Tracking In Sequences Research Articles

Archival data provides insights into the ambiguous track-maker gait from the Lower Jurassic (Sinemurian) Razorback beds, Queensland, Australia: evidence of theropod quadrupedalism?

ABSTRACT The ichnological and palaeobiological interpretation of the first dinosaur tracks described from the Lower Jurassic (Sinemurian) Razorback beds, anthropogenic ‘fireclay caverns’ of Mount Morgan, Australia, is reviewed. This track sequence of two size categories has been widely accepted as having been formed by a theropod walking in an uncharacteristic quadrupedal stance. However, the morphology of the purported manus impression remained ambiguous due to the poor reproduction quality of the original image data. Here, we present previously unpublished archival photographic and replica material of this track surface. These clearly show the morphological details of the track series that are consistent with registration by two different sized bipedal track-makers. Overall, our findings illustrate that retained archival data can be pivotal in the resolution of palaeoichnological obscurities.

Probing the Magnetic Structure of a Pair of Transpolar Arcs With a Solar Wind Pressure Step

AbstractWe present observations of the Northern Hemisphere auroras taken with the far ultraviolet cameras onboard the Imager for Magnetopause‐to‐Aurora Global Exploration spacecraft during a compression of the magnetosphere by a solar wind pressure step on 30 December 2001. The compression occurs during a period of northward interplanetary magnetic field which has given rise to the presence of a pair of transpolar arcs (TPAs) near the dawnside oval. The compression causes a brightening of the oval, from dayside to nightside over the course of 10 min, followed by a brightening of the midnight sector oval and TPAs from nightside to dayside, again over 10 min. We suggest that the brightening is caused by pitch angle scattering of particles trapped on closed magnetic field lines and that the sequence of the brightening tracks the solar wind pressure step as it progresses along the length of the magnetotail. Traveling at 600 km s , the step reaches up to 90 down‐tail over the period of brightening, suggesting that the magnetic field lines which map to the TPAs are closed and stretch almost this length down‐tail.

Robust multi-kernelized correlators for UAV tracking with adaptive context analysis and dynamic weighted filters

In recent years, the correlation filter (CF)-based method has significantly advanced in the tracking for unmanned aerial vehicles (UAVs). As the core component of most trackers, CF is a discriminative classifier to distinguish the object from the surrounding environment. However, the poor representation of the object and lack of contextual information have restricted the tracker to gain better performance. In this work, a robust framework with multi-kernelized correlators is proposed to improve robustness and accuracy simultaneously. Both convolutional features extracted from the neural network and hand-crafted features are employed to enhance expressions for object appearances. Then, the adaptive context analysis strategy helps filters to effectively learn the surrounding information by introducing context patches with the GMSD index. In the training stage, multiple dynamic filters with time-attenuated factors are introduced to avoid tracking failure caused by dramatic appearance changes. The response maps corresponding to different features are finally fused before the novel resolution enhancement operation to increase distinguishing capability. As a result, the optimization problem is reformulated, and a closed-form solution for the proposed framework can be obtained in the kernel space. Extensive experiments on 100 challenging UAV tracking sequences demonstrate that the proposed tracker outperforms other 23 state-of-the-art trackers and can effectively handle unexpected appearance variations under the complex and constantly changing working conditions.

Abrupt-motion-aware lightweight visual tracking for unmanned aerial vehicles

Visual tracking for unmanned aerial vehicles (UAVs) is a hot research topic for the wide applications of UAVs. As UAVs are high-altitude and high-freedom platforms, small targets in UAV tracking sequences are often under the attribute of large-scale location change due to the abrupt motion of the platform. Currently, many visual tracking methods based on the local search hypothesis have been widely researched on low-speed moving platforms. However, these methods cannot be directly used on the UAV platform, because targets will appear in any position of the new frame. To address this problem, we propose an abrupt-motion-aware visual tracking method in this paper. Because of the high power consumption of deep learning models, the proposed method is a lightweight tracker for small UAVs without the deep learning framework. Our method consists of three major components: abrupt motion estimation, object tracking and model updating. Abrupt motion often leads to abnormal changes in the response map of trackers. Thus, by analyzing the changes of tracking response maps, the abrupt motion can be detected efficiently. When abrupt motion happens, keypoint matching will be adaptively implemented to estimate the ego-motion and skipped otherwise. Then, the target location is predicted by the correlation filter tracker in a local search region. Moreover, according to the confidence analysis, an adaptive model update strategy is designed to alleviate the model noise caused by the short-term occlusion. Experimental results confirm the robustness and the accuracy of our method on challenging sequences and show the comparative performance of the proposed method against several state-of-the-art lightweight methods.

Quasimetagenomic source tracking of Listeria monocytogenes from naturally contaminated ice cream

BackgroundThe more quickly bacterial pathogens responsible for foodborne illness outbreaks can be linked to a vehicle of transmission or a source, the more illnesses can be prevented. Whole genome sequencing (WGS) based approaches to source tracking have greatly increased the speed and resolution with which public health response can pinpoint the vehicle and source of outbreaks. Traditionally, WGS approaches have focused on the culture of an individual isolate before proceeding to DNA extraction and sequencing. For Listeria monocytogenes (Lm), generation of an individual isolate for sequencing typically takes about 6 days. Here we demonstrate that a hybrid, “quasimetagenomic” approach ie; direct sequencing of microbiological enrichments (first step in pathogen detection and recovery) can provide high resolution source tracking sequence data, 5 days earlier than response that focuses on culture and sequencing of an individual isolate. This expedited approach could save lives, prevent illnesses and potentially minimize unnecessary destruction of food.MethodsNaturally contaminated ice cream (from a 2015 outbreak) was enriched to recover Listeria monocytogenes following protocols outlined in the Bacteriological Analytic Manual (BAM). DNA from enriching microbiota was extracted and sequenced at incremental time-points during the first 48 h of pre-enrichment using the Illumina MiSeq platform (2 by 250), to evaluate genomic coverage of target pathogen, Listeria monocytogenes.ResultsQuasimetagenomic sequence data acquired from hour 20 were sufficient to discern whether or not Lm strain/s were part of the ongoing outbreak or not. Genomic data from hours 24, 28, 32, 36, 40, 44, and 48 of pre-enrichments all provided identical phylogenetic source tracking utility to the WGS of individual isolates (which require an additional 5 days to culture).ConclusionsThe speed of this approach (more than twice as fast as current methods) has the potential to reduce the number of illnesses associated with any given outbreak by as many as 75% percent of total cases and potentially with continued optimization of the entire chain of response, contribute to minimized food waste.

Accurate Long-Term Multiple People Tracking using Video and Body-Worn IMUs.

Most modern approaches for video-based multiple people tracking rely on human appearance to exploit similarities between person detections. Consequently, tracking accuracy degrades if this kind of information is not discriminative or if people change apparel. In contrast, we present a method to fuse video information with additional motion signals from body-worn inertial measurement units (IMUs). In particular, we propose a neural network to relate person detections with IMU orientations, and formulate a graph labeling problem to obtain a tracking solution that is globally consistent with the video and inertial recordings. The fusion of visual and inertial cues provides several advantages. The association of detection boxes in the video and IMU devices is based on motion, which is independent of a person's outward appearance. Furthermore, inertial sensors provide motion information irrespective of visual occlusions. Hence, once detections in the video are associated with an IMU device, intermediate positions can be reconstructed from corresponding inertial sensor data, which would be unstable using video only. Since no dataset exists for this new setting, we release a dataset of challenging tracking sequences, containing video and IMU recordings together with ground-truth annotations. We evaluate our approach on our new dataset, achieving an average IDF1 score of 91.2%. The proposed method is applicable to any situation that allows one to equip people with inertial sensors.

Surrounding-aware correlation filter for UAV tracking with selective spatial regularization

The great advance of visual object tracking has provided unmanned aerial vehicle (UAV) with intriguing capability for various practical applications. With promising performance and efficiency, discriminative correlation filter-based trackers have drawn great attention and undergone remarkable progress. However, background interference and boundary effect remain two thorny problems. In this paper, a surrounding-aware tracker with selective spatial regularization (SASR) is presented. SASR tracker extracts surrounding samples according to the size and shape of the object in order to utilize context and maintain the integrality of the object. Additionally, a selective spatial regularizer is introduced to address boundary effect. Central coefficients in the filter are evenly regularized to preserve valid information from the object. While the others are penalized according to their spatial location. Under the framework of SASR tracker, surrounding information and selective spatial regularization prove to be complementary to each other, which actually did not draw much attention before. They managed to improve not only the robustness against various distractions in the surrounding but also the flexibility to catch up with frequent appearance change of the object. Qualitative evaluation and quantitative experiments on challenging UAV tracking sequences have shown that SASR tracker has performed favorably against 23 state-of-the-art trackers.

License Plate Recognition in Urban Road Based on Vehicle Tracking and Result Integration

Abstract Multiple surveillance cameras provide huge video resources that need further mining to collect traffic stream data such as license plate recognition (LPR). However, these surveillance cameras have limited spatial resolution, which may not always suffice to precisely recognize license plates by existing LPR systems. This work is focused on the LPR method in low-quality images from surveillance video screenshots on urban road. The methodology we proposed is based on vehicle tracking and result integration, and we recognize the plate with an end-to-end method without character segmentation. First, we track each vehicle to get vehicle tracking sequence. Moreover, a plate detector based on an object detection framework is trained to detect license plates of each vehicle from the sequence and a license plate sequence is formed. In addition, an end-to-end convolutional neural network architecture is applied to recognize license plates from the sequence. Finally, we integrate the recognition result of continuous frames to get the final result. Evaluation results on multiple datasets show that our method significantly outperforms others without segmentation or integration in real traffic scene.

Fault ride-through capability of star-connected cascaded multilevel converter based hybrid energy storage system under unbalanced grid failure

This paper proposes a fault-tolerant control method for star-connected cascaded multilevel converter (CMC) based hybrid energy storage system (HESS) to enhance its fault ride-through capability under unbalanced grid failure. In this topology, battery and capacitor are used as two types of dc sources. Unbalanced grid will lead to uneven power flow among three-phase links, so it's challenging to distribute active power between different types of converter cells to perform voltage balancing control. With proposed control method, battery cells and capacitor cells respectively perform unbalanced voltage tracking and zero sequence voltage (ZSV) injection. The system can maintain dc-side voltages, allowing system to ride through faulty situations and enhance its reliability. Proposed method is implemented in the DSP and verified by a 5 MW/35 kV system based on RT-LAB HIL (hardware-in-loop) platform, experimental results validate the reliability of system has been enhanced.

An efficient urban localization method based on speed humps

Outdoor localization is of great importance for driving navigation, attracting many research efforts in past decades. Prevailing GPS achieves meter-level localization accuracy under general outdoor conditions. Yet, GPS service performs poorly in urban canyons where skyscrapers block GPS signals and drain mobile phone battery quickly within few hours. In this work, we exploit common city facilities, i.e., speed humps, as an indicator for vehicle location. The key insight is that when the vehicle passes through the speed bump, it experiences significant fluctuations, causing larger acceleration in the vertical direction. On this basis, we design a localization scheme that utilizes the accelerator equipped on modern smart phones to track sequence of speed bumps, which is further transferred into sequence of moving directions of the vehicle, and adopt effective road mapping technology to derive real-time location. As we have concerned, it is the first attempt to exploit the spatiotemporal characteristics generated by the speed humps to recover the trajectory of the travelling route and infer the current position. Experimental results in typical outdoor environment (campus) demonstrate a comparable performance with GPS method, yet achieve lower energy consumption.

Coupling adaptive molecular evolution to phylodynamics using fitness-dependent birth-death models.

Beneficial and deleterious mutations cause the fitness of lineages to vary across a phylogeny and thereby shape its branching structure. While standard phylogenetic models do not allow mutations to feedback and shape trees, birth-death models can account for this feedback by letting the fitness of lineages depend on their type. To date, these multi-type birth-death models have only been applied to cases where a lineage's fitness is determined by a single character state. We extend these models to track sequence evolution at multiple sites. This approach remains computationally tractable by tracking the genotype and fitness of lineages probabilistically in an approximate manner. Although approximate, we show that we can accurately estimate the fitness of lineages and site-specific mutational fitness effects from phylogenies. We apply this approach to estimate the population-level fitness effects of mutations in Ebola and influenza virus, and compare our estimates with in vitro fitness measurements for these mutations.

Magnetic Resonance Navigation for Targeted Embolization in a Two-Level Bifurcation Phantom.

This work combines a particle injection system with our proposed magnetic resonance navigation (MRN) sequence with the intention of validating MRN in a two-bifurcation phantom for endovascular treatment of hepatocellular carcinoma (HCC). A theoretical physical model used to calculate the most appropriate size of the magnetic drug-eluting bead (MDEB, 200μm) aggregates was proposed. The aggregates were injected into the phantom by a dedicated particle injector while a trigger signal was automatically sent to the MRI to start MRN which consists of interleaved tracking and steering sequences. When the main branch of the phantom was parallel to B0, the aggregate distribution ratio in the (left-left, left-right, right-left and right-right divisions was obtained with results of 8, 68, 24 and 0% respectively at baseline (no MRN) and increased to 84%, 100, 84 and 92% (p < 0.001, p = 0.004, p < 0.001, p < 0.001) after implementing our MRN protocol. When the main branch was perpendicular to B0, the right-left branch, having the smallest baseline distribution rate of 0%, reached 80% (p < 0.001) after applying MRN. Moreover, the success rate of MRN was always more than 92% at the 1st bifurcation in the experiments above.

Enforcing Position-Based Confidentiality With Machine Learning Paradigm Through Mobile Edge Computing in Real-Time Industrial Informatics

Position-based services (PBSs) that deliver networked amenities based on roaming user's positions have become progressively popular with the propagation of smart mobile devices. Position is one of the important circumstances in PBSs. For effective PBSs, extraction and recognition of meaningful positions and estimating the subsequent position are fundamental procedures. Several researchers and practitioners have tried to recognize and predict positions using various techniques; however, only few deliberate the progress of position-based real-time applications considering significant tasks of PBSs. In this paper, a method for conserving position confidentiality of roaming PBSs users using machine learning techniques is proposed. We recommend a three-phase procedure for roaming PBS users. It identifies user position by merging decision trees and k-nearest neighbor and estimates user destination along with the position track sequence using hidden Markov models. Moreover, a mobile edge computing service policy is followed in the proposed paradigm, which will ensure the timely delivery of PBSs. The benefits of mobile edge service policy offer position confidentiality and low latency by means of networking and computing services at the vicinity of roaming users. Thorough experiments are conducted, and it is confirmed that the proposed method achieved above 90% of the position confidentiality in PBSs.

A multiple feature fused model for visual object tracking via correlation filters

Common tracking algorithms only use a single feature to describe the target appearance, which makes the appearance model easily disturbed by noise. Furthermore, the tracking performance and robustness of these trackers are obviously limited. In this paper, we propose a novel multiple feature fused model into a correlation filter framework for visual tracking to improve the tracking performance and robustness of the tracker. In different tracking scenarios, the response maps generated by the correlation filter framework are different for each feature. Based on these response maps, different features can use an adaptive weighting function to eliminate noise interference and maintain their respective advantages. It can enhance the tracking performance and robustness of the tracker efficiently. Meanwhile, the correlation filter framework can provide a fast training and accurate locating mechanism. In addition, we give a simple yet effective scale variation detection method, which can appropriately handle scale variation of the target in the tracking sequences. We evaluate our tracker on OTB2013/OTB50/OBT2015 benchmarks, which are including more than 100 video sequences. Extensive experiments on these benchmark datasets demonstrate that the proposed MFFT tracker performs favorably against the state-of-the-art trackers.

GantryMate: A Modular MR-Compatible Assistance System for MR-Guided Needle Interventions.

Percutaneous minimally invasive interventions are difficult to perform in closed-bore high-field magnetic resonance systems owing to the limited space between magnet and patient. To enable magnetic resonance–guided needle interventions, we combine a small, patient-mounted assistance system with a real-time instrument tracking sequence based on a phase-only cross-correlation algorithm for marker detection. The assistance system uses 2 movable plates to align an external passive marker with the anatomical target structure. The targeting accuracy is measured in phantom experiments, yielding a precision of 1.7 ± 1.0 mm for target depths up to 38 ± 13 mm. In in vivo experiments, the possibility to track and target static and moving structures is demonstrated.

Initial Matting-Guided Visual Tracking With Siamese Network

Fully-convolutional Siamese networks for visual tracking have drawn great attention in balancing tracking accuracy and speed. However, there is still some inherent inaccuracy with advanced trackers, since they only learn a general matching model from large scale datasets by off-line training. This generates the target template without sufficient discriminant information and does not adapt well to the current tracking sequence. In this paper, we introduce the channel attention mechanism into the network to better learn the matching model and, during the online tracking phase, we design an initial matting guidance strategy in which: 1) the superpixel matting algorithm is applied to extract the target foreground in the initial frame, and 2) the matted image with foreground only is fed into the network and fused with the original image feature. Under matting guidance, the fused target template has more details for representation of target appearance and more structural information from superpixels for robust tracking. The experimental results on object tracking benchmark (OTB) show that our approach achieves excellent performance while it also provides real-time tracking speed.

Simulation and measurement study of metro wheel wear based on the Archard model

PurposeThe purpose of this paper is to study the wear evolution of metro wheels under the conditions of different track sequences, track composition and vehicle load and then to predict wheel wear and to guide its maintenance.MethodologyBy using the SIMPACK and MATLAB software, numerical simulation analysis of metro wheel wear is carried out based on Hertz theory, the FASTSIM algorithm and the Archard model. First of all, the vehicle dynamics model is established to calculate the motion relationship and external forces of wheel-rail in the SIMPACK software. Then, the normal force of wheel-rail is solved based on Hertz theory, and the tangential force of wheel-rail is calculated based on the FASTSIM algorithm through the MATLAB software. Next, in the MATLAB software, the wheel wear is calculated based on the Archard model, and a new wheel profile is obtained. Finally, the new wheel profile is re-input into the vehicle system dynamics model in the SIMPACK software to carry out cyclic calculation of wear.FindingsThe results show that the setting order of different curves has an obvious influence on wear when the proportion of the straight track and the curve is fixed. With the increase in running mileage, the severe wear zone is shifted from tread to flange root under the condition of the sequence-type track, but the wheel wear distribution is basically stable for the unit-type track, and their wear growth rates become closer. In the tracks with different straight-curved ratio, the more proportion the curved tracks occupy, the closer the severe wear zone is shifted to flange root. At the same time, an increase in weight of the vehicle load will aggravate the wheel wear, but it will not change the distribution of wheel wear. Compared with the measured data of one city B type metro in China, the numerical simulation results of wheel wear are nearly the same with the measured data.Practical implicationsThese results will be helpful for metro tracks planning and can predict the trend of wheel wear, which has significant importance for the vehicle to do the repair operation. At the same time, the security risks of the vehicle are decreased economically and effectively.Originality/valueAt present, many scholars have studied the influence of metro tracks on wheel wear, but mainly focused on a straight line or a certain radius curve and neglected the influence of track sequence and track composition. This study is the first to examine the influence of track sequence on metro wheel wear by comparing the sequence-type track and unit-type track. The results show that the track sequence has a great influence on the wear distribution. At the same time, the influence of track composition on wheel wear is studied by comparing different straight-curve ratio tracks; therefore, wheel wear can be predicted integrally under different track conditions.

Simultaneous slice excitation for accelerated passive marker tracking via phase-only cross correlation (POCC) in MR-guided needle interventions.

Toaccelerate a passive tracking sequence based on phase-only cross correlation (POCC) using simultaneous slice excitation. For magnetic resonance (MR)-guided biopsy procedures, passive markers have been proposed that can be automatically localized online using a POCC-based tracking sequence. To accelerate the sequence, a phase-offset multiplanar (POMP) excitation technique was implemented to acquire tracking images. In a phantom experiment, the POMP-POCC sequence was tested and compared with the sequential non-accelerated version in terms of duration and accuracy. Further, technical feasibility of thePOMP-POCC sequence was tested in a patient undergoing a prostate biopsy. The temporal resolution of the POMP-POCC tracking sequence is accelerated by 33% compared with the sequential approach. In phantom experiments, the POMP-POCC and sequential sequences yielded the same targeting accuracy of 1.6 ± 0.7mm. Technical proof of concept of the new sequence could be demonstrated in a successful in vivo prostate biopsy. POMP-POCC tracking can substantially reduce the duration of localization of passive markers in MR-guided needle interventions without compromising targeting accuracy.

Jurassic arthropod tracks from northern Iran

In 2010, a siltstone slab containing three arthropod trackways was discovered in the Middle Jurassic Dansirit Formation in the Ruyan region, central Alborz Mountains, northern Iran. Quality of preservation is varied, but the best-preserved track sequences consist of a chevron-shaped pair of outer tracks surrounding two pairs of inner tracks. These trace fossils are named herein as a new ichnogenus and ichnospecies, Porpaichnus dansiritensis. The depositional environment of the track-bearing stratum is enigmatic. If the sediment is of littoral origin, the footprints were likely made by a decapod crustacean. For a terrestrial deposit, the imprint morphology is possible evidence of an arachnid that used its pedipalps to supplement four pairs of walking legs. These morphological characteristics suggest the track-maker is may have been an early member of the Infraorder Mygalomorpha. If so, the 170 Ma trackways are the earliest known evidence of a tarantula-like spider. Although the oldest known tarantula fossils date to the Miocene, fossil evidence of mygalomorph spiders dates to the Cretaceous, and molecular clock evidence suggests that divergence of spider families occurred in the late Paleozoic.

Compact Design of a Hydraulic Driving Robot for Intraoperative MRI-Guided Bilateral Stereotactic Neurosurgery

In this letter, we present an intraoperative magnetic resonance imaging (MRI)-guided robot for bilateral stereotactic procedures. Its compact design enables robot's operation within the constrained space of standard imaging head coil. magnetic resonance (MR) safe and high-performance hydraulic transmissions are incorporated. A maximum stiffness coefficient of 24.35 N/mm can be achieved with transmission fluid preloaded at 2 bar. Sufficient targeting accuracy (average within ≤1.73 mm) has been demonstrated in a simulated needle insertion task of deep brain stimulation. A novel MR-based wireless tracking technique is adopted. It is capable of offering real-time and continuous (30-40 Hz) three-dimensional (3-D) localization of robotic instrument under the proper MR tracking sequence. It outperforms the conventional method of using low-contrast passive fiducials that can only be revealed in the MR image domain. Two wireless tracking units/markers are integrated with the robot, which are two miniaturized coil circuits in size of 1.5 × 5 × 0.2 mm 3 , fabricated on flexible thin films. A navigation test was performed under the standard MRI settings in order to visualize the 3-D localization of the robotic instrument. MRI compatibility test was also carried out to prove the minimal interference to MR images of the presented hydraulic robotic platform.