Region Tracking Research Articles

A novel foreground region analysis using NCP-DBP texture pattern for robust visual tracking

Robust visual tracking is the important stage in the computer vision applications such as robotics, man-free control systems, and the visual surveillance. Accurate motion states estimation and the target representation in visual tracking system are based on the appearances of the target. The factor affects the learning of target representation is the accumulated error due to the pose, illumination changes, and the uneven background. The presence of dynamic background and the shadowing effects causes the visual drift and destructive information. Besides, the misclassification of target region induces the false detection of moving objects. The K-means and Fuzzy-C-means clustering algorithms are available to segment the foreground/background and suppress the shadow region on the basis of the non-changing background of the surveillance area. This paper proposes the novel background normalization technique with textural pattern analysis to suppress the shadow region. The Neighborhood Chain Prediction (NCP) algorithm is used to cluster the uneven background and the Differential Boundary Pattern (DBP) extracts the texture of the video frame to suppress the shadow pixels present in the frame. The lower intensity estimation and the prediction of the area around the lower intensity in proposed work enhance the pixels for shadow removal. The shadow-free frame split up into several grids and the histograms of features are extracted from the grid formatted frame. Finally, the Machine Level Classification (MLC) finds the matching grid corresponds to the tracking region and provides the binary labeling to separate the background and foreground. The proposed DBP-based visual tracking system is high robustness over the sudden illumination changes and the dynamic background due to the texture pattern analysis. The comparison of proposed NCP-DBP combination with the existing segmentation techniques regarding the accuracy, precision, recall, F-measure, success and error rate assured the effectiveness in visual tracking applications.

Ultraviolet sensitization of high-energy heavy-ion tracks in polyethylene terephthalate

The reasons underlying the selective acceleration of the etching of heavy-ion tracks in polyethylene terephthalate irradiated by ultraviolet radiation (UV) are examined. The use of high-performance liquid chromatography, atomic-force microscopy, and infrared (IR) spectroscopy enable us to ascertain that etching is accelerated mainly due to the photodestruction of radiolysis products, which leads to the formation of an additional amount of low-molecular products with carboxyl groups in the region of tracks, thereby ultimately accelerating the polymer-etching process.

A New Human Eye Tracking Algorithm of Optimized TLD Based on Improved Mean-Shift

In this paper, an improved Mean-shift algorithm was integrated with standard tracking–learning–detection (TLD) model tracker for improving the tracking effects of standard TLD model and enhancing the anti-occlusion capability and the recognition capability of similar objectives. The target region obtained by the improved Mean-shift algorithm and the target region obtained by the TLD model tracker are integrated to achieve favorable tracking effects. Then the optimized TLD tracking system was applied to human eye tracking. In the tests, the model can be self-adopted to partial occlusion, such as eye-glasses, closed eyes and hand occlusion. And the roll angle can approach 90[Formula: see text], raw angle can approach 45[Formula: see text] and pitch angle can approach 60[Formula: see text]. In addition, the model never mistakenly transfers the tracking region to another eye (similar target on the same face) in longtime tracking. Experimental results indicate that: (1) the optimized TLD model shows sound tracking stability even when targets are partially occluded or rotated; (2) tracking speed and accuracy are superior to those of the standard TLD and some mainstream tracking methods. In summary, the optimized TLD model show higher robustness, stability and better responding to complex eye tracking requirement.

Experimental Highlights: Heavy Quark Physics in Heavy-Ion Collisions at RHIC

The discovery at RHIC of large high- p T suppression and flow of electrons from heavy quarks flavors have altered our view of the hot and dense matter formed in central Au + Au collisions at √ s NN = 200 GeV. These results suggest a large energy loss and flow of heavy quarks in the hot, dense matter. In recent years, the RHIC experiments upgraded the detectors; (1) PHENIX Collaboration installed silicon vertex tracker (VTX) at midrapidity region and forward silicon vertex tracker (FVTX) at the forward rapidity region, and (2) STAR Collaboration installed the heavy flavor tracker (HFT) and the muon telescope detector (MTD) both at the mid-rapidity region. The PHENIX experiments established measurements of ψ (1 S ) and ψ (2 S ) production as a function of system size, p + p , p + Al, p + Au, and 3 He + Au collisions at √ s NN = 200 GeV. In p/ 3 He + A collisions at forward rapidity, we observe no difference in the ψ (2 S )/ ψ (1 S ) ratio relative to p + p collisions. At backward rapidity, where the comoving particle density is higher, we find that the ψ (2 S ) is preferentially suppressed by a factor of two. STAR Collaboration presents the first J/ ψ measurements in the di-muon decay channel in Au + Au at √ s NN = 200 GeV at mid-rapidity. We observe a clear J/ψ R AA suppression and qualitatively well described by transport models, including dissociation and regeneration simultaneously.

Simulations of cratering and sputtering from an ion track in crystalline and amorphous Lennard Jones thin films

Impacts of swift heavy ions of different energy loss in amorphous and crystalline Lennard-Jones (LJ) thin films (2–60nm) were simulated using classical molecular dynamics to study cratering and sputtering in model molecular thin films. Crater size is determined mostly by evaporation and melt flow from the hot ion track, while rim size is determined both by melt flow and by coherent displacement of particles due to the large pressure developed in the excited region, with minor influence of particles from the substrate. Sputtering yields from both crystalline and amorphous samples are similar (including the scaling with energy loss), due to the extremely high temperature and disordered condition of the track region from where most ejected particles originate in the early stages of the track evolution. Cratering, however clearly depends on the crystallinity of the film. Craters and rims are much smaller in crystalline films mainly due to faster energy dissipation, higher stress threshold for plasticity and smaller free-volume in the ordered phase. We also found a large dependence of the induced surface effects on film thickness below a critical thickness value. The pressure pulse due to the ion impact is weaker and cooling of the excited track is more efficient in short tracks, both contributing to the decreased radiation damage efficiency on ultrathin layers. Despite the simplicity of the LJ model, the simulations in the amorphous films reproduce remarkably well several of the experimental features seen recently on polymer thin and ultrathin films irradiated by swift heavy ions.

Molecular dynamics simulation of polymerlike thin films irradiated by fast ions: A comparison between FENE and Lennard-Jones potentials

In this paper, the surface effects of individual heavy ions impacting thin polymerlike films were investigated, using molecular dynamics simulations with the finite extensible nonlinear elastic (FENE) potential to describe the molecular chains. The perturbation introduced by the ions in the lattice was modeled assuming that the initial excitation energy in the ion track is converted into an effective temperature, as in a thermal spike. The track was heated only within the film thickness $h$, leaving a nonexcited substrate below. The effect of decreasing thickness on cratering and sputtering was evaluated. The results were compared to experimental data of thin polymer films bombarded by MeV--GeV ions and to simulations performed with the Lennard-Jones potential. While several qualitative results observed in the experiments were also seen in the simulations, irrespective of the potential used, there are important differences observed on FENE films. Crater dimensions, rim volume, and sputtering yields are substantially reduced, and a threshold thickness for molecular ejection appears in FENE simulations. This is attributed to the additional restrictions on mass transport out of the excited track region imposed by interchain interactions (entanglements) and by the low mobility of the molten phase induced by the spike.

Silicon pixel-detector R&D for CLIC

The physics aims at the future CLIC high-energy linear e+e- collider set very high precision requirements on the performance of the vertex and tracking detectors. Moreover, these detectors have to be well adapted to the experimental conditions, such as the time structure of the collisions and the presence of beam-induced backgrounds. The principal challenges are: a point resolution of a few μm, ultra-low mass (∼ 0.2%X0 per layer for the vertex region and ∼ 1%X0 per layer for the outer tracker), very low power dissipation (compatible with air-flow cooling in the inner vertex region) and pulsed power operation, complemented with ∼ 10 ns time stamping capabilities. A highly granular all-silicon vertex and tracking detector system is under development, following an integrated approach addressing simultaneously the physics requirements and engineering constraints. For the vertex-detector region, hybrid pixel detectors with small pitch (25 μm) and analog readout are explored. For the outer tracking region, both hybrid concepts and fully integrated CMOS sensors are under consideration. The feasibility of ultra-thin sensor layers is validated with Timepix3 readout ASICs bump bonded to active edge planar sensors with 50 μm to 150 μm thickness. Prototypes of CLICpix readout ASICs implemented in 6525 nm CMOS technology with 25 μm pixel pitch have been produced. Hybridisation concepts have been developed for interconnecting these chips either through capacitive coupling to active HV-CMOS sensors or through bump-bonding to planar sensors. Recent R&D achievements include results from beam tests with all types of hybrid assemblies. Simulations based on Geant4 and TCAD are used to validate the experimental results and to assess and optimise the performance of various detector designs.

Uma Revisão dos Processos de Interação Oceano-Atmosfera em Regiões de Intenso Gradiente Termal do Oceano Atlântico Sul Baseada em Dados Observacionais

Resumo De um modo geral, a interação do oceano com a atmosfera em regiões de intensa atividade da mesoescala oceânica (frentes oceanográficas, meandros e turbilhões de escalas espaciais típicas de cerca de 100-500 km e escalas temporais de cerca de 2-3 meses) apresenta uma correlação positiva entre a temperatura da superfície do mar (TSM) e variáveis meteorológicas tais como a estabilidade da Camada Limite Atmosférica Marinha (CLAM), a intensidade do vento e os fluxos de calor, de momentum e de gases entre o oceano e a atmosfera. Isto sugere que o oceano força a atmosfera nas escalas espaciais e temporais relacionados à mesoescala oceânica. Principalmente com base em dados observacionais, porém não exclusivamente, este trabalho apresenta uma breve revisão científica sobre o impacto das estruturas de mesoescala presentes no Oceano Atlântico Sudoeste em alguns componentes do sistema acoplado oceano-atmosfera que, em certos aspectos, impactam o tempo e o clima da regiões continentais adjacentes na América do Sul. Inclui-se neste artigo também uma breve revisão do estado da arte do conhecimento sobre a parte oceânica da Zona de Convergência do Atlântico Sul. Este artigo apresenta as características oceanográficas gerais da área de estudo, incluindo alguns aspectos sobre a circulação do Atlântico Sul e a variabilidade. Lembrando do fato que o Atlântico Sudoeste e Sul são regiões consideradas como trilha de tempestade, este trabalho também discute os impactos dos gradientes de TSM do Oceano Atlântico Sul Ocidental sobre os sistemas atmosféricos transientes que atravessam frequentemente esta região. Além disso, o artigo discute novos indícios de que os processos oceanográficos que ocorrem no litoral sul do Brasil no inverno tem um forte impacto sobre a modulação CLAM sobre a plataforma continental do sul do Brasil. O artigo aponta também índicos passados e presentes que os processos ecológicos causados pela variabilidade climática atmosférica e marinha na costa sul do Brasil impactam na desova e captura da sardinha (Sardinella Brasiliensis), que é um dos mais importantes recursos marinhos renováveis do Brasil. O artigo termina apresentando alguns dos esforços observacionais atuais do Brasil, visando a coleta de dados meteorológicos e marinhos no Oceano Atlântico Equatorial e Sul. Estes esforços visam aumentar a nossa compreensão do acoplamento oceano-atmosfera nas escalas sinóticas e climáticas, bem como o papel do Oceano Atlântico em controlar o calor, momentum e fluxos de dióxido de carbono para a atmosfera.

Solar Powered Water Pumping System Employing Switched Reluctance Motor Drive

This paper presents a solar photovoltaic array fed water pumping system employing a switched reluctance motor (SRM) drive. The electronic commutation of the SRM drive at fundamental frequency offers reduced switching losses in a mid-point converter and considerably increases the efficiency of proposed system. The speed of SRM is controlled by varying the dc-bus voltage of the mid-point converter. A dc–dc Cuk converter operating in continuous conduction mode (CCM) is used for dc-bus voltage control. The CCM operation of inductors helps to reduce the ringing effect and decreases the losses of dc–dc converter. Current and voltage stresses on devices including switching stress of Cuk converter are also reduced in CCM. The Cuk converter facilitates the continuous and smooth input/output currents to SRM drive with boundless region for maximum power point tracking (MPPT) operation. The adjustment in step size of an incremental conductance MPPT algorithm facilitates the soft starting of SRM drive. The proposed system, subjected to dynamically atmospheric conditions is designed, modeled, and simulated using MATLAB/Simulink environment. A prototype of proposed configuration is also developed and its performance is validated with test results for the control of speed over varying insolation levels.

Structure of ion tracks in ceria irradiated with high energy xenon ions

Structure and accumulation behavior of ion tracks in CeO2 irradiated with 200 MeV Xe ions were examined by transmission electron microscopy (TEM) and scanning transmission electron microscopy (STEM) to obtain fundamental knowledge on the microstructure evolution induced by fission fragments in nuclear fuels and transmutation targets, which is of importance for the development of advanced fuel/target materials at high burn-up conditions. Bright-field (BF) TEM images of ion tracks from an inclined direction showed Fresnel contrast along penetrating path of incident ions. The signal intensity of high-angle annular dark-field (HAADF) STEM images was decreased at the core damage region of ion tracks along the path of ions, revealing the reduction of atomic density inside the ion track. Preferential formation of smaller and larger ion tracks was observed at a high ion fluence of 1 × 1014 cm−2 compared to a low ion fluence of 1 × 1011 cm−2. Results were discussed due to the coalescences and incomplete recovery of the core damage regions during the overlap of high density electronic excitation damage, which is induced during the repetition of the formation and recovery of ion tracks within an influence region.

Trends and projections of Southern Hemisphere baroclinicity: the role of external forcing and impact on Australian rainfall

Changes in the characteristics of Southern Hemisphere (SH) storms, in all seasons, during the second half of the twentieth century, have been related to changes in the annual cycle of SH baroclinic instability. In particular, significant negative trends in baroclinic instability, as measured by the Phillips Criterion, have been found in the region of the climatological storm tracks; a zonal band of significant positive trends occur further poleward. Corresponding to this decrease/increase in baroclinic instability there is a decrease/increase in the growth rate of storm formation at these latitudes over this period, and in some cases a preference for storm formation further poleward than normal. Based on model output from a multi-model ensemble (MME) of coupled atmosphere–ocean general circulation models, it is shown that these trends are the result of external radiative forcing, including anthropogenic greenhouse gases, ozone, aerosols and land-use change. The MME is used in an analysis of variance method to separate the internal (natural) variability in the Phillips Criterion from influences associated with anomalous external radiative forcing. In all seasons, the leading externally forced mode has a significant trend and a loading pattern highly correlated with the pattern of trends in the Phillips Criterion. The covariance between the externally forced component of SH rainfall and the leading external mode strongly resembles the MME pattern of SH rainfall trends. A comparison between similar analyses of MME simulations using the second half of the twenty-first century of the Representative Concentration Pathways (RCP) RCP8.5 and RCP4.5 scenarios show that trends in the Phillips Criterion and rainfall are projected to continue and intensify under increasing anthropogenic greenhouse gas concentrations.

SU‐F‐J‐142: Proposed Method to Broaden Inclusion Potential of Patients Able to Use the Calypso Tracking System in Prostate Radiotherapy

Purpose:To introduce a non‐standard method of patient setup, using BellyBoard immobilization, to better utilize the localization and tracking potential of an RF‐beacon system with EBRT for prostate cancer.Methods:An RF‐beacon phantom was imaged using a wide bore CT scanner, both in a standard level position and with a known rotation (4° pitch and 7.5° yaw). A commercial treatment planning system (TPS) was used to determine positional coordinates of each beacon, and the centroid of the three beacons for both setups. For each setup at the Linac, kV AP and Rt Lateral images were obtained. A full characterization of the RF‐beacon system in clinical mode was completed for various beacons’ array‐to‐centroid distances, which includes vertical, lateral, and longitudinal offset data, as well as pitch and yaw offset measurements for the tilted phantom. For the single patient who has been setup using the proposed BellyBoard method, a supine simulation was first obtained. When abdominal protrusion was found to be exceeding the limits of the RF‐Beacon system through distance‐based analysis in the TPS, the patient is re‐simulated prone with the BellyBoard. Array to centroid distance is measured again in the TPS, and if found to be within the localization or tracking region it is applied.Results:Characterization of limitations for the RF‐beacon system in clinical mode showed acceptable consistency of offset determination for phantom setup accuracy. The nonstandard patient setup method reduced the beacons’ centroid‐to‐array distance by 8.32cm, from 25.13cm to 16.81cm; completely out of tracking range (greater than 20cm) to within setup tracking range (less than 20cm).Conclusion:Using the RF‐beacon system in combination with this novel patient setup can allow patients who would otherwise not be candidates for beacon enhanced EBRT to now be able to benefit from the reduced PTV margins of this treatment method.

Retrieval of ice cloud properties using an optimal estimation algorithm and MODIS infrared observations: 2. Retrieval evaluation

AbstractAn infrared‐based optimal estimation (OE‐IR) algorithm for retrieving ice cloud properties is evaluated. Specifically, the implementation of the algorithm with MODerate resolution Imaging Spectroradiometer (MODIS) observations is assessed in comparison with the operational retrieval products from MODIS on the Aqua satellite (MYD06), Cloud‐Aerosol Lidar with Orthogonal Polarization (CALIOP), and the Imaging Infrared Radiometer (IIR); the latter two instruments fly on the Cloud‐Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) satellite in the Afternoon Constellation (A‐Train) with Aqua. The results show that OE‐IR cloud optical thickness (τ) and effective radius (reff) retrievals perform best for ice clouds having 0.5 < τ < 7 and reff < 50 µm. For global ice clouds, the averaged retrieval uncertainties of τ and reff are 19% and 33%, respectively. For optically thick ice clouds with τ larger than 10, however, the τ and reff retrieval uncertainties can exceed 30% and 50%, respectively. For ice cloud top height (h), the averaged global uncertainty is 0.48 km. Relatively large h uncertainty (e.g., > 1 km) occurs for τ < 0.5. Analysis of 1 month of the OE‐IR retrievals shows large τ and reff uncertainties in storm track regions and the southern oceans where convective clouds are frequently observed, as well as in high‐latitude regions where temperature differences between the surface and cloud top are more ambiguous. Generally, comparisons between the OE‐IR and the operational products show consistent τ and h retrievals. However, obvious differences between the OE‐IR and the MODIS Collection 6 reff are found.

Transport in Bulk Superconductors: A Practical Approach?

The characterization of the critical current density of bulk high-temperature superconductors is typically performed using magnetometry, which involves numerous assumptions, including, significantly, that $J_{{c}}$ within the sample is uniform. Unfortunately, magnetometry is particularly challenging to apply where a local measurement of $J_{{c}}$ across a feature, such as a grain boundary, is desired. Although transport measurements appear to be an attractive alternative to magnetization, it is extremely challenging to reduce the cross-sectional area of a bulk sample sufficiently to achieve a sufficiently low critical current that can be generated by a practical current source. In the work described here, we present a technique that enables transport measurements to be performed on sections of bulk superconductors. Metallographic techniques and resin reinforcement were used to create an I-shaped sample of bulk superconductor from a section of Gd–Ba–Cu–O containing 15 wt % Ag2O. The resulting superconducting track had a cross-sectional area of 0.44 mm2. The sample was found to support a critical current of 110 A using a field criterion in the narrowed track region of 1 $\mu\text{V cm}^{-1}$ . We conclude, therefore, that it is possible to measure critical current densities in excess of $2.5 \times 10^{8} \text{A m}^{-2}$ in sections of a bulk superconductor.

Target-free approach for vision-based structural system identification using consumer-grade cameras

Recent reports on America's infrastructure have emphasized the importance of structural health monitoring of civil infrastructures. System identification is a key component of many structural health monitoring strategies. Current system identification methods estimate models of a structure by measuring displacements, accelerations, and strains with wired or wireless sensors. However, these methods typically involve installation of a limited number of sensors at discrete locations and require additional data acquisition devices. To overcome these limitations, computer vision-based techniques have been introduced recently that employ high-speed and high-resolution cameras. Such cameras can be quite costly and require tedious installation of targets. This paper investigates the potential of using consumer-grade cameras for structural system identification without the need to install targets. The underlying methods for target-free displacement measurements are introduced, including region of interest selection, feature detection, point tracking, and outlier removal. A set of experiments are conducted to assess the efficacy of the proposed approach by comparing the accuracy of the identified model with one obtained using a conventional wired system. Careful comparison of the results demonstrates the significant potential of the proposed approach. Copyright © 2016 John Wiley & Sons, Ltd.

Early online detection of high volatility clusters using Particle Filters

This work presents a novel online early detector of high-volatility clusters based on uGARCH models (a variation of the GARCH model), risk-sensitive particle-filtering-based estimators, and hypothesis testing procedures. The proposed detector utilizes Risk-Sensitive Particle Filters (RSPF) to generate an estimate of the volatility probability density function (PDF) that offers better resolution in the areas of the state-space that are associated with the incipient appearance of high-volatility clusters. This is achieved using the Generalized Pareto Distribution for the generation of particles. Risk-sensitive estimates are used by a detector that evaluates changes between prior and posterior probability densities via asymmetric hypothesis tests, allowing early detection of sudden volatility increments (typically associated with early stages of high-volatility clusters). Performance of the proposed approach is compared to other implementations based on the classic Particle Filter, in terms of its capability to track regions of the state-space associated to a greater financial risk. The proposed volatility cluster detection scheme is tested and validated using both simulated and actual IBM’s daily stock market data.

Experience from design, prototyping and production of a DC-DC conversion powering scheme for the CMS Phase-1 Pixel Upgrade

The CMS collaboration has adopted a DC-DC conversion powering scheme for the Phase-1 Upgrade of its pixel detector. DC-DC buck converters with a conversion ratio of around 3 are installed on the support structures, outside of the sensitive tracking region, requiring a re-design of the low and high voltage distribution to the pixel modules. After several years of R&D, the project has entered the production phase. A total of 1800 DC-DC converters are being produced, and rigorous quality assurance and control is being employed during the production process. The testing program is outlined, results from mass production are presented and issues that have been encountered are described. In addition, two system level challenges, namely the choice of output voltage in the presence of large, load-dependent voltage drops, and the thermal management required to remove the heat load caused by the DC-DC converters, are discussed.

Power Control of BDFRG Variable-Speed Wind Turbine System Covering All Wind Velocity Ranges

In this paper, a power control strategy for the brushless doubly fed reluctance generator (BDFRG) based variable-speed wind turbine system is proposed. The proposed control strategy covers all system operational regions including: maximum power point tracking (MPPT) region, constant speed region, and constant power region; whereas, the studies in the literature for the BDFRG wind turbine system are only limited to the MPPT region. For capturing maximum power from the wind in the MPPT region, a turbine power feedback based MPPT, which is a method with fast dynamic response, is used. In the constant speed region, the BDFRG speed is kept constant, and for high wind velocities in constant power region, the controller decreases the BDFRG speed to prevent the increase of the turbine power more than its rated value. In addition, a turbine power observer is proposed to obtain turbine power. The BDFRG wind turbine system model based their dynamic equations, which explained in the paper, is simulated in MATLAB/Simulink software and the performance of the proposed control strategy is studied. The simulation results verify the effectiveness of the proposed control strategy in all three operational regions as well as the acceptable performance of the turbine power observer.

Robotic Visual Tracking of Relevant Cues in Underwater Environments with Poor Visibility Conditions

Using visual sensors for detecting regions of interest in underwater environments is fundamental for many robotic applications. Particularly, for an autonomous exploration task, an underwater vehicle must be guided towards features that are of interest. If the relevant features can be seen from the distance, then smooth control movements of the vehicle are feasible in order to position itself close enough with the final goal of gathering visual quality images. However, it is a challenging task for a robotic system to achieve stable tracking of the same regions since marine environments are unstructured and highly dynamic and usually have poor visibility. In this paper, a framework that robustly detects and tracks regions of interest in real time is presented. We use the chromatic channels of a perceptual uniform color space to detect relevant regions and adapt a visual attention scheme to underwater scenes. For the tracking, we associate with each relevant point superpixel descriptors which are invariant to changes in illumination and shape. The field experiment results have demonstrated that our approach is robust when tested on different visibility conditions and depths in underwater explorations.

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization.

To first demonstrate the viability of applying an image processing technique for tracking regions on low-contrast cine-MR images acquired during image-guided radiation therapy, and then outline a scheme that uses tracking data for optimizing gating results in a patient-specific manner. A first-generation MR-IGRT system-treating patients since January 2014-integrates a 0.35 T MR scanner into an annular gantry consisting of three independent Co-60 sources. Obtaining adequate frame rates for capturing relevant patient motion across large fields-of-view currently requires coarse in-plane spatial resolution. This study initially (1) investigate the feasibility of rapidly tracking dense pixel correspondences across single, sagittal plane images (with both moderate signal-to-noise and spatial resolution) using a matching objective for highly descriptive vectors called scale-invariant feature transform (SIFT) descriptors associated to all pixels that describe intensity gradients in local regions around each pixel. To more accurately track features, (2) harmonic analysis was then applied to all pixel trajectories within a region-of-interest across a short training period. In particular, the procedure adjusts the motion of outlying trajectories whose relative spectral power within a frequency bandwidth consistent with respiration (or another form of periodic motion) does not exceed a threshold value that is manually specified following the training period. To evaluate the tracking reliability after applying this correction, conventional metrics-including Dice similarity coefficients (DSCs), mean tracking errors (MTEs), and Hausdorff distances (HD)-were used to compare target segmentations obtained via tracking to manually delineated segmentations. Upon confirming the viability of this descriptor-based procedure for reliably tracking features, the study (3) outlines a scheme for optimizing gating parameters-including relative target position and a tolerable margin about this position-derived from a probability density function that is constructed using tracking results obtained just prior to treatment. The feasibility of applying the matching objective for SIFT descriptors toward pixel-by-pixel tracking on cine-MR acquisitions was first retrospectively demonstrated for 19 treatments (spanning various sites). Both with and without motion correction based on harmonic analysis, sub-pixel MTEs were obtained. A mean DSC value spanning all patients of 0.916 ± 0.001 was obtained without motion correction, with DSC values exceeding 0.85 for all patients considered. While most patients show accurate tracking without motion correction, harmonic analysis does yield substantial gain in accuracy (defined using HDs) for three particularly challenging subjects. An application of tracking toward a gating optimization procedure was then demonstrated that should allow a physician to balance beam-on time and tissue sparing in a patient-specific manner by tuning several intuitive parameters. Tracking results show high fidelity in assessing intrafractional motion observed on cine-MR acquisitions. Incorporating harmonic analysis during a training period improves the robustness of the tracking for challenging targets. The concomitant gating optimization procedure should allow for physicians to quantitatively assess gating effectiveness quickly just prior to treatment in a patient-specific manner.