Segmentation Tracking Research Articles

Measurement of the electron reconstruction efficiency at LHCb

The single electron track-reconstruction efficiency is calibrated using a sample corresponding to 1.3 fb−1 of pp collision data recorded with the LHCb detector in 2017. This measurement exploits B+→ J/ψ(e+e−)K+ decays, where one of the electrons is fully reconstructed and paired with the kaon, while the other electron is reconstructed using only the information of the vertex detector. Despite this partial reconstruction, kinematic and geometric constraints allow the B meson mass to be reconstructed and the signal to be well separated from backgrounds. This in turn allows the electron reconstruction efficiency to be measured by matching the partial track segment found in the vertex detector to tracks found by LHCb's regular reconstruction algorithms. The agreement between data and simulation is evaluated, and corrections are derived for simulated electrons in bins of kinematics. These correction factors allow LHCb to measure branching fractions involving single electrons with a systematic uncertainty below 1%.

On-track Tests for the Running Stability of a Metro Trainset

A field test on-track was conducted to verify the running stability of a metro train according to UIC 515 through measuring the lateral acceleration on the bogie frame. In this test, various running speeds, load case, running directions and three track lines were examined. The test scope, method and specification are presented as well as the test instruments and data processing. It is found that the running stability in bogies of the trainset are quite different on various track segments. The stability performances of each bogie for a specific train under various load cases and running directions on various track segment are suggested to be examined.

MAVNet: An Effective Semantic Segmentation Micro-Network for MAV-Based Tasks

Real-time semantic image segmentation on platforms subject to size, weight, and power constraints is a key area of interest for air surveillance and inspection. In this letter, we propose MAVNet: a small, light-weight, deep neural network for real-time semantic segmentation on micro aerial vehicles (MAVs). MAVNet, inspired by ERFNet [E. Romera, J. M. lvarez, L. M. Bergasa, and R. Arroyo, “ErfNet: Efficient residual factorized convnet for real-time semantic segmentation,” IEEE Trans. Intell. Transp. Syst. , vol. 19, no. 1, pp. 263–272, Jan. 2018.], features 400 times fewer parameters and achieves comparable performance with some reference models in empirical experiments. Additionally, we provide two novel datasets that represent challenges in semantic segmentation for real-time MAV tracking and infrastructure inspection tasks and verify MAVNet on these datasets. Our algorithm and datasets are made publicly available.

Goat track networks facilitate efficiency in movement and foraging

Striking networks of livestock tracks have been observed in hilly rangelands throughout the world. They have strong spatial heterogeneity in micro-topography, vegetation, soil physical properties, and hydrological and bio-geochemical processes. We have limited knowledge of the structural characteristics of these networks and their implications to energy efficiency of foraging livestock and associated land use policies. The objectives were to quantify the structure of the goat track network and the pattern of use by goats, and explore the implications of the network structure to forage efficiency and the potential mechanisms for maintenance of the network. Fifteen sites of terracette landscapes on hilly rangelands of Loess Plateau were selected. The imagery of goat tracks at each site were processed to generate a graph of the network and analyzed to examine the network structural characteristics and the pattern of use by goats. The characteristics of the goat track network, with low track angles of parallel segments and high track angles of conjunctive segments, facilitate energy-efficient movement of foraging goats and enables goats to access forage in most of the non-track areas. The goats preferred using the track segments with lower track angles and smaller turn angles. The network structure facilitates the energy efficiency of movement and forage accessibility of the goats. The network is likely maintained by goats’ preferential use of the track segments with high efficiency, which may have significant implications to the recent policy to exclude grazing over expansive regions of hilly rangelands of Loess Plateau.

Increasing Robustness by Reallocating the Margins in the Timetable

It is a common practice to improve the punctuality of a railway service by the addition of time margins during the planning process of a timetable. Due to the capacity constraints of the railway network, a limited amount of time margins can be inserted. The paper presents a model and heuristic technique to find the better position for the limited amount of time margins (headway buffers and running time supplements) in a train timetable. The aim of reallocating the time margins is to adjust an existing timetable to minimize the sum of train delays at the event of the operational disturbances. The model consists of two basic parts. Firstly, the paper treats the train timetable as a Directed Arc Graph (DAG) with the aggregation concept and proposes a heuristic technique known as Critical Time Margins Allocation (CTMA), which is based on the critical path method (CPM), to reallocate the time margins. Secondly, the paper evaluates the original and modified timetable under different disturbed situations. The case study is developed on a hypothetical small railway network and a practical timetable of single-line train timetable for the track segment of Rawalpindi to Lalamusa, Pakistan. The results show that the timetable modified with the CTMA reduces the total delay time by an average of 3.25% for the small railway network and 5.18% for the large dataset. It suggests that adding the time supplements to the proper positions in a timetable can reduce the delay propagation and increase the robustness of the timetable.

Segment-averaged LET concept and analytical calculation from microdosimetric quantities in proton radiation therapy.

This work introduces the concept of segment-averaged linear energy transfer (LET) as a new approach to average distributions of LET of proton beams based on a revisiting of microdosimetry theory. The concept of segment-averaged LET is then used to generate an analytical model from Monte Carlo simulations data to perform fast and accurate calculations of LET distributions for proton beams. The distribution of energy imparted by a proton beam into a representative biological structure or site is influenced by the distributions of (a) LET, (b) segment length, which is the section of the proton track in the site, and (c) energy straggling of the proton beam. The distribution of LET is thus generated by the LET of each component of the beam in the site. However, the situation when the LET of each single proton varies appreciably along its path in the site is not defined. Therefore, a new distribution can be obtained if the particle track segment is decomposed into smaller portions in which LET is roughly constant. We have called "segment distribution" of LET the one generated by the contribution of each portion. The average of that distribution is called segment-averaged LET. This quantity is obtained in the microdosimetry theory from the average and standard deviation of the distributions of energy imparted to the site, segment length, and energy imparted per collision. All this information is calculated for protons of clinically relevant energies by means of Geant4-DNA microdosimetric simulations. Finally, a set of analytical functions is proposed for each one of the previous quantities. The presented model functions are fitted to data from Geant4-DNA simulations for monoenergetic beams from 100keV to 100MeV and for spherical sites of 1, 5, and 10μm in diameter. The average differences along the considered energy range between calculations based on our analytical models and MC for segment-averaged dose-averaged restricted LET are -0.2±0.7keV/μm for the 1μm case, 0.0±0.9keV/μm for the 5μm case, and -0.3±1.1keV/μm for the 10μm case, respectively. All average differences are below the average standard deviation (1σ) of the MC calculations. A new way of averaging LET for a proton beam is performed to incorporate the effects produced by the variation of stopping power of each individual proton along microscopic biological structures. An analytical model based on MC simulations allows for fast and accurate calculations of segment-averaged dose-averaged restricted LET for proton beams, which otherwise would need to be calculated from exhaustive MC simulations of clinical plans.

Dose-averaged LET calculation for proton track segments using microdosimetric Monte Carlo simulations.

There is an increasing interest in calculating linear energy transfer (LET) distributions for proton therapy treatments in order to assess the influence of this quantity in biological terms. Microdosimetric Monte Carlo (MC) simulations are useful tools to calculate dose-averaged LET, as this has been broadly proposed as the most adequate quantity to characterize these biological effects. However, a straightforward uniform sampling of the scoring site turns out to be computationally unaffordable. In contrast, some issues have been pointed out with the more efficient weighted sampling approach, frequently used in literature. Here, we address the issues associated with the latter method and propose adequate corrections to achieve reliable calculations of dose-averaged LET values from microdosimetry. Proton track structures have been simulated with Geant4-DNA considering two different approaches. One version employs a uniform sampling for placing the spherical site and is used as the reference. The other one uses a weighted sampling by considering the spatial distribution of transfer points. Some corrections are proposed for calculating a dose-averaged LET comparable to the reference case. An additional MC approach is proposed to obtain the weighted mean of the energy imparted per electronic collision of the proton within the site, the function, related to the straggling distribution, as an intermediate step in the LET calculation. Energy imparted per event distributions are different when employing either sampling methods, due to the different geometrical randomness. We have found an agreement below (0.15±0.05)keV/μm in the worst case for uniform and weighted methods in dose-averaged LET values when the weighted sampling results are corrected according to our proposal. Our analysis is restricted to spherical sites of 1 and 10μm diameter and monoenergetic beams in the range from 2 to 90MeV. This work shows a reliable and computational-efficient method to perform calculations of track segment dose-averaged LET using MC simulations for proton therapy beams, including the necessary considerations for obtaining the straggling distribution characteristics. The validity of this approach remains as long as the stopping power of the proton can be considered as constant along its track within the site.

Patch-based adaptive weighting with segmentation and scale (PAWSS) for visual tracking in surgical video.

Vision-based tracking in an important component for building computer assisted interventions in minimally invasive surgery as it facilitates estimation of motion for instruments and anatomical targets. Tracking-by-detection algorithms are widely used for visual tracking, where the problem is treated as a classification task and a tracking target appearance model is updated over time using online learning. In challenging conditions, like surgical scenes, where tracking targets deform and vary in scale, the update step is prone to include background information in model appearance or to lack the ability to estimate change of scale, which degrades the performance of classifier. In this paper, we propose a Patch-based Adaptive Weighting with Segmentation and Scale (PAWSS) tracking framework that tackles both scale and background problems. A simple but effective colour-based segmentation model is used to suppress background information and multi-scale samples are extracted to enrich the training pool, which allows the tracker to handle both incremental and abrupt scale variations between frames. Experimentally, we evaluate our approach on Online Tracking Benchmark (OTB) dataset and Visual Object Tracking (VOT) challenge datasets, showing that our approach outperforms recent state-of-the-art trackers, and it especially improves successful rate score on OTB dataset, while on VOT datasets, PAWSS ranks among the top trackers while operating at real-time frame rates. Focusing on the application of PAWSS to surgical scenes, we evaluate on MICCAI 2015 challenge instrument tracking challenge and in vivo datasets, showing that our approach performs the best among all submitted methods and also has promising performance on in vivo surgical instrument tracking.

PELACAKAN DAN SEGMENTASI OBJEK BERGERAK MENGGUNAKAN METODE K-MEANS CLUSTERING BERBASIS VARIASI JARAK

In computer vision tracking and object segmentation is one important step in video processing. Accuracy in object tracking is important in video processing, where accurate object tracking is a thing that continues to be done by many researchers. there are still many problems that are often experienced when tracking objects in terms of lighting, noise up to a high level of error. Many methods can be used in research, one of which is clustering method. Clustering method is a method that is widely used in grouping data, one of which is often used is Kmeans clustering. This method is very flexible, and is able to classify large amounts of data. Besides that, Kmeans is also able to work adeptly and segment the image well. For this study using 5 distance approaches (cambera, chebychef, mahattan, minkowski, Euclidean) distance approach which is expected to improve the results of better accuracy. From the results of the research produced a mahatan distance approach has the best accuracy results with a PNSR value of 16,34399 and the lowest MSE value with a value of 1521,793. Compared to the use of standard models with Euclidean, the approach of high distance accuracy increases

Trajectory-based gait pattern shift detection for assistive robotics applications

In the medical field, rehabilitation of the lower limbs is a slow and continuous process, where healthcare professionals have to follow each patient over long periods of time. In conventional rehabilitation, the progression of a patient is assessed by a professional, who analyzes visual tracking data. This assessment is dependent on each professional’s own experience. In this paper, we propose an approach to analyze tracking data, captured by our robotic walker’s gait tracking system, to detect shifts in the gait pattern over time automatically. For this purpose, the system takes in gait tracking data and segments it into gait cycles (heel strike to heel strike). Then, our approach handles each gait cycle considering it as a group of gait parameters that define trajectories in that time frame. From each gait parameter within the cycle, spatiotemporal features are extracted and similarity rates are computed using autoencoders. These spatiotemporal features and similarity rates are fused in a feature space which is fed to a one-class support vector machine that constructs a model of the observable gait cycle. Each posterior observed gait cycle is checked for shifts, using a set of proposed novelty detection techniques. Experimental tests using a dataset captured using our robotic walker platform revealed a promising performance when detecting if a gait cycle is ‘reference’ or ‘novel’ when compared to a previously trained model of a unique ‘reference’ gait pattern.

MODIFICATION OF TOOL FOR MOVING TRACK SEGMENTS IN DELTA DESIGN CAD

Describes the process of improving and developing tools in computer‑aided design system Delta Design. Currently, the modern process of PCB development is quite complex and time‑consuming process. Existing CAD systems make it easier to design a printed circuit Board model by providing powerful development tools. Along with the increasing complexity of modern printed circuit boards, the requirements for development tools are also growing, making them constantly improve. Using the example of the Delta Design system, the process of improving the tool for moving track segments is described. The analysis of the advantages and disadvantages of the existing tool is made, and the decision on the need to develop a new algorithm is justified. Of the two proposed variants of such an algorithm, the optimal one was chosen in terms of the quality of the result obtained and the convenience of operation.

An Adaptive Track Segmentation Algorithm for a Railway Intrusion Detection System.

Video surveillance-based intrusion detection has been widely used in modern railway systems. Objects inside the alarm region, or the track area, can be detected by image processing algorithms. With the increasing number of surveillance cameras, manual labeling of alarm regions for each camera has become time-consuming and is sometimes not feasible at all, especially for pan-tilt-zoom (PTZ) cameras which may change their monitoring area at any time. To automatically label the track area for all cameras, video surveillance system requires an accurate track segmentation algorithm with small memory footprint and short inference delay. In this paper, we propose an adaptive segmentation algorithm to delineate the boundary of the track area with very light computation burden. The proposed algorithm includes three steps. Firstly, the image is segmented into fragmented regions. To reduce the redundant calculation in the evaluation of the boundary weight for generating the fragmented regions, an optimal set of Gaussian kernels with adaptive directions for each specific scene is calculated using Hough transformation. Secondly, the fragmented regions are combined into local areas by using a new clustering rule, based on the region’s boundary weight and size. Finally, a classification network is used to recognize the track area among all local areas. To achieve a fast and accurate classification, a simplified CNN network is designed by using pre-trained convolution kernels and a loss function that can enhance the diversity of the feature maps. Experimental results show that the proposed method finds an effective balance between the segmentation precision, calculation time, and hardware cost of the system.

NON-RIGID MULTI-BODY TRACKING IN RGBD STREAMS

Abstract. To efficiently collect training data for an off-the-shelf object detector, we consider the problem of segmenting and tracking non-rigid objects from RGBD sequences by introducing the spatio-temporal matrix with very few assumptions – no prior object model and no stationary sensor. Spatial temporal matrix is able to encode not only spatial associations between multiple objects, but also component-level spatio temporal associations that allow the correction of falsely segmented objects in the presence of various types of interaction among multiple objects. Extensive experiments over complex human/animal body motions with occlusions and body part motions demonstrate that our approach substantially improves tracking robustness and segmentation accuracy.

On the initial approximation of charged particle tracks in detectors with linear sensing elements

The search for charged particle tracks in detectors with linear sensing elements, such as wire chambers, strip silicon detectors etc., starts with identification of straight track segments. The latter are deduced by constructing all possible combinations of activated detector elements. In the high multiplicity environment, with many activated detector elements, this causes large combinatorics and significantly reduces the performance of the track finding algorithms. In this report we trace this problem back to determination of the parameters of a straight line build from a number of skew lines (sensing elements of a detector) in space. Based on the intersection points of two hyperbolas, we demonstrate an analytic solution in the case of four skew detector elements.The procedure can also be applied as a first approximation to the more general case of curved track finding.

Acquiring observations for test and validation in the space surveillance and tracking segment of ESA's SSA Programme

This paper describes selected current and planned optical (both passive and laser ranging) and radar observations data acquisition campaigns conducted by ESA's SSA Programme. One of these initiatives comprises the qualification of optical sensors. First qualification results from several telescopes are presented. The concept of an Expert Centre interfacing the SSA Space Surveillance and Tracking (SST) data centre and external sensors (optical passive telescopes and laser ranging sensors) is described that is found relevant for the community of optical observers in SST. Results from the validation and qualification campaigns performed to Borowiec laser station and ESA's Test-bed telescope in Cebreros are reported. ESA's two half-metre class telescopes on robotic mounts have been integrated in the frame of a technology development programme. Following an in-factory qualification programme, under human supervision and involving commercial, off-the-shelf processing software, for full-end autonomy and robustness testing, the deployment to final sites, covering both hemispheres, is expected to finalise in 2018. Main figure of merits of these robotic telescopes are described. ESA's test-bed radars also participated in several coordinated campaigns. We present first results of the quality assessment in this paper.

Metro transit system resilience: Understanding the impacts of outdoor tracks and weather conditions on metro system interruptions

One of the main challenges facing transit agencies is offering reliable service with minimum number of interruptions and ensuing delays. Although this issue has recently emerged as a top priority in many cities to ensure sustainable social and environmental progress, there has been little research effort to investigate issues surrounding service disruption. As a response to this gap, this study aims at understanding the impact of outdoor track segments (or open-air sectors) of the metro system and weather conditions on the number of service interruptions and the magnitude of resulting delays at the stop level. The study uses detailed metro system interruption data collected in 2013 by the TTC, the public transit provider in the City of Toronto, Canada. Descriptive statistics and statistical models are developed for the purpose of the study. The empirical investigation reveals that outdoor tracks have a statistically significant association with metro system’s service interruptions. Longer outdoor track distances are linked to both higher frequencies and delays of service interruptions. Weather conditions, in terms of the amount of snow on the ground and rainfall interactions with outdoor tracks, have also a significant association with the frequency and duration of service interruptions. The paper results provide policy makers and planners with useful policy-relevant information related to the impact of outdoor tracks and weather conditions on the metro system interruptions that could be used to support higher capital investments when planning rail transit systems to achieve the system resilience.

Automatic diaphragm segmentation for real-time lung tumor tracking on cone-beam CT projections: a convolutional neural network approach

Purpose: To automatically segment the diaphragm on individual lung cone-beam CT projection images, to enable real-time tracking of lung tumors using kilovoltage imaging. Methods: The deep neural network Mask R-CNN was trained on 3500 raw cone-beam CT projection images from 10 lung cancer patients, with the diaphragm manually segmented on each image used as a ground truth label. Ground-truth breathing traces were extracted from each patient for both diaphragm hemispheres, and apex positions were compared against the predicted output of the neural network. Ten-fold cross-validation was used to evaluate the segmentation accuracy. Results: The mean diaphragm apex prediction error was 4.4 mm. The mean percentage of projection images for which a successful prediction could me made was 87.3%. Prediction accuracy at some lateral gantry angles was worse due to overlap between diaphragm hemispheres, and the increased amount of fatty tissue. Conclusions: The neural network was able to track the diaphragm apex position successfully. This allows accurate assessment of the breathing phase, which can be used to estimate the position of the lung tumor in real time.

GPS tracking data reveals daily spatio-temporal movement patterns of waterfowl

BackgroundSpatio-temporal patterns of movement can characterize relationships between organisms and their surroundings, and address gaps in our understanding of species ecology, activity budgets, bioenergetics, and habitat resource management. Highly mobile waterfowl, which can exploit resources over large spatial extents, are excellent models to understand relationships between movements and resource usage, landscape interactions and specific habitat needs.MethodsWe tracked 3 species of dabbling ducks with GPS-GSM transmitters in 2015–17 to examine fine-scale movement patterns over 24 h periods (30 min interval), dividing movement pathways into temporally continuous segments and spatially contiguous patches. We quantified distances moved, area used and time allocated across the day, using linear and generalized linear mixed models. We investigated behavior through relationships between these variables.ResultsMovements and space-use were small, and varied by species, sex and season. Gadwall (Mareca strepera) generally moved least (FFDs: 0.5–0.7 km), but their larger foraging patches resulted from longer within-area movements. Pintails (Anas acuta) moved most, were more likely to conduct flights > 300 m, had FFDs of 0.8–1.1 km, used more segments and patches per day that they revisited more frequently, resulting in the longest daily total movements. Females and males differed only during the post-hunt season when females moved more. 23.6% of track segments were short duration (1–2 locations), approximately 1/3 more than would be expected if they occurred randomly, and were more dispersed in the landscape than longer segments. Distance moved in 30 min shortened as segment duration increased, likely reflecting phases of non-movement captured within segments.ConclusionsPacific Flyway ducks spend the majority of time using smaller foraging and resting areas than expected or previously reported, implying that foraging areas may be highly localized, and nutrients obtainable from smaller areas. Additionally, movement reductions over time demonstrates behavioral adjustments that represent divergent energetic demands, the detection of which is a key advantage of higher frequency data. Ducks likely use less energy for movement than currently predicted and management, including distribution and configuration of essential habitat, may require reconsideration. Our study illustrates how fine-scale movement data from tracking help understand and inform various other fields of research.

Experimental study of the vibration characteristics of the floating slab track in metro turnout zones

In railway turnout areas, vertical and horizontal structure irregularities, including geometry and stiffness, result in vibration amplification during the passage of trains. These vibrations can then spread to the surrounding environment. A steel spring floating slab track may be used to control such vibrations, especially in metro-type urban railways. An experimental study was conducted to investigate the vibration-mitigating effects of the floating slab track in turnout areas, and the results were compared with the performance of a regular slab track. Four test cases (consisting of six test sections) were selected: a floating slab track in the turnout zone (consisting of a switch rail section and a nose rail section), a floating slab track in the plain line, a slab track in the turnout zone (consisting of a switch rail section and a nose rail section), and a slab track in the plain line. The vibration characteristics of the floating slab track in the plain line and in the turnout were calculated to explain the test results. The test results indicate that when trains pass across the floating slab track in the turnout zone, the vertical vibration response is close to the horizontal response on the switch rail sections. The use of floating slab track can effectively reduce this vertical vibration. However, the vertical vibration response is much larger than the horizontal response on the nose rail sections of the turnout zone. When the floating slab track is used in these turnout zones, the vertical vibration of the rail decreases while the horizontal vibration increases. Compared to sections using the regular slab track in the turnout zone, the vibration of the floating slab track segments in the turnout zone is shown to be exacerbated, although the vibration level at the adjacent tunnel wall is effectively reduced.

An alternative procedure to measure railroad track irregularities. Application to a scaled track

In this paper an alternative procedure to accurately measure static railroad track irregularities is proposed and applied to a scaled railroad track. The purpose of this work is the determination of highly-precise measured data in short track segments that needs to be used as input in the validation of railroad computational models that are used for on-board railroad track measurement systems. The procedure consists of the use of a topographic total station combined with a postprocessing of the measured data that reduces misalignment errors and provide the analytical ideal geometry of the track together with its irregular geometry characterized in terms of the magnitudes of track gauge, vertical profile, alignment and cross level. Experimental results are compared to standard magnitudes of full scale tracks showing that real track geometry can differ from PSD-based predicted one. This supports the application of the proposed procedure for an accurate geometric determination of short track segments.