Improved simultaneous computation of motion detection and optical flow for object tracking

Object tracking systems require accurate segmentation of the objects from the background for effective tracking. Motion segmentation or optical flow can be used to segment incoming images. Whilst optical flow allows multiple moving targets to be separated based on their individual velocities, optical flow techniques are prone to errors caused by changing lighting and occlusions, both common in a surveillance environment. Motion segmentation techniques are more robust to fluctuating lighting and occlusions, but don't provide information on the direction of the motion. In this paper we propose a combined motion segmentation/optical flow algorithm for use in object tracking. The proposed algorithm uses the motion segmentation results to inform the optical flow calculations and ensure that optical flow is only calculated in regions of motion, and improve the performance of the optical flow around the edge of moving objects. Optical flow is calculated at pixel resolution and tracking of flow vectors is employed to improve performance and detect discontinuities, which can indicate the location of overlaps between objects. The algorithm is evaluated by attempting to extract a moving target within the flow images, given expected horizontal and vertical movement (i.e. the algorithms intended use for object tracking). Results show that the proposed algorithm outperforms other widely used optical flow techniques for this surveillance application.

Person tracking using motion detection and optical flow

Person tracking systems to date have either relied on motion detection or optical flow as a basis for person detection and tracking. As yet, systems have not been developed that utilise both these techniques. We propose a person tracking system that uses both, made possible by a novel hybrid optical flow-motion detection technique that we have developed. This provides the system with two methods of person detection, helping to avoid missed detections and the need to predict position, which can lead to errors in tracking and mistakes when handling occlusion situations. Our results show that our system is able to track people accurately, with an average error less than four pixels, and that our system outperforms the current CAVIAR benchmark system.

Adaptive optical flow for person tracking

Person tracking systems are dependent on being able to locate a person accurately across a series of frames. Optical flow can be used to segment a moving object from a scene, provided the expected velocity of the moving object is known; but successful detection also relies on being able segment the background. A problem with existing optical flow techniques is that they don’t discriminate the foreground from the background, and so often detect motion (and thus the object) in the background. To overcome this problem, we propose a new optical flow technique, that is based upon an adaptive background segmentation technique, which only determines optical flow in regions of motion. This technique has been developed with a view to being used in surveillance systems, and our testing shows that for this application it is more effective than other standard optical flow techniques.

Object tracking using multiple motion modalities

This paper presents an object tracking system that utilises a hybrid multi-layer motion segmentation and optical flow algorithm. While many tracking systems seek to combine multiple modalities such as motion and depth or multiple inputs within a fusion system to improve tracking robustness, current systems have avoided the combination of motion and optical flow. This combination allows the use of multiple modes within the object detection stage. Consequently, different categories of objects, within motion or stationary, can be effectively detected utilising either optical flow, static foreground or active foreground information. The proposed system is evaluated using the ETISEO database and evaluation metrics and compared to a baseline system utilising a single mode foreground segmentation technique. Results demonstrate a significant improvement in tracking results can be made through the incorporation of the additional motion information.

Automatic tracking, super-resolution and recognition of human faces from surveillance video

Identifying an individual from surveillance video is a difficult, time consuming and labour intensive process. The proposed system aims to streamline this process by filtering out unwanted scenes and enhancing an individual's face through super-resolution. An automatic face recognition system is then used to identify the subject or present the human operator with likely matches from a database. A person tracker is used to speed up the subject detection and super-resolution process by tracking moving subjects and cropping a region of interest around the subject's face to reduce the number and size of the image frames to be super-resolved respectively. In this paper, experiments have been conducted to demonstrate how the optical flow super-resolution method used improves surveillance imagery for visual inspection as well as automatic face recognition on an Eigenface and Elastic Bunch Graph Matching system. The optical flow based method has also been benchmarked against the ``hallucination'' algorithm, interpolation methods and the original low-resolution images. Results show that both super-resolution algorithms improved recognition rates significantly. Although the hallucination method resulted in slightly higher recognition rates, the optical flow method produced less artifacts and more visually correct images suitable for human consumption.

Estimating Sensor Motion from Wide-Field Optical Flow on a Log-Dipolar Sensor

Log-polar image architectures, motivated by the structure of the human visual field, have long been investigated in computer vision for use in estimating motion parameters from an optical flow vector field. Practical problems with this approach have been: (i) dependence on assumed alignment of the visual and motion axes; (ii) sensitivity to occlusion form moving and stationary objects in the central visual field, where much of the numerical sensitivity is concentrated; and (iii) inaccuracy of the log-polar architecture (which is an approximation to the central 20°) for wide-field biological vision. In the present paper, we show that an algorithm based on generalization of the log-polar architecture; termed the log-dipolar sensor, provides a large improvement in performance relative to the usual log-polar sampling. Specifically, our algorithm: (i) is tolerant of large misalignmnet of the optical and motion axes; (ii) is insensitive to significant occlusion by objects of unknown motion; and (iii) represents a more correct analogy to the wide-field structure of human vision. Using the Helmholtz-Hodge decomposition to estimate the optical flow vector field on a log-dipolar sensor, we demonstrate these advantages, using synthetic optical flow maps as well as natural image sequences.

Measurement of the distributions of event-by-event flow harmonics in lead-lead collisions at = 2.76 TeV with the ATLAS detector at the LHC

The distributions of event-by-event harmonic flow coefficients v_n for n=2-4 are measured in sqrt(s_NN)=2.76 TeV Pb+Pb collisions using the ATLAS detector at the LHC. The measurements are performed using charged particles with transverse momentum pT> 0.5 GeV and in the pseudorapidity range |eta|<2.5 in a dataset of approximately 7 ub^-1 recorded in 2010. The shapes of the v_n distributions are described by a two-dimensional Gaussian function for the underlying flow vector in central collisions for v_2 and over most of the measured centrality range for v_3 and v_4. Significant deviations from this function are observed for v_2 in mid-central and peripheral collisions, and a small deviation is observed for v_3 in mid-central collisions. It is shown that the commonly used multi-particle cumulants are insensitive to the deviations for v_2. The v_n distributions are also measured independently for charged particles with 0.51 GeV. When these distributions are rescaled to the same mean values, the adjusted shapes are found to be nearly the same for these two pT ranges. The v_n distributions are compared with the eccentricity distributions from two models for the initial collision geometry: a Glauber model and a model that includes corrections to the initial geometry due to gluon saturation effects. Both models fail to describe the experimental data consistently over most of the measured centrality range.

Revisiting the ISN Flow Parameters, using a variable IBEX pointing strategy

The Interstellar Boundary Explorer (IBEX) has observed the interstellar neutral (ISN) gas flow over the past 6 yr during winter/spring when the Earth's motion opposes the ISN flow. Since IBEX observes the interstellar atom trajectories near their perihelion, we can use an analytical model based upon orbital mechanics to determine the interstellar parameters. Interstellar flow latitude, velocity, and temperature are coupled to the flow longitude and are restricted by the IBEX observations to a narrow tube in this parameter space. In our original analysis we found that pointing the spacecraft spin axis slightly out of the ecliptic plane significantly influences the ISN flow vector determination. Introducing the spacecraft spin axis tilt into the analytical model has shown that IBEX observations with various spin axis tilt orientations can substantially reduce the range of acceptable solutions to the ISN flow parameters as a function of flow longitude. The IBEX operations team pointed the IBEX spin axis almost exactly within the ecliptic plane during the 2012-2014 seasons, and about 5° below the ecliptic for half of the 2014 season. In its current implementation the analytical model describes the ISN flow most precisely for the spin axis orientation exactly in the ecliptic. This analysis refines the derived ISN flow parameters with a possible reconciliation between velocity vectors found with IBEX and Ulysses, resulting in a flow longitude lambda∞ = 74.°5 ± 1.°7 and latitude beta∞ = -5.°2 ± 0.°3, but at a substantially higher ISN temperature than previously reported.

Interstellar Flow and Temperature Determination with IBEX: Robustness and Sensitivity to Systematic Effects

The Interstellar Boundary Explorer (IBEX) samples the interstellar neutral (ISN) gas flow of several species every year from December through late March when the Earth moves into the incoming flow. The first quantitative analyses of these data resulted in a narrow tube in four-dimensional interstellar parameter space, which couples speed, flow latitude, flow longitude, and temperature, and center values with approximately 3° larger longitude and 3 km s⁻¹ lower speed, but with temperatures similar to those obtained from observations by the Ulysses spacecraft. IBEX has now recorded six years of ISN flow observations, providing a large database over increasing solar activity and using varying viewing strategies. In this paper, we evaluate systematic effects that are important for the ISN flow vector and temperature determination. We find that all models in use return ISN parameters well within the observational uncertainties and that the derived ISN flow direction is resilient against uncertainties in the ionization rate. We establish observationally an effective IBEX-Lo pointing uncertainty of ±0°18 in spin angle and confirm an uncertainty of ±0°1 in longitude. We also show that the IBEX viewing strategy with different spin-axis orientations minimizes the impact of several systematic uncertainties, and thus improves the robustness of the measurement. The Helium Warm Breeze has likely contributed substantially to the somewhat different center values of the ISN flow vector. By separating the flow vector and temperature determination, we can mitigate these effects on the analysis, which returns an ISN flow vector very close to the Ulysses results, but with a substantially higher temperature. Due to coupling with the ISN flow speed along the ISN parameter tube, we provide the temperature Tvisn∞=8710+440/-680 K for Visn∞=26 km s⁻¹ for comparison, where most of the uncertainty is systematic and likely due to the presence of the Warm Breeze.

A contribuição da geomática na geografia da saúde sob uma abordagem da Teoria Geral de Sistemas.

O conjunto de técnicas de Geomática tem sido um poderoso aliado no apoio à tomada de decisões e manipulação de dados espaciais. Nas últimas décadas tornou-se quase indispensável na gestão de recursos humanos e recursos naturais. Na área da Saúde, a Geomática tem viabilizado estudos sobre: análise da distribuição de pacientes; variações na ocorrência de epidemias; monitoramento de vetores; avaliação em tempo real de situações de emergência ou catastróficas, entre outros. A associação da Medicina com a Geografia é antiga. A associação entre a saúde e a espacialização das doenças deve considerar a estruturação física do espaço geográfico a partir da caracterização de cada parte componente do sistema como preconiza a perspectiva sistêmica na Teoria Geral de Sistema, pois a população é parte integrante do espaço geográfico no qual ocorrem determinados agravos à saúde. Nestes pontos recai a relevância da presente pesquisa. O estudo foi desenvolvido na área da Bacia Hidrográfica de Jacarepaguá no município do Rio de Janeiro. Com aproximadamente 295 km2 é composta por 19 bairros e tem uma população aproximada de 682000 habitantes. O estudo pretendeu estruturar uma metodologia para inserção das técnicas de Geomática na prática de análises de dados de saúde, apoiada na Teoria Geral de Sistemas, visando contribuir no processo de vigilância ambiental em saúde permitindo realizar um prognóstico de situações de risco de determinada população. A base cartográfica que apoiou o estudo foi construída através de cartas topográficas da DSG na escala 1:50000. Das cartas foram retiradas informações de planimetria relevantes ao estudo e as informações de altimetria que foram utilizadas na elaboração do modelo digital de terreno (MDT). Com o MDT foi gerado o mapa de declividade por grau que permitiu criar divisões em 5 classes para posterior geração de mapas temáticos com os dados de saúde. Os dados de saúde foram retirados do Sistema de Informações de Notificação de Agravos (SINAN) disponibilizado pelo Ministério da Saúde. A doença analisada foi a leptospirose. Os casos foram localizados pontualmente a partir dos endereços de residência. A hipótese aventada neste estudo era a existência de um alto grau de correlação entre as partes componentes representadas pela estruturação física do espaço e a ocorrência de leptospirose. Com os resultados comprovou-se a hipótese nula, pois somente ocorrem doenças em áreas associadas ao Fundo Chato da Baixada de Jacarepaguá e nos Declives Suaves dos Morros Isolados, também localizados no Subsistema Baixada. Isto demonstra que em termos desta doença existe uma ausência de população nesta componente espacial em áreas de maiores declividades.

Electrical Evaluation of a Low Concentrating PVT Collector Based on Performance Ratio

Photovoltaic Thermal/Hybrid collectors are an emerging technology that combines PV and solar thermal collectors by producing heat and electricity simultaneously. In this paper, the electrical performance evaluation of a low concentrating PVT collector was done through two testing parts: power comparison and performance ratio testing. For the performance ratio testing, it is required to identify and measure the factors affecting the performance ratio on a low concentrating PVT collector. Factors such as PV cell configuration, collector acceptance angle, flow rate, tracking the sun, temperature dependence and diffuse to irradiance ratio. Solarus low concentrating PVT collector V12 was tested at Dalarna University in Sweden using the electrical equipment at the solar laboratory. The PV testing has showed differences between the two receivers. Back2 was producing 1.8 energy output more than Back1 throughout the day. Front1 and Front2 were almost the same output performance. Performance tests showed that the cell configuration for Receiver2 with cells grouping (6- 32-32-6) has proved to have a better performance ratio when to it comes to minimizing the shading effect leading to more output power throughout the day because of lowering the mismatch losses. Different factors were measured and presented in this thesis in chapter 5. With the current design, it has been obtained a peak power at STC of 107W per receiver. The solar cells have an electrical efficiency of approximately 19% while the maximum measured electrical efficiency for the collector was approximately 18 % per active cell area, in addition to a temperature coefficient of -0.53%/ ˚C. Finally a recommendation was done to help Solarus AB to know how much the electrical performance is affected during variable ambient condition and be able to use the results for analyzing and introducing new modification if needed.

Impact of Planetary Gravitation on High Precision Neutral Atom Measurements

Measurements of energetic neutral atoms (ENAs) have been extremely successful in providing very important information on the physical processes inside and outside of our heliosphere. For instance, recent Interstellar Boundary Explorer (IBEX) observations have provided new insights into the local interstellar environment and improved measurements of the interstellar He temperature, velocity, and direction of the interstellar flow vector. Since particle collisions are rare, and radiation pressure is negligible for these neutrals, gravitational forces mainly determine the trajectories of neutral He atoms. Depending on the distance of an ENA to the source of a gravitational field and its relative speed and direction, this can result in significant deflection and acceleration. In this paper, we investigate the impact of the gravitational effects of Earth, the Moon, and Jupiter on ENA measurements performed in Earth's orbit. The results show that current analysis of the interstellar neutral parameters by IBEX is not significantly affected by planetary gravitational effects. We further studied the possibility of whether or not the Helium focusing cone of the Sun and Jupiter could be measured by IBEX and whether or not these cones could be used as an independent measure of the temperature of interstellar Helium.

Analysis of Evidence from Core Sample Fractures in Stewardson Lake Uranium Prospect

This study was performed to characterize evidence of potential unconformity-type U mineralizing fluids in drill core fractures from the Stewardson Lake prospect, in the Athabasca Basin, located in Northern Saskatchewan and Alberta, Canada. Fractures were visually classified into eight varieties. This classification scheme was improved with the use of mineralogical characterization through SEM (Scanning Electron Microscope) and XRD analyses of the fracture fills and resulted in the identification of various oxides, hydroxides, sulfides, and clays or clay-sized minerals. Fractures were tallied to a total of ten categories with some commonalities in color. The oxidative, reductive or mixed nature of the fluids interacting with each fracture was determined based on its fill mineralogy. The measured Pb isotopic signature of samples was used to distinguish fractures affected solely by fluids emanating from a U mineralization source, from those affected by mixed fluids. Anomalies in U and U-pathfinder elements detected in fractures assisted with attributing them to the secondary dispersion halo of potential mineralization. Three types of fracture functions (chimney, composite and drain) were defined based on their interpreted flow vector and history. A secondary dispersion halo boundary with a zone of dominance of infiltrating fluids was suggested for two boreholes. The control of fill mineralogy on fracture color was investigated and the indicative and non-indicative colors and minerals, with respect to a secondary dispersion halo, were formally described. The fracture colors and fills indicative of proximity to the basement host of the potential mineralization were also identified. In addition, three zones of interest were delineated in the boreholes with respect to their geochemical dynamics and their relationship to the potential mineralization: a shallow barren overburden zone, a dispersion and alteration zone at intermediate depth, and a second deeper zone of dispersion and alteration.

Group segmentation during object tracking using optical flow discontinuities

Within a surveillance video, occlusions are commonplace, and accurately resolving these occlusions is key when seeking to accurately track objects. The challenge of accurately segmenting objects is further complicated by the fact that within many real-world surveillance environments, the objects appear very similar. For example, footage of pedestrians in a city environment will consist of many people wearing dark suits. In this paper, we propose a novel technique to segment groups and resolve occlusions using optical flow discontinuities. We demonstrate that the ratio of continuous to discontinuous pixels within a region can be used to locate the overlapping edges, and incorporate this into an object tracking framework. Results on a portion of the ETISEO database show that the proposed algorithm results in improved tracking performance overall, and improved tracking within occlusions.

Fixed-wing attitude estimation using temporal tracking of the horizon and optical flow

In this paper, a method has been developed for estimating pitch angle, roll angle and aircraft body rates based on horizon detection and temporal tracking using a forward-looking camera, without assistance from other sensors. Using an image processing front-end, we select several lines in an image that may or may not correspond to the true horizon. The optical flow at each candidate line is calculated, which may be used to measure the body rates of the aircraft. Using an Extended Kalman Filter (EKF), the aircraft state is propagated using a motion model and a candidate horizon line is associated using a statistical test based on the optical flow measurements and the location of the horizon. Once associated, the selected horizon line, along with the associated optical flow, is used as a measurement to the EKF. To test the accuracy of the algorithm, two flights were conducted, one using a highly dynamic Uninhabited Airborne Vehicle (UAV) in clear flight conditions and the other in a human-piloted Cessna 172 in conditions where the horizon was partially obscured by terrain, haze and smoke. The UAV flight resulted in pitch and roll error standard deviations of 0.42◦ and 0.71◦ respectively when compared with a truth attitude source. The Cessna flight resulted in pitch and roll error standard deviations of 1.79◦ and 1.75◦ respectively. The benefits of selecting and tracking the horizon using a motion model and optical flow rather than naively relying on the image processing front-end is also demonstrated.