Robust visual tracking based on online learning sparse representation

Handling appearance variations is a very challenging problem for visual tracking. Existing methods usually solve this problem by relying on an effective appearance model with two features: (1) being capable of discriminating the tracked target from its background, (2) being robust to the target's appearance variations during tracking. Instead of integrating the two requirements into the appearance model, in this paper, we propose a tracking method that deals with these problems separately based on sparse representation in a particle filter framework. Each target candidate defined by a particle is linearly represented by the target and background templates with an additive representation error. Discriminating the target from its background is achieved by activating the target templates or the background templates in the linear system in a competitive manner. The target's appearance variations are directly modeled as the representation error. An online algorithm is used to learn the basis functions that sparsely span the representation error. The linear system is solved via ℓ1 minimization. The candidate with the smallest reconstruction error using the target templates is selected as the tracking result. We test the proposed approach using four sequences with heavy occlusions, large pose variations, drastic illumination changes and low foreground-background contrast. The proposed approach shows excellent performance in comparison with two latest state-of-the-art trackers.

Enhanced efficiency of envelope-tracking based broadband inverse class-E power amplifier

In this paper, the envelope-tracking technique is exploited to boost average efficiency of the newly introduced broadband Inverse Class-E power amplifier. A 2.26 GHz - 20.5 dBm - 3 V power amplifier was designed, constructed, and measured. For a multi-carrier input signal with 10 dB peak-to-average ratio, the average PAE was increased from 5.7% to 54.5%. © 2008 IEEE.

Understanding the migratory orientation program of birds: extending laboratory studies to study free flying migrants in a natural setting

For many years, orientation in migratory birds has primarily been studied in the laboratory. Although a laboratory-based setting enables greater control over environmental cues, the laboratory-based findings must be confirmed in the wild in free-flying birds to be able to fully understand how birds orient during migration. Despite the difficulties associated with following free-flying birds over long distances, a number of possibilities currently exist for tracking the long distance, sometimes even globe-spanning, journeys undertaken by migrating birds. Birds fitted with radio transmitters can either be located from the ground or from aircraft (conventional tracking), or from space. Alternatively, positional information obtained by onboard equipment (e.g., GPS units) can be transmitted to receivers in space. Use of these tracking methods has provided a wealth of information on migratory behaviors that are otherwise very difficult to study. Here, we focus on the progress in understanding certain components of the migration-orientation system. Comparably exciting results can be expected in the future from tracking free-flying migrants in the wild. Use of orientation cues has been studied in migrating raptors (satellite telemetry) and thrushes (conventional telemetry), highlighting that findings in the natural setting may not always be as expected on the basis of cage-experiments. Furthermore, field tracking methods combined with experimental approaches have finally allowed for an extension of the paradigmatic displacement experiments performed by Perdeck in 1958 on the short-distance, social migrant, the starling, to long-distance migrating storks and long-distance, non-socially migrating passerines. Results from these studies provide fundamental insights into the nature of the migratory orientation system that enables experienced birds to navigate and guide inexperienced, young birds to their species-specific winter grounds.

Human pose tracking in low dimensional space enhanced by limb correction

This paper proposes a two-level 3D human pose tracking method for a specific action captured by several cameras. The generation of pose estimates relies on fitting a 3D articulated model on a Visual Hull generated from the input images. First, an initial pose estimate is constrained by a low dimensional manifold learnt by Temporal Laplacian Eigenmaps. Then, an improved global pose is calculated by refining individual limb poses. The validation of our method uses a public standard dataset and demonstrates its accurate and computational efficiency. © 2011 IEEE.

Empirical performance of RSSI-based Monte Carlo localisation for active RFID patient tracking systems

The range of potential applications for indoor and campus based personnel localisation has led researchers to create a wide spectrum of different algorithmic approaches and systems. However, the majority of the proposed systems overlook the unique radio environment presented by the human body leading to systematic errors and inaccuracies when deployed in this context. In this paper RSSI-based Monte Carlo Localisation was implemented using commercial 868 MHz off the shelf hardware and empirical data was gathered across a relatively large number of scenarios within a single indoor office environment. This data showed that the body shadowing effect caused by the human body introduced path skew into location estimates. It was also shown that, by using two body-worn nodes in concert, the effect of body shadowing can be mitigated by averaging the estimated position of the two nodes worn on either side of the body. © Springer Science+Business Media, LLC 2012.

Online Multiperson Tracking With Occlusion Reasoning and Unsupervised Track Motion Model

We address the problem of multi-target tracking in realistic crowded conditions by introducing a novel dual-stage online tracking algorithm. The problem of data-association between tracks and detections, based on appearance, is often complicated by partial occlusion. In the first stage, we address the issue of occlusion with a novel method of robust data-association, that can be used to compute the appearance similarity between tracks and detections without the need for explicit knowledge of the occluded regions. In the second stage, broken tracks are linked based on motion and appearance, using an online-learned linking model. The online-learned motion-model for track linking uses the confident tracks from the first stage tracker as training examples. The new approach has been tested on the town centre dataset and has performance comparable with the present state-of-the-art

PLL with secondary loop control for self tracking antennas

This paper shows a simple, yet highly effective, tracking phase locked loop circuit which has applications for self steered antenna arrays. The tracking PLL has been demonstrated to accurately phase track signal levels as low as -120 dBm, making it suitable for applications such as SATCOM ground terminals. The implementation is simple requiring a low Q voltage controlled oscillator, a downconverting mixer and a PLL circuit.

Tracking the Fate of Microbially Sequestered Carbon Dioxide in Soil Organic Matter

The microbial contribution to soil organic matter (SOM) has recently been shown to be much larger than previously thought and thus its role in carbon sequestration may also be underestimated. In this study we employ C-13 ((CO2)-C-13) to assess the potential CO2 sequestration capacity of soil chemoautotrophic bacteria and combine nuclear magnetic resonance (NMR) with stable isotope probing (SIP), techniques that independently make use of the isotopic enrichment of soil microbial biomass. In this way molecular information generated from NMR is linked with identification of microbes responsible for carbon capture. A mathematical model is developed to determine real-time CO2 flux so that net sequestration can be calculated. Twenty-eight groups of bacteria showing close homologies with existing species were identified. Surprisingly, Ralstonia eutropha was the dominant group. Through NMR we observed the formation of lipids, carbohydrates, and proteins produced directly from CO2 utilized by microbial biomass. The component of SOM directly associated with CO2 capture was calculated at 2.86 mg C (89.21 mg kg(-1)) after 48 h. This approach can,differentiate between SOM derived through microbial uptake of CO2 and other SOM constituents and represents a first step in tracking the fate and dynamics of microbial biomass in soil.

Behavioural context of multi-scale species distribution models assessed by radio-tracking

Incorporating ecological processes and animal behaviour into Species Distribution Models (SDMs) is difficult. In species with a central resting or breeding place, there can be conflict between the environmental requirements of the 'central place' and foraging habitat. We apply a multi-scale SDM to examine habitat trade-offs between the central place, roost sites, and foraging habitat in . Myotis nattereri. We validate these derived associations using habitat selection from behavioural observations of radio-tracked bats. A Generalised Linear Model (GLM) of roost occurrence using land cover variables with mixed spatial scales indicated roost occurrence was positively associated with woodland on a fine scale and pasture on a broad scale. Habitat selection of radio-tracked bats mirrored the SDM with bats selecting for woodland in the immediate vicinity of individual roosts but avoiding this habitat in foraging areas, whilst pasture was significantly positively selected for in foraging areas. Using habitat selection derived from radio-tracking enables a multi-scale SDM to be interpreted in a behavioural context. We suggest that the multi-scale SDM of . M. nattereri describes a trade-off between the central place and foraging habitat. Multi-scale methods provide a greater understanding of the ecological processes which determine where species occur and allow integration of behavioural processes into SDMs. The findings have implications when assessing the resource use of a species at a single point in time. Doing so could lead to misinterpretation of habitat requirements as these can change within a short time period depending on specific behaviour, particularly if detectability changes depending on behaviour. © 2011 Gesellschaft für ökologie.

Establishing optimal quantitative-polymerase chain reaction assays for routine diagnosis and tracking of minimal residual disease in JAK2-V617F-associated myeloproliferative neoplasms:a joint European LeukemiaNet/MPN&MPNr-EuroNet (COST action BM0902) study

Reliable detection of JAK2-V617F is critical for accurate diagnosis of myeloproliferative neoplasms (MPNs); in addition, sensitive mutation-specific assays can be applied to monitor disease response. However, there has been no consistent approach to JAK2-V617F detection, with assays varying markedly in performance, affecting clinical utility. Therefore, we established a network of 12 laboratories from seven countries to systematically evaluate nine different DNA-based quantitative PCR (qPCR) assays, including those in widespread clinical use. Seven quality control rounds involving over 21,500 qPCR reactions were undertaken using centrally distributed cell line dilutions and plasmid controls. The two best-performing assays were tested on normal blood samples (n=100) to evaluate assay specificity, followed by analysis of serial samples from 28 patients transplanted for JAK2-V617F-positive disease. The most sensitive assay, which performed consistently across a range of qPCR platforms, predicted outcome following transplant, with the mutant allele detected a median of 22 weeks (range 6-85 weeks) before relapse. Four of seven patients achieved molecular remission following donor lymphocyte infusion, indicative of a graft vs MPN effect. This study has established a robust, reliable assay for sensitive JAK2-V617F detection, suitable for assessing response in clinical trials, predicting outcome and guiding management of patients undergoing allogeneic transplant.

Analysis of Dependence Tracking Algorithms for Task Dataflow Execution

Processor architectures has taken a turn towards many-core processors, which integrate multiple processing cores on a single chip to increase overall performance, and there are no signs that this trend will stop in the near future. Many-core processors are harder to program than multi-core and single-core processors due to the need of writing parallel or concurrent programs with high degrees of parallelism. Moreover, many-cores have to operate in a mode of strong scaling because of memory bandwidth constraints. In strong scaling increasingly finer-grain parallelism must be extracted in order to keep all processing cores busy.

Task dataflow programming models have a high potential to simplify parallel program- ming because they alleviate the programmer from identifying precisely all inter-task de- pendences when writing programs. Instead, the task dataflow runtime system detects and enforces inter-task dependences during execution based on the description of memory each task accesses. The runtime constructs a task dataflow graph that captures all tasks and their dependences. Tasks are scheduled to execute in parallel taking into account dependences specified in the task graph.

Several papers report important overheads for task dataflow systems, which severely limits the scalability and usability of such systems. In this paper we study efficient schemes to manage task graphs and analyze their scalability. We assume a programming model that supports input, output and in/out annotations on task arguments, as well as commutative in/out and reductions. We analyze the structure of task graphs and identify versions and generations as key concepts for efficient management of task graphs. Then, we present three schemes to manage task graphs building on graph representations, hypergraphs and lists. We also consider a fourth edge-less scheme that synchronizes tasks using integers. Analysis using micro-benchmarks shows that the graph representation is not always scalable and that the edge-less scheme introduces least overhead in nearly all situations.