Search Results for author: Michael Arens

Found 22 papers, 3 papers with code

A Comparison of Deep Saliency Map Generators on Multispectral Data in Object Detection

no code implementations26 Aug 2021 Jens Bayer, David Münch, Michael Arens

The dataset used in this work is the Multispectral Object Detection Dataset, where each scene is available in the FIR, MIR and NIR as well as visual spectrum.

Autonomous Driving Image Classification +1

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

no code implementations1 Jul 2021 Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris

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.

motion prediction Object Tracking +1

MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction

no code implementations30 Jun 2021 Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris

By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs.

Object Tracking Time Series

MODISSA: a multipurpose platform for the prototypical realization of vehicle-related applications using optical sensors

no code implementations28 May 2021 Björn Borgmann, Volker Schatz, Marcus Hammer, Marcus Hebel, Michael Arens, Uwe Stilla

We present the current state of development of the sensor-equipped car MODISSA, with which Fraunhofer IOSB realizes a configurable experimental platform for hardware evaluation and software development in the context of mobile mapping and vehicle-related safety and protection.

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

no code implementations22 Mar 2021 Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens, Brendan T. Morris

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.

Imputation Time Series

3D Surface Reconstruction From Multi-Date Satellite Images

1 code implementation4 Feb 2021 Sebastian Bullinger, Christoph Bodensteiner, Michael Arens

The reconstruction of accurate three-dimensional environment models is one of the most fundamental goals in the field of photogrammetry.

Stereo Matching Structure from Motion

A Photogrammetry-based Framework to Facilitate Image-based Modeling and Automatic Camera Tracking

2 code implementations2 Dec 2020 Sebastian Bullinger, Christoph Bodensteiner, Michael Arens

We propose a framework that extends Blender to exploit Structure from Motion (SfM) and Multi-View Stereo (MVS) techniques for image-based modeling tasks such as sculpting or camera and motion tracking.

Structure from Motion

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

1 code implementation6 Aug 2020 Stéphane Vujasinović, Stefan Becker, Timo Breuer, Sebastian Bullinger, Norbert Scherer-Negenborn, Michael Arens

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.

3D Reconstruction Structure from Motion +2

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

no code implementations28 May 2020 Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens

Methods to quantify the complexity of trajectory datasets are still a missing piece in benchmarking human trajectory prediction models.

Quantization Trajectory Prediction

A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks

no code implementations27 Mar 2020 Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens

The analysis and quantification of sequence complexity is an open problem frequently encountered when defining trajectory prediction benchmarks.

Quantization Trajectory Prediction

Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition

no code implementations3 Mar 2020 Jens Bayer, David Münch, Michael Arens

Therefore, it is necessary for such a learning-based system in a real world environment, to be aware of its own capabilities and limits and to be able to distinguish between confident and unconfident results of the inference, especially if the sample cannot be explained by the underlying distribution.

Action Recognition Metric Learning +1

Modeling continuous-time stochastic processes using $\mathcal{N}$-Curve mixtures

no code implementations12 Aug 2019 Ronny Hug, Wolfgang Hübner, Michael Arens

Towards this end, a neural network model for continuous-time stochastic processes usable for sequence prediction is proposed.

Trajectory Prediction

Investigation on Combining 3D Convolution of Image Data and Optical Flow to Generate Temporal Action Proposals

no code implementations11 Mar 2019 Patrick Schlosser, David Münch, Michael Arens

In this paper, several variants of two-stream architectures for temporal action proposal generation in long, untrimmed videos are presented.

Action Recognition Optical Flow Estimation +1

An RNN-based IMM Filter Surrogate

no code implementations5 Feb 2019 Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens

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.

Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

no code implementations17 Oct 2018 Nikolas Hesse, Sergi Pujades, Michael J. Black, Michael Arens, Ulrich G. Hofmann, A. Sebastian Schroeder

To demonstrate the applicability of SMIL, we fit the model to RGB-D sequences of freely moving infants and show, with a case study, that our method captures enough motion detail for General Movements Assessment (GMA), a method used in clinical practice for early detection of neurodevelopmental disorders in infants.

3D Vehicle Trajectory Reconstruction in Monocular Video Data Using Environment Structure Constraints

no code implementations ECCV 2018 Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, Rainer Stiefelhagen

We apply Structure from Motion techniques to vehicle and background images to determine for each frame camera poses relative to vehicle instances and background structures.

Optical Flow Estimation Semantic Segmentation +1

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

no code implementations19 May 2018 Stefan Becker, Ronny Hug, Wolfgang Hübner, Michael Arens

In recent years, there is a shift from modeling the tracking problem based on Bayesian formulation towards using deep neural networks.

Trajectory Prediction

Particle-based pedestrian path prediction using LSTM-MDL models

no code implementations16 Apr 2018 Ronny Hug, Stefan Becker, Wolfgang Hübner, Michael Arens

Recurrent neural networks are able to learn complex long-term relationships from sequential data and output a pdf over the state space.

3D Trajectory Reconstruction of Dynamic Objects Using Planarity Constraints

no code implementations16 Nov 2017 Sebastian Bullinger, Christoph Bodensteiner, Michael Arens, Rainer Stiefelhagen

We apply Structure from Motion techniques to object and background images to determine for each frame camera poses relative to object instances and background structures.

Optical Flow Estimation Semantic Segmentation +1

Cannot find the paper you are looking for? You can Submit a new open access paper.