Segmentation Tracking Research Articles

Multistep Track Segmentation and Motion Classification for Transient Mobility Analysis

Molecular interactions are often transient and might change within the window of observation, leading to changes in molecule movement. Therefore, accurate motion analysis often requires transient motion classification. Here we present an accurate and computationally efficient transient mobility analysis framework, termed “divide-and-conquer moment scaling spectrum” (DC-MSS). DC-MSS works in a multistep fashion: 1) it utilizes a local movement descriptor throughout a track to divide it into initial segments of putatively different motion classes; 2) it classifies these segments via moment scaling spectrum (MSS) analysis of molecule displacements; and 3) it uses the MSS analysis results to refine the track segmentation. This strategy uncouples the initial identification of motion switches from motion classification, allowing DC-MSS to circumvent the sensitivity-accuracy tradeoff of classic rolling window approaches for transient motion analysis, while at the same time harnessing the classification power of MSS analysis. Testing of DC-MSS demonstrates that it detects switches among free diffusion, confined diffusion, directed diffusion, and immobility with great sensitivity. To illustrate the utility of DC-MSS, we have applied it to single-particle tracks of the transmembrane protein CD44 on the surface of macrophages, revealing actin cortex-dependent transient mobility changes.

FatRegion: A Fast Adaptive Tree-Structured Region Extraction Approach

Coherent image regions can be used as good features for many computer vision tasks, such as object tracking, segmentation, and recognition. Most of previous region extraction methods, however, are not suitable for online applications because of their either heavy computations or unsatisfactory results. We propose a seed-based region growing and merging approach to generate simultaneously coherent and discriminative image regions. We present a quadtree-based seed initialization algorithm to adaptively place seeds into different image areas and then grow them into regions by a color- and edge-guided growing procedure. To merge these regions in different levels, we propose to use the generalized boundary strength to measure the quality of region merging result. In addition, we present a region merging algorithm of linear time complexity to perform efficient and effective region merging. Overall, our new approach simultaneously holds these advantages: 1) it is extremely fast with linear complexity in both time and space, which takes less than 50 ms to process an HVGA image; 2) it can give a direct control of the region number and well adapt to image regions with various sizes and shapes; and 3) it provides a tree-structured representation of the regions and thus can model the image from multiple scales. We evaluate the proposed approach on the standard benchmarks with extensive comparisons with the state-of-the-art methods. The experimental results demonstrate its good comprehensive performances. Example applications using the extracted regions as features for online object tracking and multiclass object segmentation also exhibit its potential for many computer vision tasks.

Test beam demonstration of silicon microstrip modules with transverse momentum discrimination for the future CMS tracking detector

A new CMS Tracker is under development for operation at the High Luminosity LHC from 2026 onwards. It includes an outer tracker based on dedicated modules that will reconstruct short track segments, called stubs, using spatially coincident clusters in two closely spaced silicon sensor layers. These modules allow the rejection of low transverse momentum track hits and reduce the data volume before transmission to the first level trigger. The inclusion of tracking information in the trigger decision is essential to limit the first level trigger accept rate. A customized front-end readout chip, the CMS Binary Chip (CBC), containing stub finding logic has been designed for this purpose. A prototype module, equipped with the CBC chip, has been constructed and operated for the first time in a 4 GeV/c positron beam at DESY. The behaviour of the stub finding was studied for different angles of beam incidence on a module, which allows an estimate of the sensitivity to transverse momentum within the future CMS detector. A sharp transverse momentum threshold around 2 GeV/c was demonstrated, which meets the requirement to reject a large fraction of low momentum tracks present in the LHC environment on-detector. This is the first realistic demonstration of a silicon tracking module that is able to select data, based on the particle's transverse momentum, for use in a first level trigger at the LHC . The results from this test are described here.

RETRACTED ARTICLE: Visualized image segmentation for multi-object tracking by weak clustering technique

RETRACTED ARTICLE: Visualized image segmentation for multi-object tracking by weak clustering technique

Acceleration sensor technology for rail track asset condition monitoring

In the rail traffic industry, the utilisation of inexpensive real-time sensors and the industrial internet of things for proactive asset management is a relatively new concept with great potential. As railways are one of the longest-lasting infrastructure assets, even marginal efficiency and cost gains have a significant impact on the life-cycle cost. This paper shows how wireless three-dimensional acceleration sensor technology can be applied to monitor track condition. The data collection was carried out in October 2016 on a railway line operated by Finnish Railways. In the test, a sensor was attached to a train unit and the acceleration of the train on a track segment was repeatedly measured at variable speeds. The collected data set was enhanced using map-matching and Bayesian filtering in order to improve the Global Positioning System location accuracy of the data. The filtered acceleration signals were analysed, and detected anomalies were compared against known parameters such as bridges and switches. The results of the testing support the feasibility of the concept. Finally, the implications of the concept regarding proactive asset management of track networks and statistical process control-based monitoring of tracks’ condition are discussed.

Large Area Coverage of a TPC Endcap with GridPix Detectors

The Large Prototype TPC at DESY, Hamburg, was built by the LCTPC collaboration as a testbed for new readout technologies of Time Projection Chambers. Up to seven modules of about 400 cm2 each can be placed in the endcap. Three of these modules were equipped with a total of 160 GridPix detectors. This is a combination of a highly pixelated readout ASIC and a Micromegas built on top. GridPix detectors have a very high efficiency of detecting primary electrons, which leads to excellent spatial and energy resolutions. For the first time a large number of GridPix detectors has been operated and long segments of tracks have been recorded with excellent precision.

Wavelet/PSO-Based Segmentation and Marker-Less Tracking of the Gallbladder in Monocular Calibration-free Laparoscopic Cholecystectomy

This paper presents an automatic segmentation and monocular marker-less tracking method of the gallbladder in minimally invasive laparoscopic cholecystectomy intervention that can be used for the construction of an adaptive calibrationfree medical augmented reality system. In particular, the proposed method consists of three steps, namely, a segmentation of 2D laparoscopic images using a combination of photometric population-based statistical approach and edge detection techniques, a PSO-based detection of the targeted anatomical structure (the gallbladder) and, finally, the 3D model waveletbased multi-resolution analysis and adaptive 2D/3D registration. The proposed population-based statistical segmentation approach of 2D laparoscopic images differs from classical approaches (histogram thresholding), in that we consider anatomical structures and surgical instruments in terms of distributions of RGB color triples. This allows an efficient handling, superior robustness and to readily integrate current intervention information. The result of this step consists in a set of point clouds with a loosely gradient information that can cover various anatomical structures. In order to enhance both sensitivity and specificity, the detection of the targeted structure (the gallbladder) is based on a modified PSO (particles swarm optimization) scheme which maximizes both internal features density and the divergence with neighboring structures such as, the liver. Finally, a multi-particles based representation of the targeted structure is constructed, thanks to a proposed wavelet-based multi-resolution analysis of the 3D model of the targeted structure which is registered adaptively with the 2D particles generated during the previous step. Results are shown on both synthetic and real data. © 2018, (IJACSA) International Journal of Advanced Computer Science and Applications.

Color Constancy Adjustment Using Sub-Blocks of the Image

Extreme presence of the source light in digital images decreases the performance of many image processing algorithms, such as video analytics, object tracking, and image segmentation. This paper presents a color constancy adjustment technique, which lessens the impact of large unvarying color areas of the image on the performance of the existing statistical-based color correction algorithms. The proposed algorithm splits the input image into several non-overlapping blocks. It uses the average absolute difference value of each block’s color component as a measure to determine if the block has adequate color information to contribute to the color adjustment of the whole image. It is shown through experiments that by excluding the unvarying color areas of the image, the performances of the existing statistical-based color constancy methods are significantly improved. The experimental results of four benchmark image data sets validate that the proposed framework using Gray World, Max-RGB, and Shades of Gray statistics-based methods’ images have significantly higher subjective and competitive objective color constancy than those of the existing and state-of-the-art methods’ images.

An Image Segmentation Method for Global Vision Robot Fish Competition

Image segmentation is a key link of vision system of the global vision bionic robot fish, and a precondition of target localization and tracking. In this paper, we propose a visual threshold method for color image segmentation. Firstly, a visualization research on the R, G and B components in different regions of the image is carried out to find out the main factors, which influence the image segmentation effect, and then an image segmentation method is proposed based on R and B components. It is proved by experiments that the image segmentation method is simple and practical, which is more suitable for the image segmentation and target tracking in our test-bed than the Gaussian mixture model. The image segmentation method also provides reference for other fields.

Навигационные треки как альтернатива планово-высотной основы

Навигационные треки как альтернатива планово-высотной основы

Implicit and Explicit Knowledge Both Improve Dual Task Performance in a Continuous Pursuit Tracking Task.

The goal of this study was to investigate the effect of predictability on dual-task performance in a continuous tracking task. Participants practiced either informed (explicit group) or uninformed (implicit group) about a repeated segment in the curves they had to track. In Experiment 1 participants practices the tracking task only, dual-task performance was assessed after by combining the tracking task with an auditory reaction time task. Results showed both groups learned equally well and tracking performance on a predictable segment in the dual-task condition was better than on random segments. However, reaction times did not benefit from a predictable tracking segment. To investigate the effect of learning under dual-task situation participants in Experiment 2 practiced the tracking task while simultaneously performing the auditory reaction time task. No learning of the repeated segment could be demonstrated for either group during the training blocks, in contrast to the test-block and retention test, where participants performed better on the repeated segment in both dual-task and single-task conditions. Only the explicit group improved from test-block to retention test. As in Experiment 1, reaction times while tracking a predictable segment were no better than reaction times while tracking a random segment. We concluded that predictability has a positive effect only on the predictable task itself possibly because of a task-shielding mechanism. For dual-task training there seems to be an initial negative effect of explicit instructions, possibly because of fatigue, but the advantage of explicit instructions was demonstrated in a retention test. This might be due to the explicit memory system informing or aiding the implicit memory system.

Statistical Assessment of the OWZ Tropical Cyclone Tracking Scheme in ERA-Interim

AbstractThe Okubo–Weiss–Zeta (OWZ) tropical cyclone (TC) detection scheme, which has been used to detect TCs in climate, seasonal prediction, and weather forecast models, is assessed on its ability to produce a realistic TC track climatology in the ERA-Interim product over the 25-yr period 1989 to 2013. The analysis focuses on TCs that achieve gale-force (17 m s−1) sustained winds. Objective criteria were established to define TC tracks once they reach gale force for both observed and detected TCs. A lack of consistency between storm tracks preceding this level of intensity led these track segments to be removed from the analysis. A subtropical jet (STJ) diagnostic is used to terminate transitioning TCs and is found to be preferable to a fixed latitude cutoff point. TC tracks were analyzed across seven TC basins, using a probabilistic clustering technique that is based on regression mixture models. The technique grouped TC tracks together based on their geographical location and shape of trajectory in five separate “cluster regions” around the globe. A mean trajectory was then regressed for each cluster that showed good agreement between the detected and observed tracks. Other track measures such as interannual TC days and translational speeds were also replicated to a satisfactory level, with TC days showing limited sensitivity to different latitude cutoff points. Successful validation in reanalysis data allows this model- and grid-resolution-independent TC tracking scheme to be applied to climate models with confidence in its ability to identify TC tracks in coarse-resolution climate models.

Unconscious physiological response of healthy volunteers to dynamic respiration-synchronized couch motion

BackgroundIntrafractional motion can be a substantial uncertainty in precision radiotherapy. Conventionally, the target volume is expanded to account for the motion. Couch-tracking is an alternative, where the patient is moved to compensate for the tumor motion. However, the couch motion may influence the patient’s stress and respiration behavior decreasing the couch-tracking effectiveness.MethodsIn total, 100 volunteers were positioned supine on a robotic couch, which moved dynamically and respiration synchronized. During the measurement, the skin conductivity, the heartrate, and the gaze location were measured indicating the volunteer’s stress. Volunteers rated the subjective motion sickness using a questionnaire. The measurement alternated between static and tracking segments (three cycles), each 1 min long.ResultsThe respiration amplitude showed no significant difference between tracking and static segments, but decreased significantly from the first to the last tracking segment (p < 0.0001). The respiration frequency differed significantly between tracking and static segments (p < 0.0001), but not between the first and the last tracking segment. The physiological parameters and the questionnaire showed mild signals of stress and motion sickness.ConclusionGenerally, people tolerated the couch motions. The interaction between couch motion and the patient’s breathing pattern should be considered for a clinical implementation.Trial registrationThe study was registered at ClinicalTrials.gov (NCT02820532) and the Swiss national clinical trials portal (SNCTP000001878) on June 20, 2016.

Prediction of wheel profile wear and vehicle dynamics evolution considering stochastic parameters for high-speed train

The aim of this paper is to accurately predict the evolution of wheel profile wear and related vehicle dynamics for high-speed trains by considering the stochastic wheel/rail interactions, which experience quite variants with time and along long distant high-speed lines in China. These variants include the rail profiles, track geometries, track irregularities and interface characteristics associated with each segment of track. Mathematic normal distribution is introduced to rationally describe these stochastic parameters. The Archard wear model and FASTSIM algorithm are employed to determine the wear within a contact patch of the wheel, and a strategy based on the travel distance of wheel is used in the profile updating procedure. Referring to previous works, a nonlinear multibody vehicle system model is built and its accuracy was validated by lab tests. In the numerical simulation, three methods of stochastic matching of parameters in wheel/rail interactions are performed, including all constant parameters, only stochastic rail profiles, and both stochastic rail profiles and stochastic track parameters. Comparative studies show that there are good agreements in the wear evaluation of wheel profile between the simulated and measured results, as well as the behavior evaluation of vehicle dynamics in a total travel distance of 300,000km. It is essential, therefore, to consider the stochastic matchings of parameters in the wheel/rail interaction for predicting the wheel profile wear and vehicle dynamics evolution of high-speed trains.

High Linear Energy Transfer Particle Irradiation Leads to Increased Expression of In Vitro Markers of Immunogenic Cell Death

Radiotherapy (RT) fosters a form of tumor cell death that results in dendritic cell activation, effector T-cell cross priming/tumor trafficking, and the formation of a tumor cell/T-cell immune response. This type of immunogenicity is comprised of the release of immune modulating signals, which include the release of high mobility group box 1 (HMGB1), ATP, and the translocation of calreticulin to the cell surface. Previous studies have demonstrated a positive correlation between markers of immunogenic cell death (ICD) and radiation dose with X-rays. Less is known about the effect of higher energies using charged particle irradiation and ICD. In this study, we explore whether varying linear energy transfer (LET) greater than 60 keV/μm with helium ion irradiation would impact immunogenicity in tumor cells as measured by levels of calreticulin translocation, ATP release, and HMGB1 release. Reporter cell lines designed to detect ATP luminescence (RLUs), red fluorescence protein tagged HMGB1 (relative fluorescent units [RFUs]), and cell surface calreticulin (percentage of calreticulin positive cells [%CRT+]) were derived from TSA (murine mammary carcinoma; syngeneic to BALB/c mice) cells. Prior to irradiation, the cells were seeded on six micron thick Mylar attached to 1.5 cm metal rings. The cells were then irradiated at the Radiological Research Accelerator Facility (RARAF) through a Track Segment Charged-Particle Irradiator. ATP and HMGB1 levels were measured 72 hours after RT and calreticulin was measured 24 hours after RT. Various doses of 250kV X-rays and LETs of helium ions were delivered and levels of these tumor ICD markers were determined. For ATP measurements, when compared to non-irradiated controls, cells irradiated with 5 and 20 Gy X-rays and with 5 Gy 65, 80, 110, and 160 keV/μm helium ions resulted in RLU fold-changes of 1.00 ± 0.05 (non-irradiated), 2.33 ± 0.08, 3.27 ± 0.19, 3.24 ± 0.10, 3.99 ± 0.33, 4.12 ± 0.32, and 2.91 ± 0.16 respectively. For HMGB1 measurements, when compared to controls, cells irradiated with 5 and 20 Gy X-rays and with 5 Gy 65, 80, 110, and 160 keV/μm helium ions resulted in RFU fold-changes of 1.00 ± 0.02 (non-irradiated), 1.43 ± 0.03, 1.72 ± 0.03, 1.97 ± 0.06, 1.64 ± 0.03, 1.61 ± 0.04, and 1.51 ± 0.03, respectively. For calreticulin measurements, when compared to controls, cells irradiated with 5 and 20 Gy X-rays and with 5 Gy 65, 80, 110, and 160 keV/μm helium ions resulted in %CRT+ fold-changes of 1.00 ± 0.12 (non-irradiated), 2.32 ± 0.15, 3.07 ± 0.32, 3.16 ± 0.17, 3.01 ± 0.12, 2.74 ± 0.39, and 1.61 ± 0.15, respectively. Immunogenicity of tumor cells as measured by immune cell death signals increases with high LET ion irradiation when compared to low LET X-ray irradiation at the same dose. These marker levels appear to decrease at LETs greater than 110 keV/μm. Further investigation is warranted on the effects of high LET charged particle irradiation on the tumor immune response.

364 Tumor Compression Effect on White Matter Pathways Revealed by Local Connectome Fingerprint

Abstract INTRODUCTION Low-grade gliomas (LGGs) are slow growing tumors that often cause infiltration and/or compression of the white matter pathways. Regular imaging modalities are no capable of revealing such a pathologic condition. Furthermore, up-to-date there is no reliable noninvasive imaging method to address this issue. Here we report that the local connectome fingerprint, an along track density measurement derived from diffusion MRI (dMRI), is capable of revealing the tumor compression effect on the surrounding white matter pathways. METHODS We acquired high angular resolution dMRI data on 16 patients diagnosed of LGG (WHO grade II). Peritumoral fiber tracts underwent qualitative and quantitative evaluation. Contralateral hemisphere counterparts were used for comparison. The local connectome fingerprint of peritumoral tract segment and their ratio to healthy side were visualized and calculated in comparison with 842 normal subjects from the Human Connectome Project. RESULTS &gt;Our results showed significant increase in the ratios to the normal side among displaced tracts and decreases among the infiltrated tracts when compared to their healthy counterpart. Qualitative analysis of 65 peritumoral tracts revealed 9 (13.8%) unaffected, 24 (36.9%) displaced, 13 (20%) infiltrated and 19 (29.2%) tracts with a combination of displacement and infiltration. There were no disrupted tracts. The along tracks local connectome fingerprint further localizes the track segments with compression effect caused by the tumor mass. This feature cannot be observed in conventional tensor and diffusivity analysis. CONCLUSION The unique capability of local connectome fingerprint in revealing the compression and infiltration effect can provide potential diagnostic and prognostic applications in clinical intervention of patients with WHO grade-II low-grade gliomas.

Convolutional networks for vehicle track segmentation

Existing methods to detect vehicle tracks in coherent change detection images, a product of combining two synthetic aperture radar images taken at different times of the same scene, rely on simple and fast models to label track pixels. These models, however, are unable to capture natural track features, such as continuity and parallelism. More powerful but computationally expensive models can be used in offline settings. We present an approach that uses dilated convolutional networks consisting of a series of 3×3 convolutions to segment vehicle tracks. The design of our networks considers the fact that remote sensing applications tend to operate in low power and have limited training data. As a result, we aim for small and efficient networks that can be trained end-to-end to learn natural track features entirely from limited training data. We demonstrate that our six-layer network, trained on just 90 images, is computationally efficient and improves the F-score on a standard dataset to 0.992, up from 0.959 obtained by the current state-of-the-art method.

Application of maximum entropy to statistical inference for inversion of data from a single track segment.

In this paper an approach is presented to estimate the constraint required to apply maximum entropy (ME) for statistical inference with underwater acoustic data from a single track segment. Previous algorithms for estimating the ME constraint require multiple source track segments to determine the constraint. The approach is relevant for addressing model mismatch effects, i.e., inaccuracies in parameter values determined from inversions because the propagation model does not account for all acoustic processes that contribute to the measured data. One effect of model mismatch is that the lowest cost inversion solution may be well outside a relatively well-known parameter value's uncertainty interval (prior), e.g., source speed from track reconstruction or towed source levels. The approach requires, for some particular parameter value, the ME constraint to produce an inferred uncertainty interval that encompasses the prior. Motivating this approach is the hypothesis that the proposed constraint determination procedure would produce a posterior probability density that accounts for the effect of model mismatch on inferred values of other inversion parameters for which the priors might be quite broad. Applications to both measured and simulated data are presented for model mismatch that produces minimum cost solutions either inside or outside some priors.

Identifying locations along railway networks with the highest tree fall hazard

Disruptions of railway traffic have many reasons. Tree falls onto railway tracks or overhead lines rank among the most common causes of disruptions of a natural origin. 2039 tree-fall events, containing up to 70 individual trees per event, were registered on the Czech railway network between 2012 and 2015. 32% of them were directly caused by 14 weather extremes during which more than 20 concurrent tree-fall events were registered. Moreover, 12 train derailments due to fallen trees were registered on Czech railways within the same period.We combined land use data along railway tracks and data on tree falls. Land use and railway tracks data were obtained from a freely available Open Street Map database. The tree fall hazard was then computed using empirical data, data on land use and a generalized rule of succession. The clustering approach was also applied to focus on localities where tree falls were concentrated regardless of the resulting segment hazard. There were 59 rail track segments (out of 2960) with the highest tree fall hazard and 267 clusters were finally identified. The clusters and the most hazardous railway segments will be among the first in the process of line side vegetation monitoring in order to minimize potential losses from tree fall. The presented method can be widely applicable elsewhere.

Automatic analysis of complex athlete techniques in broadcast taekwondo video

Athlete detection and action recognition in sports video is a very challenging task due to the dynamic and cluttered background. Several attempts for automatic analysis focus on athletes in many sports videos have been made. However, taekwondo video analysis remains an unstudied field. In light of this, a novel framework for automatic techniques analysis in broadcast taekwondo video is proposed in this paper. For an input video, in the first stage, athlete tracking and body segmentation are done through a modified Structure Preserving Object Tracker. In the second stage, the de-noised frames which completely contain the body of analyzed athlete from video sequence, are trained by a deep learning network PCANet to predict the athlete action of each single frame. As one technique is composed of many consecutive actions and each action corresponds a video frame, focusing on video sequences to achieve techniques analysis makes sense. In the last stage, linear SVM is used with the predicted action frames to get a techniques classifier. To evaluate the performance of the proposed framework, extensive experiments on real broadcast taekwondo video dataset are provided. The results show that the proposed method achieves state-of-the-art results for complex techniques analysis in taekwondo video.