Vision-based target tracking and surveillance with robust set-valued state estimation

Tracking a target from a video stream (or a sequence of image frames) involves nonlinear measurements in Cartesian coordinates. However, the target dynamics, modeled in Cartesian coordinates, result in a linear system. We present a robust linear filter based on an analytical nonlinear to linear measurement conversion algorithm. Using ideas from robust control theory, a rigorous theoretical analysis is given which guarantees that the state estimation error for the filter is bounded, i.e., a measure against filter divergence is obtained. In fact, an ellipsoidal set-valued estimate is obtained which is guaranteed to contain the true target location with an arbitrarily high probability. The algorithm is particularly suited to visual surveillance and tracking applications involving targets moving on a plane.

Tracking multiple mobile agents with single frequency continuous wave radar

In this paper, a novel concept to determine the velocity and the location information of multiple mobile agents using Doppler radar has been introduced. Also, an expression for the minimum number of inline sensors needed to guarantee this estimation for n number of mobile agents has been obtained. Current methods use the time derivative of the displacement of adjacent position measurements to find the velocities of agents. This method is error prone, particularly, if the agents are accelerating. In our approach we incorporate direction-of-arrival (DOA) radar which tracks the location and the velocity of each and every agent in each measurement step.

Tracking phenotypically and functionally distinct T cell subsets via T cell repertoire diversity

Antigen-specific T cell receptors (TCRs) recognise complexes of immunogenic peptides (p) and major histocompatibility complex (MHC) glycoproteins. Responding T cell populations show profiles of preferred usage (or bias) toward one or few TCRβ chains. Such skewing is also observed, though less commonly, in TCRα chain usage. The extent and character of clonal diversity within individual, antigen-specific T cell sets can be established by sequence analysis of the TCRVβ and/or TCRVα CDR3 loops. The present review provides examples of such TCR repertoires in prominent responses to acute and persistent viruses. The determining role of structural constraints and antigen dose is discussed, as is the way that functionally and phenotypically distinct populations can be defined at the clonal level. In addition, clonal dissection of “high” versus “low” avidity, or “central” versus “effector” memory sets provides insights into how these antigen specific T cell responses are generated and maintained. As TCR diversity potentially influences both the protective capacity of CD8+ T cells and the subversion of immune control that leads to viral escape, analysing the spectrum of TCR selection and maintenance has implications for improving the functional efficacy of T cell responsiveness and effector function.

Socioeconomic position and the tracking of physical activity and cardiorespiratory fitness from childhood to adulthood

This study examined the influence of childhood socioeconomic position (SEP) and social mobility on activity and fitness tracking from childhood into adulthood. In a prospective cohort of 2,185 Australian adults (aged 26–36 years), first examined in 1985 (at ages 7–15 years), self-reported physical activity and cardiorespiratory fitness (subsample only) were measured. SEP measures included retrospectively reported parental education (baseline) and own education (follow-up). There was little evidence of a relation between childhood SEP and activity tracking, but high childhood SEP (maternal education) was associated with a 59% increased likelihood of persistent fitness, and medium childhood SEP (paternal and parental education) was associated with a 33%–36% decreased likelihood of persistent fitness. Upward social mobility was associated with a greater likelihood of increasing activity (38%–49%) and fitness (90%), and persistently high SEP was associated with a greater likelihood of increasing activity (males: 58%) and fitness (males and females combined: 89%). In conclusion, persistently high SEP and upward social mobility were associated with increases in activity and fitness from childhood to adulthood. Findings highlight socioeconomic differentials in activity and fitness patterns and suggest that improvements in education may represent a pathway through which physical activity levels can be increased and health benefits achieved

A method for stereo-vision-based tracking for robotic applications

Vision-based tracking of an object using perspective projection inherently results in non-linear measurement equations in the Cartesian coordinates. The underlying object kinematics can be modelled by a linear system. In this paper we introduce a measurement conversion technique that analytically transforms the non-linear measurement equations obtained from a stereo-vision system into a system of linear measurement equations.We then design a robust linear filter around the converted measurement system. The state estimation error of the proposed filter is bounded and we provide a rigorous theoretical analysis of this result. The performance of the robust filter developed in this paper is demonstrated via computer simulation and via practical experimentation using a robotic manipulator as a target. The proposed filter is shown to outperform the extended Kalman filter (EKF).

Tracking of sedentary behaviours of young people : a systematic review

Objective : To review the empirical evidence concerning the strength of tracking of sedentary behaviours from childhood and adolescence.

Methods : Published English language studies were located from computerised and manual searches in 2009. Included studies were prospective, longitudinal studies with at least one sedentary behaviour for at least two time-points, with tracking coefficients reported, and included children (aged 3–11 years) and adolescents (12–18 years) at baseline.

Results : Based on data from 21 independent samples, tracking coefficients (r) ranged from 0.08 (over 16 years) to 0.73 (over 2 years) for TV viewing, from 0.18 (boys over 3 years) to 0.52 (over 2 years) for electronic game/computer use, from 0.16 (girls over 4 years) to 0.65 (boys over 2 years) for total screen time, and from −0.15 (boys over 2 years) to 0.48 (over 1 year) for total sedentary time. Study follow-up periods ranged from 1 to up to 27 years, and tracking coefficients tended to be higher with shorter follow-ups.

Conclusions : Sedentary behaviours track at moderate levels from childhood or adolescence. Data suggest that sedentary behaviours may form the foundation for such behaviours in the future and some may track slightly better than physical activity.

Maximum likelihood approach for tracking multiple mobile agents with a moving doppler radar system

Tracking mobile agents with a Doppler radar system mounted on a moving vehicle is considered in this paper. Dopplers modulated from mobile agents on the single frequency continuous wave signals are analyzed in order to estimate the positions and velocities of multiple mobile agents. The measurement noise is assumed to be Gaussian and the maximum likelihood estimation is utilized to enhance the localization accuracy.

Fusion based 3D tracking of mobile transmitters via robust set-valued state estimation with RSS measurements

This paper investigates the problem of location and velocity detection of a mobile agent using Received Signal Strength (RSS) measurements captured by geographically distributed seed nodes. With inherently nonlinear power measurements, we derive a powerful linear measurement scheme using an analytical measurement conversion technique which can readily be used with RSS measuring sensors. We also employ the concept of sensor fusion in conjunction for the case of redundant measurements to further enhance the estimation accuracy.

Mobile agent tracking with single frequency continuous wave radar : a linear robust filtering based approach

3-alkylpyrrole to the fabric surface. Direct applications of a conductive paint to the textile surface eliminate the exposure of the substrate to damaging oxidizing agents which allow the coating of more sensitive and delicate substrates. All textiles produced are tested for abrasion resistance and conductivity. For alkyl polypyrrole coated fabrics, the optimum carbon chain lengths are between n=10 and n=14, which result in optimum values of conductivity and solubility. The darkness of the tone is inversely related to the surface resistivity of the resulting conductive fabric. Therefore, deep black coatings have low resistivity whereas light gray coatings on a white fabric surface have higher surface resistivity. Longer alkyl chains result in higher surface resistivity in fabrics. The conductive coating of poly(3-decanylpyrrole) on the textile surface has a better abrasion resistance compared to that of an unsubstituted polypyrrole coating.

Combining multiple tracking algorithms for improved general performance

Automated tracking of objects through a sequence of images has remained one of the difficult problems in computer vision. Numerous algorithms and techniques have been proposed for this task. Some algorithms perform well in restricted environments, such as tracking using stationary cameras, but a general solution is not currently available. A frequent problem is that when an algorithm is refined for one application, it becomes unsuitable for other applications. This paper proposes a general tracking system based on a different approach. Rather than refine one algorithm for a specific tracking task, two tracking algorithms are employed, and used to correct each other during the tracking task. By choosing the two algorithms such that they have complementary failure modes, a robust algorithm is created without increased specialisation.

Tracking and surveillance in wide-area spatial environments using the abstract hidden markov model.

In this paper, we consider the problem of tracking an object and predicting the object's future trajectory in a wide-area environment, with complex spatial layout and the use of multiple sensors/cameras. To solve this problem, there is a need for representing the dynamic and noisy data in the tracking tasks, and dealing with them at different levels of detail. We employ the Abstract Hidden Markov Models (AHMM), an extension of the well-known Hidden Markov Model (HMM) and a special type of Dynamic Probabilistic Network (DPN), as our underlying representation framework. The AHMM allows us to explicitly encode the hierarchy of connected spatial locations, making it scalable to the size of the environment being modeled. We describe an application for tracking human movement in an office-like spatial layout where the AHMM is used to track and predict the evolution of object trajectories at different levels of detail.

A method for tracking rats in a complex and completely dark environment using computerized video analysis

The automated tracking of rodents in open field environments has become a standard laboratory technique for the investigation of the effects of drugs, novel therapeutic interventions and genetic mutations on behavior. Here, we develop an extension of this technique that permits tracking in full darkness through a complex (‘enriched’) environment comprising naturalistic structures such as tunnels and hides. To eliminate unwanted light reflections and tape noise, we developed a unique video filter that combines the advantages of differential and non-differential filtering. This filter enabled the tracking of albino rats against a relatively dark background to an accuracy of approximately 97% compared to hand tracking of the same animal, irrespective of whether the rat was inside a hide box or tunnel or out in the open field. The system as a whole can be easily deployed using standard PCs and inexpensive infrared cameras and lights.

A probabilistic framework for tracking in wide-area environments

Surveillance in wide-area spatial environments is characterised by complex spatial layouts, large state space, and the use of multiple cameras/sensors. To solve this problem, there is a need for representing the dynamic and noisy data in the tracking tasks, and dealing with them at different levels of detail. This requirement is particularly suited to the Layered Dynamic Probabilistic Network (LDPN), a special type of Dynamic Probabilistic Network (DPN). In this paper, we propose the use of LDPN as the integrated framework for tracking in wide-area environments. We illustrate, with the help of a synthetic tracking scenario, how the parameters of the LDPN can be estimated from training data, and then used to draw predictions and answer queries about unseen tracks at various levels of detail.

Human saccadic eye movements and tracking by active foveation in log polar space

One of the possible models of the human visual system (HVS) in the computer vision literature has a high resolution fovea and exponentially decreasing resolution periphery. The high resolution fovea is used to extract necessary information in order to solve a vision task and the periphery may be used to detect motion. To obtain the desired information, the fovea is guided by the contents of the scene and other knowledge to position the fovea over areas of interest. These eye movements are called saccades and corrective saccades. A two stage process has been implemented as a mechanism for changing foveation in log polar space. Initially, the open loop stage roughly foveates on the best interest feature and then the closed loop stage is invoked to accurately iteratively converge onto the foveation point. The open loop stage developed for the foveation algorithm is applied to saccadic eye movements and a tracking system. Log polar space is preferred over Cartesian space as: (1) it simultaneously provides high resolution and a wide viewing angle; and (2) feature invariance occurs in the fovea which simplifies the foveation process.