electrospun scaffolds was assessed using a modified 3-[4,5-dimethyl(thiazol-2yl)-3,5-diphery] tetrazolium bromide assay and cell morphology was assessed by phalloidin-FITC staining of F-actin. Argon plasma treatment of electrospun polystyrene scaffold resulted in significantly increased cell attachment (p<0.05p<0.05). The alignment factors of the actin filaments were 0.19 and 0.74 for the random and aligned scaffold respectively, compared to 0.51 for the native tissue. The data suggests that electrospinning of polystyrene generates 3D scaffolds which complement polystyrene used in 2D cell culture systems.

Rhythm makes the world go round:an MEG-TMS study on the role of right TPJ theta oscillations in embodied perspective taking

While some aspects of social processing are shared between humans and other species, some aspects are not. The former seems to apply to merely tracking another's visual perspective in the world (i.e., what a conspecific can or cannot perceive), while the latter applies to perspective taking in form of mentally “embodying” another's viewpoint. Our previous behavioural research had indicated that only perspective taking, but not tracking, relies on simulating a body schema rotation into another's viewpoint. In the current study we employed Magnetoencephalography (MEG) and revealed that this mechanism of mental body schema rotation is primarily linked to theta oscillations in a wider brain network of body-schema, somatosensory and motor-related areas, with the right posterior temporo-parietal junction (pTPJ) at its core. The latter was reflected by a convergence of theta oscillatory power in right pTPJ obtained by overlapping the separately localised effects of rotation demands (angular disparity effect), cognitive embodiment (posture congruence effect), and basic body schema involvement (posture relevance effect) during perspective taking in contrast to perspective tracking. In a subsequent experiment we interfered with right pTPJ processing using dual pulse Transcranial Magnetic Stimulation (dpTMS) and observed a significant reduction of embodied processing. We conclude that right TPJ is the crucial network hub for transforming the embodied self into another's viewpoint, body and/or mind, thus, substantiating how conflicting representations between self and other may be resolved and potentially highlighting the embodied origins of high-level social cognition in general.

CamSim:a distributed smart camera network simulator

Smart cameras allow pre-processing of video data on the camera instead of sending it to a remote server for further analysis. Having a network of smart cameras allows various vision tasks to be processed in a distributed fashion. While cameras may have different tasks, we concentrate on distributed tracking in smart camera networks. This application introduces various highly interesting problems. Firstly, how can conflicting goals be satisfied such as cameras in the network try to track objects while also trying to keep communication overhead low? Secondly, how can cameras in the network self adapt in response to the behavior of objects and changes in scenarios, to ensure continued efficient performance? Thirdly, how can cameras organise themselves to improve the overall network's performance and efficiency? This paper presents a simulation environment, called CamSim, allowing distributed self-adaptation and self-organisation algorithms to be tested, without setting up a physical smart camera network. The simulation tool is written in Java and hence allows high portability between different operating systems. Relaxing various problems of computer vision and network communication enables a focus on implementing and testing new self-adaptation and self-organisation algorithms for cameras to use.