Rudolf Mester
Bakgrunn og aktiviteter
Rudolf Mester har ledet Visual Sensorics and Information Processing Lab ved Goethe University, Frankfurt, siden 2004.
Siden oktober 2018 har han vært hos NTNU på Institutt for Datateknologi og Informatikk (IDI) som professor (DNV GL legatprofessorat) og medlem av Norwegian Open AI Lab.
Tidligere har han ledet forskningsinitiativer og prosjekter innen intelligent visual vehicle sensorics, applikasjoner av AI i mobile systemer, visual surround sensing for autonom kjøring, og maskinlæring for ‘trenbare kjøretøy’ og kjøretøykontroll.
Foruten disse applikasjonsorienterte emnene, utfører han grunnleggende forskning innen ytelsesanalyse av AI-metoder, kvalitetssikring av maskinlæringsalgoritmer, og innen de fundamentale perception og planleggings algoritmene for kjøretøy som bygger på estimasjonsteori, kontrollteori og maskinlæring.
På NTNU fokuserer Rudolf Mester på ytelse, tillitskvantifisering og kvalitetssikring av AI/maskinlærings-metoder.
Han er fokusert på klassiske og ML-baserte perception metoder for intelligente maskiner og autonome systemer, både på vei, under vann, og i luft.
Støtten fra DNV GL for dette legatprofessoratet er i godt samarbeid, annerkjent og verdsatt.
Vitenskapelig, faglig og kunstnerisk arbeid
2021
- (2021) Few-Shot Open World Learner. IFAC-PapersOnLine.
- (2021) The VAROS Synthetic Underwater Data Set: Towards realistic multi-sensor underwater data with ground truth. IEEE International Conference on Computer Vision (ICCV).
- (2021) Image Inpainting with Learnable Feature Imputation. Pattern Recognition, 42nd DAGM German Conference.
- (2021) Improving Vehicle Localization with Two Low-Cost GPS Receivers. Innovations in Smart Cities Applications.
- (2021) Geolocation estimation of target vehicles using neural network-based image processing and geometric computations. 2021.
2020
- (2020) Autoferry Gemini: a real-time simulation platform for electromagnetic radiation sensors on autonomous ships. IOP Conference Series: Materials Science and Engineering.
- (2020) A Shared Representation for Object Tracking and Classification using Siamese Networks. 2020 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI).
- (2020) Identifying and Counting Vehicles in Multiple Lanes by Using a Low-Cost Vehicle-Mounted Sensor for Intelligent Traffic Management Systems. Hybrid Artificial Intelligent Systems, 15th International Conference, HAIS 2020.
2019
- (2019) Mono-SF: Multi-View Geometry meets Single-View Depth for Monocular Scene Flow Estimation of Dynamic Traffic Scenes. IEEE International Conference on Computer Vision (ICCV).
- (2019) DistanceNet: Estimating Traveled Distance from Monocular Images using a Recurrent Convolutional Neural Network. IEEE Computer Society Conference on Computer Vision and Pattern Recognition workshops.
- (2019) SDNet: Semantically Guided Depth Estimation Network. Lecture Notes in Computer Science (LNCS). vol. 11824 LNCS.
- (2019) Fast Cross Correlation for Limited Angle Tomographic Data. Lecture Notes in Computer Science (LNCS). vol. 11482 LNCS.
- (2019) Fast alignment of limited angle tomograms by projected cross correlation. European Signal Processing Conference. vol. 2019-September.
- (2019) DeepPrivacy: A Generative Adversarial Network for Face Anonymization. Advances in Visual Computing.
- (2019) Simulated autonomous driving in a realistic driving environment using deep reinforcement learning and a deterministic finite state machine. APPIS'19: Proceedings of the 2nd International Conference on Applications of Intelligent Systems.
2018
- (2018) CNN-based multi-frame IMO detection from a monocular camera. IEEE conference proceedings. 2018. ISBN 978-1-5386-4452-2.
- (2018) Spatio-Temporal Depth Interpolation (STDI). IEEE conference proceedings. 2018. ISBN 978-1-5386-4452-2.