63 citations · 196 across the 35 of their papers we have counts for
40 papers
It's All Just Vectorization: einx, a Universal Notation for Tensor Operations
Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +1
Tensor operations represent a cornerstone of modern scientific computing. However, the Numpy-like notation adopted by predominant tensor frameworks is often difficult to read and w…
Augmentation techniques for video surveillance in the visible and thermal spectral range
Vanessa Buhrmester, Ann-Kristin Grosselfinger, David Munch +1
In intelligent video surveillance, cameras record image sequences during day and night. Commonly, this demands different sensors. To achieve a better performance it is not unusual…
Evaluating Explainability in Safety-Critical ATR Systems: Limitations of Post-Hoc Methods and Paths Toward Robust XAI
Vanessa Buhrmester, David Muench, Dimitri Bulatov +1
Explainable Artificial Intelligence (XAI) is increasingly rec ognized as essential for deploying machine learning systems in safety critical environments. In Automatic Target Recog…
Generating Synthetic Ground Truth Distributions for Multi-step Trajectory Prediction using Probabilistic Composite Bézier Curves
Ronny Hug, Stefan Becker, Wolfgang Hübner +1
An appropriate data basis grants one of the most important aspects for training and evaluating probabilistic trajectory prediction models based on neural networks. In this regard,…
Utilizing dataset affinity prediction in object detection to assess training data
Stefan Becker, Jens Bayer, Ronny Hug +2
Data pooling offers various advantages, such as increasing the sample size, improving generalization, reducing sampling bias, and addressing data sparsity and quality, but it is no…
Eigenpatches -- Adversarial Patches from Principal Components
Jens Bayer, Stefan Becker, David Münch +1
Adversarial patches are still a simple yet powerful white box attack that can be used to fool object detectors by suppressing possible detections. The patches of these so-called ev…
Geo-Tiles for Semantic Segmentation of Earth Observation Imagery
Sebastian Bullinger, Florian Fervers, Christoph Bodensteiner +1
To cope with the high requirements during the computation of semantic segmentations of earth observation imagery, current state-of-the-art pipelines divide the corresponding data i…
READMem: Robust Embedding Association for a Diverse Memory in Unconstrained Video Object Segmentation
Stéphane Vujasinović, Sebastian Bullinger, Stefan Becker +3
We present READMem (Robust Embedding Association for a Diverse Memory), a modular framework for semi-automatic video object segmentation (sVOS) methods designed to handle unconstra…
Uncertainty-aware Vision-based Metric Cross-view Geolocalization
Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +2
This paper proposes a novel method for vision-based metric cross-view geolocalization (CVGL) that matches the camera images captured from a ground-based vehicle with an aerial imag…
Bézier Curve Gaussian Processes
Ronny Hug, Stefan Becker, Wolfgang Hübner +2
Probabilistic models for sequential data are the basis for a variety of applications concerned with processing timely ordered information. The predominant approach in this domain i…
Continuous Self-Localization on Aerial Images Using Visual and Lidar Sensors
Florian Fervers, Sebastian Bullinger, Christoph Bodensteiner +2
This paper proposes a novel method for geo-tracking, i.e. continuous metric self-localization in outdoor environments by registering a vehicle's sensor information with aerial imag…
Revisiting Click-based Interactive Video Object Segmentation
Stephane Vujasinovic, Sebastian Bullinger, Stefan Becker +3
While current methods for interactive Video Object Segmentation (iVOS) rely on scribble-based interactions to generate precise object masks, we propose a Click-based interactive Vi…
Improving Semantic Image Segmentation via Label Fusion in Semantically Textured Meshes
Florian Fervers, Timo Breuer, Gregor Stachowiak +3
Models for semantic segmentation require a large amount of hand-labeled training data which is costly and time-consuming to produce. For this purpose, we present a label fusion fra…
A Comparison of Deep Saliency Map Generators on Multispectral Data in Object Detection
Jens Bayer, David Münch, Michael Arens
Deep neural networks, especially convolutional deep neural networks, are state-of-the-art methods to classify, segment or even generate images, movies, or sounds. However, these me…
Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction
Stefan Becker, Ronny Hug, Wolfgang Hübner +2
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 incr…
MissFormer: (In-)attention-based handling of missing observations for trajectory filtering and prediction
Stefan Becker, Ronny Hug, Wolfgang Hübner +2
In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning t…
MODISSA: a multipurpose platform for the prototypical realization of vehicle-related applications using optical sensors
Björn Borgmann, Volker Schatz, Marcus Hammer +3
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…
3D Surface Reconstruction From Multi-Date Satellite Images
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. Since satellite images provide suitable pro…
Handling Missing Observations with an RNN-based Prediction-Update Cycle
Stefan Becker, Ronny Hug, Wolfgang Hübner +2
In tasks such as tracking, time-series data inevitably carry missing observations. While traditional tracking approaches can handle missing observations, recurrent neural networks…
A Photogrammetry-based Framework to Facilitate Image-based Modeling and Automatic Camera Tracking
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…
Integration of the 3D Environment for UAV Onboard Visual Object Tracking
Stéphane Vujasinović, Stefan Becker, Timo Breuer +3
Single visual object tracking from an unmanned aerial vehicle (UAV) poses fundamental challenges such as object occlusion, small-scale objects, background clutter, and abrupt camer…
A Short Note on Analyzing Sequence Complexity in Trajectory Prediction Benchmarks
Ronny Hug, Stefan Becker, Wolfgang Hübner +1
The analysis and quantification of sequence complexity is an open problem frequently encountered when defining trajectory prediction benchmarks. In order to enable a more informati…
Quantifying the Complexity of Standard Benchmarking Datasets for Long-Term Human Trajectory Prediction
Ronny Hug, Stefan Becker, Wolfgang Hübner +1
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 t…
Image-based OoD-Detector Principles on Graph-based Input Data in Human Action Recognition
Jens Bayer, David Münch, Michael Arens
Living in a complex world like ours makes it unacceptable that a practical implementation of a machine learning system assumes a closed world. Therefore, it is necessary for such a…