arXiv subjects

Stefan Becker

Publications and source records attributed to Stefan Becker.

32 records · Page 2Linked to original sources

arXiv2021

Handling Missing Observations with an RNN-based Prediction-Update Cycle

In tasks such as tracking, time-series data inevitably carry missing observations. While traditional tracking approaches can handle missing observations, recurrent neural networks (RNNs) are designed to receive input data in every step. Furthermore, current solutions for RNNs, like omitting the missing data or data imputation, are not sufficient to account for the resulting increased uncertainty. Towards this end, this paper introduces an RNN-based approach that provides a full temporal filtering cycle for motion state estimation. The Kalman filter inspired approach, enables to deal with missing observations and outliers. For providing a full temporal filtering cycle, a basic RNN is extended to take observations and the associated belief about its accuracy into account for updating the current state. An RNN prediction model, which generates a parametrized distribution to capture the predicted states, is combined with an RNN update model, which relies on the prediction model output and the current observation. By providing the model with masking information, binary-encoded missing events, the model can overcome limitations of standard techniques for dealing with missing input values. The model abilities are demonstrated on synthetic data reflecting prototypical pedestrian tracking scenarios.

cs.CV↗

arXiv2021

Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction

Deep learning-based models, such as recurrent neural networks (RNNs), have been applied to various sequence learning tasks with great success. Following this, these models are increasingly replacing classic approaches in object tracking applications for motion prediction. On the one hand, these models can capture complex object dynamics with less modeling required, but on the other hand, they depend on a large amount of training data for parameter tuning. Towards this end, we present an approach for generating synthetic trajectory data of unmanned-aerial-vehicles (UAVs) in image space. Since UAVs, or rather quadrotors are dynamical systems, they can not follow arbitrary trajectories. With the prerequisite that UAV trajectories fulfill a smoothness criterion corresponding to a minimal change of higher-order motion, methods for planning aggressive quadrotors flights can be utilized to generate optimal trajectories through a sequence of 3D waypoints. By projecting these maneuver trajectories, which are suitable for controlling quadrotors, to image space, a versatile trajectory data set is realized. To demonstrate the applicability of the synthetic trajectory data, we show that an RNN-based prediction model solely trained on the generated data can outperform classic reference models on a real-world UAV tracking dataset. The evaluation is done on the publicly available ANTI-UAV dataset.

cs.CV↗

arXiv2021

Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction

Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models. In order to gain a better understanding of the complexity of trajectory prediction tasks and following the intuition, that more complex datasets contain more information, an approach for quantifying the amount of information contained in a dataset from a prototype-based dataset representation is proposed. The dataset representation is obtained by first employing a non-trivial spatial sequence alignment, which enables a subsequent learning vector quantization (LVQ) stage. A large-scale complexity analysis is conducted on several human trajectory prediction benchmarking datasets, followed by a brief discussion on indications for human trajectory prediction and benchmarking.

cs.CV↗

arXiv2020

Integration of the 3D Environment for UAV Onboard Visual Object Tracking

Single visual object tracking from an unmanned aerial vehicle (UAV) poses fundamental challenges such as object occlusion, small-scale objects, background clutter, and abrupt camera motion. To tackle these difficulties, we propose to integrate the 3D structure of the observed scene into a detection-by-tracking algorithm. We introduce a pipeline that combines a model-free visual object tracker, a sparse 3D reconstruction, and a state estimator. The 3D reconstruction of the scene is computed with an image-based Structure-from-Motion (SfM) component that enables us to leverage a state estimator in the corresponding 3D scene during tracking. By representing the position of the target in 3D space rather than in image space, we stabilize the tracking during ego-motion and improve the handling of occlusions, background clutter, and small-scale objects. We evaluated our approach on prototypical image sequences, captured from a UAV with low-altitude oblique views. For this purpose, we adapted an existing dataset for visual object tracking and reconstructed the observed scene in 3D. The experimental results demonstrate that the proposed approach outperforms methods using plain visual cues as well as approaches leveraging image-space-based state estimations. We believe that our approach can be beneficial for traffic monitoring, video surveillance, and navigation.

cs.CV↗

arXiv2020

A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks

The analysis and quantification of sequence complexity is an open problem frequently encountered when defining trajectory prediction benchmarks. In order to enable a more informative assembly of a data basis, an approach for determining a dataset representation in terms of a small set of distinguishable prototypical sub-sequences is proposed. The approach employs a sequence alignment followed by a learning vector quantization (LVQ) stage. A first proof of concept on synthetically generated and real-world datasets shows the viability of the approach.

cs.LG↗

arXiv2019

Reexamination of Tolman's law and the Gibbs adsorption equation for curved interfaces

In manuscript arXiv:1703.08719 [cond-mat.soft], it was claimed that the well-known deduction of Tolman's law is not rigorous, since Tolman's argument implies that two different definitions of the surface tension, called $γ$ and $\barγ$ in the manuscript, coincide. This claim is retracted as it can be shown by free-energy minimization that $γ= \barγ$ indeed holds for the Laplace radius. Joachim Groß, Philipp Rehner, Carlos Vega, Øivind Wilhelmsen, and the anonymous reviewers of The Journal of Chemical Physics contributed to finding the mistake in the manuscript.

cond-mat.soft↗

arXiv2019

An RNN-based IMM Filter Surrogate

The problem of varying dynamics of tracked objects, such as pedestrians, is traditionally tackled with approaches like the Interacting Multiple Model (IMM) filter using a Bayesian formulation. By following the current trend towards using deep neural networks, in this paper an RNN-based IMM filter surrogate is presented. Similar to an IMM filter solution, the presented RNN-based model assigns a probability value to a performed dynamic and, based on them, puts out a multi-modal distribution over future pedestrian trajectories. The evaluation is done on synthetic data, reflecting prototypical pedestrian maneuvers.

cs.CV↗

arXiv2018

Particle-based pedestrian path prediction using LSTM-MDL models

Recurrent neural networks are able to learn complex long-term relationships from sequential data and output a pdf over the state space. Therefore, recurrent models are a natural choice to address path prediction tasks, where a trained model is used to generate future expectations from past observations. When applied to security applications, like predicting the path of pedestrians for risk assessment, a point-wise greedy (ML) evaluation of the output pdf is not feasible, since the environment often allows multiple choices. Therefore, a robust risk assessment has to take all options into account, even if they are overall not very likely. Towards this end, a combination of particle filter sampling strategies and a LSTM-MDL model is proposed to address a multi-modal path prediction task. The capabilities and viability of the proposed approach are evaluated on several synthetic test conditions, yielding the counter-intuitive result that the simplest approach performs best. Further, the feasibility of the proposed approach is illustrated on several real world scenes.

cs.CV↗

arXiv2018

An Evaluation of Trajectory Prediction Approaches and Notes on the TrajNet Benchmark

In recent years, there is a shift from modeling the tracking problem based on Bayesian formulation towards using deep neural networks. Towards this end, in this paper the effectiveness of various deep neural networks for predicting future pedestrian paths are evaluated. The analyzed deep networks solely rely, like in the traditional approaches, on observed tracklets without human-human interaction information. The evaluation is done on the publicly available TrajNet benchmark dataset, which builds up a repository of considerable and popular datasets for trajectory-based activity forecasting. We show that a Recurrent-Encoder with a Dense layer stacked on top, referred to as RED-predictor, is able to achieve sophisticated results compared to elaborated models in such scenarios. Further, we investigate failure cases and give explanations for observed phenomena and give some recommendations for overcoming demonstrated shortcomings.

cs.CV↗

arXiv2018

An ultrahigh-vacuum cryostat for simultaneous scanning tunneling microscopy and magneto-transport measurements down to 400mK

We present the design and calibration measurements of a scanning tunneling microscope setup in a 3He ultrahigh-vacuum cryostat operating at 400 mK with a hold time of 10 days. With 2.70 m in height and 4.70 m free space needed for assembly, the cryostat fits in a one-story lab building. The microscope features optical access, an xy table, in situ tip and sample exchange, and enough contacts to facilitate atomic force microscopy in tuning fork operation and simultaneous magneto-transport measurements on the sample. Hence, it enables scanning tunneling spectroscopy on microstructured samples which are tuned into preselected transport regimes. A superconducting magnet provides a perpendicular field of up to 14 T. The vertical noise of the scanning tunneling microscope amounts to 1 pmrms within a 700 Hz bandwidth. Tunneling spectroscopy using one superconducting electrode revealed an energy resolution of 120 mueV. Data on tip-sample Josephson contacts yield an even smaller feature size of 60 mueV, implying that the system operates close to the physical noise limit.

physics.ins-det↗

arXiv2015

Contact angle of sessile drops in Lennard-Jones systems

Molecular dynamics simulation is used for studying the contact angle of nanoscale sessile drops on a planar solid wall in a system interacting via the truncated and shifted Lennard-Jones potential. The entire range between total wetting and dewetting is investigated by varying the solid--fluid dispersive interaction energy. The temperature is varied between the triple point and the critical temperature. A correlation is obtained for the contact angle in dependence of the temperature and the dispersive interaction energy. Size effects are studied by varying the number of fluid particles at otherwise constant conditions, using up to 150 000 particles. For particle numbers below 10 000, a decrease of the contact angle is found. This is attributed to a dependence of the solid-liquid surface tension on the droplet size. A convergence to a constant contact angle is observed for larger system sizes. The influence of the wall model is studied by varying the density of the wall. The effective solid-fluid dispersive interaction energy at a contact angle of 90 degrees is found to be independent of temperature and to decrease linearly with the solid density. A correlation is developed which describes the contact angle as a function of the dispersive interaction, the temperature and the solid density. The density profile of the sessile drop and the surrounding vapor phase is described by a correlation combining a sigmoidal function and an oscillation term.

cond-mat.mes-hall↗

arXiv2014

ls1 mardyn: The massively parallel molecular dynamics code for large systems

The molecular dynamics simulation code ls1 mardyn is presented. It is a highly scalable code, optimized for massively parallel execution on supercomputing architectures, and currently holds the world record for the largest molecular simulation with over four trillion particles. It enables the application of pair potentials to length and time scales which were previously out of scope for molecular dynamics simulation. With an efficient dynamic load balancing scheme, it delivers high scalability even for challenging heterogeneous configurations. Presently, multi-center rigid potential models based on Lennard-Jones sites, point charges and higher-order polarities are supported. Due to its modular design, ls1 mardyn can be extended to new physical models, methods, and algorithms, allowing future users to tailor it to suit their respective needs. Possible applications include scenarios with complex geometries, e.g. for fluids at interfaces, as well as non-equilibrium molecular dynamics simulation of heat and mass transfer.

cs.CE↗

arXiv2013

Molecular modelling and simulation of electrolyte solutions, biomolecules, and wetting of component surfaces

Massively-parallel molecular dynamics simulation is applied to systems containing electrolytes, vapour-liquid interfaces, and biomolecules in contact with water-oil interfaces. Novel molecular models of alkali halide salts are presented and employed for the simulation of electrolytes in aqueous solution. The enzymatically catalysed hydroxylation of oleic acid is investigated by molecular dynamics simulation taking the internal degrees of freedom of the macromolecules into account. Thereby, Ewald summation methods are used to compute the long range electrostatic interactions. In systems with a phase boundary, the dispersive interaction, which is modelled by the Lennard-Jones potential here, has a more significant long range contribution than in homogeneous systems. This effect is accounted for by implementing the Janecek cutoff correction scheme. On this basis, the HPC infrastructure at the Steinbuch Centre for Computing was accessed and efficiently used, yielding new insights on the molecular systems under consideration.

cond-mat.soft↗

arXiv2013

Optimization of FASTEST-3D for Modern Multicore Systems

FASTEST-3D is an MPI-parallel finite-volume flow solver based on block-structured meshes that has been developed at the University of Erlangen-Nuremberg since the early 1990s. It can be used to solve the laminar or turbulent incompressible Navier-Stokes equations. Up to now its scalability was strongly limited by a rather rigid communication infrastructure, which led to a dominance of MPI time already at small process counts. This paper describes several optimizations to increase the performance, scalability, and flexibility of FASTEST-3D. First, a node-level performance analysis is carried out in order to pinpoint the main bottlenecks and identify sweet spots for energy-efficient execution. In addition, a single-precision version of the solver for the linear equation system arising from the discretization of the governing equations is devised, which significantly increases the single-core performance. Then the communication mechanisms in FASTEST-3D are analyzed and a new communication strategy based on non-blocking calls is implemented. Performance results with the revised version show significantly increased single-node performance and considerably improved communication patterns along with much better parallel scalability. In this context we discuss the concept of "acceptable parallel efficiency" and how it influences the real gain of the optimizations. Scaling measurements are carried out on a modern petascale system. The obtained improvements are of major importance for the use of FASTEST-3D on current high-performance computer clusters and will help to perform simulations with much higher spatial and temporal resolution to tackle turbulent flow in technical applications.

cs.PF↗