Felix Ott

Felix Ott
Fraunhofer Institute for Integrated Circuits IIS | IIS · Department of Locating and Communication Systems

PhD Student
I am a scientific researcher at the Fraunhofer IIS and a PhD candidate the Ludwig-Maximilians University Munich.

About

15
Publications
1,270
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
54
Citations
Citations since 2016
15 Research Items
53 Citations
2016201720182019202020212022010203040
2016201720182019202020212022010203040
2016201720182019202020212022010203040
2016201720182019202020212022010203040
Additional affiliations
June 2020 - present
Ludwich-Maximilians University Munich
Position
  • PhD Candidate

Publications

Publications (15)
Conference Paper
Full-text available
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target doma...
Conference Paper
The Global Navigation Satellite System (GNSS) community shows great interest in detecting and eliminating GNSS interference, i.e., jammers. State-of-the-art techniques employ either threshold-based mechanisms or supervised learning on raw data streams or features thereof. However, they require special expensive GNSS receiver hardware that needs to...
Article
Full-text available
Handwriting is one of the most frequently occurring patterns in everyday life and with it comes challenging applications such as handwriting recognition, writer identification and signature verification. In contrast to offline HWR that only uses spatial information (i.e., images), online HWR uses richer spatio-temporal information (i.e., trajectory...
Conference Paper
Interference signals degrade and disrupt Global Navigation Satellite System (GNSS) receivers, impacting their localization accuracy. Therefore, they need to be detected, classified, and located to ensure GNSS operation. State-of-the-art techniques employ supervised deep learning to detect and classify potential interference signals. Here, literatur...
Preprint
Visual-inertial localization is a key problem in computer vision and robotics applications such as virtual reality, self-driving cars, and aerial vehicles. The goal is to estimate an accurate pose of an object when either the environment or the dynamics are known. Recent methods directly regress the pose using convolutional and spatio-temporal netw...
Conference Paper
Full-text available
For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type...
Preprint
Full-text available
For many applications, analyzing the uncertainty of a machine learning model is indispensable. While research of uncertainty quantification (UQ) techniques is very advanced for computer vision applications, UQ methods for spatio-temporal data are less studied. In this paper, we focus on models for online handwriting recognition, one particular type...
Preprint
Full-text available
The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target doma...
Article
Full-text available
Radio frequency (RF)-based localization yields centimeter-accurate positions under mild propagation conditions. However, propagation conditions predominant in indoor environments (e.g. industrial production) are often challenging as signal blockage, diffraction and dense multipath lead to errors in the time of flight (TOF) estimation and hence to a...
Preprint
Full-text available
Common representation learning (CRL) learns a shared embedding between two or more modalities to improve in a given task over using only one of the modalities. CRL from different data types such as images and time-series data (e.g., audio or text data) requires a deep metric learning loss that minimizes the distance between the modality embeddings....
Preprint
Full-text available
Handwriting is one of the most frequently occurring patterns in everyday life and with it come challenging applications such as handwriting recognition (HWR), writer identification, and signature verification. In contrast to offline HWR that only uses spatial information (i.e., images), online HWR (OnHWR) uses richer spatio-temporal information (i....
Conference Paper
Full-text available
Multivariate Time Series (MTS) classification is important in various applications such as signature verification, person identification, and motion recognition. In deep learning these classification tasks are usually learned using the cross-entropy loss. A related yet different task is predicting trajectories observed as MTS. Important use cases i...
Article
This paper presents a handwriting recognition (HWR) system that deals with online character recognition in real-time. Our sensor-enhanced ballpoint pen delivers sensor data streams from triaxial acceleration, gyroscope, magnetometer and force signals at 100 Hz. As most existing datasets do not meet the requirements of online handwriting recognition...
Conference Paper
Full-text available
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly fro...
Preprint
Full-text available
Visual Odometry (VO) accumulates a positional drift in long-term robot navigation tasks. Although Convolutional Neural Networks (CNNs) improve VO in various aspects, VO still suffers from moving obstacles, discontinuous observation of features, and poor textures or visual information. While recent approaches estimate a 6DoF pose either directly fro...

Network

Cited By

Projects

Projects (3)
Project
The project DARCY (Development of an advanced interference detection and robustness capabilities system) aims at the development of a network of sensors for the detection, evaluation (influence on position and time determination), characterization (type) and localization of interferers. The focus is on the development and testing of different detectors (low/medium/high-end), algorithms for local evaluation, approaches from the fields of machine learning (ML) and crowdsourcing for the fusion of events and their representation.
Project
Zur Vernetzung von Forschung und Wirtschaft hat das Fraunhofer-Institut für Integrierte Schaltungen IIS in Kooperation mit der Friedrich-Alexander-Universität Erlangen-Nürnberg und der Ludwig-Maximilians-Universität München unter weiterer Beteiligung der Fraunhofer-Institute IKS und IISB eine einzigartige Forschungsinfrastruktur in Bayern geschaffen: das ADA Lovelace Center for Analytics, Data and Applications. Es verbindet als Kooperationsplattform für Wissenschaft und Wirtschaft auf innovative Art KI-Forschung mit KI-Anwendungen. Das Besondere am ADA Lovelace Center ist tatsächlich die enge Verbindung aus Forschung und industrieller Anwendung: Mit der Art und Weise, wie wir unsere Kompetenzen, Methoden und Verfahren aus dem Bereich der Künstlichen Intelligenz in den Fragestellungen der Praxis einsetzen und an ihnen weiterentwickeln, wie wir an Projekte herangehen und wie wir mit unseren Partnern aus Industrie und Wissenschaft zusammenarbeiten, wollen wir den Zugang der Unternehmen zu umfassender KI-Expertise erleichtern und so schnell konkreten Nutzen für sie herstellen; und zwar über die Grenze des derzeit Machbaren hinaus. So wollen wir Unternehmen vom enormen Potenzial von KI überzeugen und KI in die industrielle Anwendung bringen: Das ADA Lovelace Center versteht sich als Multiplikator, um KI-Kompetenz in einem Unternehmen aufzubauen oder die vorhandene KI-Kompetenz zu stärken bzw. weiterzuentwickeln. Das wissenschaftliche Methodenspektrum, das wir im ADA Lovelace Center dafür einsetzen, ist sehr breit und die Auswahl der richtigen Methode abhängig vom Anwendungsfall. Immer aber geht es bei uns um Datenanalyse: von der klassischen Zustandsbeschreibung über Vorhersagen von Ereignissen bis hin zu entscheidungsbasierten Methoden, die z.B. automatisiert eine bestimmte Handlung auslösen sollen. Dazu binden wir übrigens neben den genannten regionalen Playern auch viele andere nationale und internationale Wissenschaftspartner ein. An folgenden Kompetenzsäulen wird geforscht: • Automatisches Lernen • Sequenzbasiertes Lernen • Erfahrungsbasiertes Lernen • Few Labels Learning • Erklärbares Lernen • Mathematische Optimierung • Semantik • Few Data Learning Eine Beschreibung zu den oben genannten Kompetenzsäulen kann unter diesem Link https://www.scs.fraunhofer.de/de/referenzen/ada-center.html#381039553 gefunden werden.
Project
The goal of the project is to develop methods that enable robust localization. With the help of machine learning, positions are estimated automatically by using reference measurements as experience data. The measurements of different (inertial-, image-, and radio-based) localization systems are used as raw data, on the basis of which deep neural networks are trained, which replace parts or entire classic positioning pipelines.