Dr. rer. nat. Marco Körner

Marco Körner wurde 1984 in Salzwedel geboren. Nach seinem Studium der Informatik an der Friedrich-Schiller-Universität Jena wurde er 2009 wissenschaftlicher Mitarbeiter am dortigen Lehrstuhl für Digitale Bildverarbeitung, wo er in verschiedene Forschungsprojekte und Lehrprogramme eingebunden war. Während dieser Zeit fertigte er unter der Betreuung von Prof. Dr.-Ing. Joachim Denzler seine Disseration mit dem Titel "Methods for Model-based and Model-free Recognition of Articulated Actions in Multi-View Environments" an und promovierte 2015 zum Dr. rer. nat.

Seit Februar 2015 ist er als akademischer Rat der stellvertretende Leiter des Lehrstuhls für Methodik der Fernerkundung und Leiter der Computer Vision Research Group. Dort beschäftigt sich seine Forschung hauptsächlich mit der Entwicklung und Anwendung von Methoden der digitalen Bildverarbeitung, Computer Vision und des maschinellen Lernens im Bereich der Erdbeobachtung und Fernerkundung

News

Forschung

Interessen

  • Computer Vision Bildanalyse
  • digitale Bildverarbeitung
  • maschinelles Lernen

Projekte

Multi-task Learning

Viele Anwendungen wie die Interpretation von Straßenräumen für das autonome Fahren erfordern die Lösung verschiedener Aufgaben auf Grundlage digitaler Bilder. Die zu extrahierenden Informationen spiegeln dabei typischerweise verschiedene Aspekte identischer Objekte der physischen Welt wieder. Dieses Wissen um bestehende Korrelationen zwischen den Tasks kann ausgenutzt werden um die einzelnen Tasks effizienter und mit höherer Genauigkeit lösen zu können.

Single-Image Depth Estimation

The generation of depth maps is essential for numerous applications, such as autonomous driving or augmented reality. Typically these are generated from stereo image pairs or by making use of active sensors (e.g. LiDAR or RGB-D cameras). Based on the monocular depth perception of humans, this project investigates the estimation of depth maps from single images using artificial neural networks .

MAV 4 BIM

This project investigates the usability of image sequences from Micro Aerial Vehicles (MAVs) for generating complete and high resolutional 3D building information models (BIMs). Beside the modelling of the building exterior in a global reference frame, the interior should be reconstructed from independent indoor flights as well. An automatic alignment of the reconstructed indoor and outdoor building models offer the generation of LOD-4 building models.

CNN-based Large-Scale Land Use and Land Cover Classification

This project aims at adopting classification methods based on Convolutional Neural Networks for Land Use and Land Cover classification. Publicly available geodata (OpenStreetMap) and multi-spectral Sentinel-2 imagery is used as training data.

Prediction of Image Sequences from Driver Assistance Systems by implicit modelling of Activity Patterns

Safe autonomous driving systems rely on autonomous vehicles that are able to drive anticipatory. This project aims at simulating the human anticipation of future scenarios by predicting traffic events from generated video frames. We build up on state of the art methods in Computer Vision and Machine Learning to generate prospective frames of a video based on the latest observed video sequence. Features learned by the model are further used for modeling and analyzing traffic scenes and activity patterns of traffic participants.

Traffic Infrastructure Modeling

Modeling the traffic infrastructure based on aerial and ground images becomes ever more important, especially since autonomous driving systems seem to be a part of the near future. This project aims to develop algorithms to process images captured by dash cams mounted on top of a car in order to detect traffic relevant objects, such as traffic participants and all infrastructure elements. In this context, we also use aerial images to analyze group behavior and predict traffic actions.

Temporal Vegetation Modeling using Recurrent Networks

Land Cover Classification approaches traditionally concentrate on spectral and textural features. However, some classes (e.g. crops) distinguish themselves with characteristic spectro-temporal behaviour, which can be utilized for classificaton. We employ Long Short-Term Memory neural networks for multi-temporal vegetation modeling and crop identification.

Publikationen

2019

  • Aigner, Sandra; Körner, Marco: FutureGAN: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3d Convolutions in Progressively Growing GANs. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) (tbp), 2019 more… BibTeX
  • Koch, Tobias; Körner, Marco; Fraundorfer, Friedrich: Automatic and Semantically-Aware 3D UAV Flight Planning for Image-Based 3D Reconstruction. Remote Sensing 11 (13), 2019 more… BibTeX Full text ( DOI )
  • Koch, Tobias; Liebel, Lukas; Fraundorfer, Friedrich; Körner, Marco: Evaluation of CNN-Based Single-Image Depth Estimation Methods. Proceedings of the European Conference on Computer Vision Workshops (ECCV-WS), Springer International Publishing, 2019 more… BibTeX
  • König, Peter; Aigner, Sandra; Körner, Marco: Enhancing Traffic Scene Predictions with Generative Adversarial Networks. Proceedings of the IEEE Intelligent Transportation Systems Conference (ITSC), 2019 more… BibTeX
  • Rußwurm, Marc; Lefèvre, Sébastien; Courty, Nicolas; Emonet, Rémi; Körner, Marco; Tavenard, Romain: End-to-end Learning for Early Classification of Time Series. arXiv preprint arXiv:1901.10681, 2019 more… BibTeX

2018

  • Azimi, Seyed Majid; Fischer, Peter; Körner, Marco; Reinartz, Peter: Aerial LaneNet: Lane Marking Semantic Segmentation in Aerial Imagery using Wavelet-Enhanced Cost-sensitive Symmetric Fully Convolutional Neural Networks. IEEE Transactions on Geoscience and Remote Sensing, 2018 more… BibTeX Full text ( DOI )
  • Azimi, Seyed Majid; Vig, Eleonora; Bahmanyar, Reza; Körner, Marco; Reinartz, Peter: Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery. arXiv preprint arXiv:1807.02700, 2018 more… BibTeX Full text ( DOI )
  • Bittner, Ksenia; Adam, Fathalrahman; Cui, Shiyong; Körner, Marco; Reinartz, Peter: Building Footprint Extraction From VHR Remote Sensing Images Combined With Normalized DSMs Using Fused Fully Convolutional Networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTAR) 11, 2018, 2615-2629 more… BibTeX Full text ( DOI )
  • Bittner, Ksenia; Körner, Marco: Automatic Large-Scale 3D Building Shape Refinement Using Conditional Generative Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018 more… BibTeX
  • Bittner, Ksenia; d'Angelo, Pablo; Körner, Marco; Reinartz, Peter: AUTOMATIC LARGE-SCALE 3D BUILDING SHAPE REFINEMENT USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORKS. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) XLII-2, 2018, 103--108 more… BibTeX Full text ( DOI )
  • Bittner, Ksenia; d’Angelo, Pablo; Körner, Marco; Reinartz, Peter: DSM-to-LoD2: Spaceborne Stereo Digital Surface Model Refinement. Remote Sensing 10 (12), 2018 more… BibTeX Full text ( DOI )
  • Kang, Jian; Körner, Marco; Wang, Yuanyuan; Taubenböck, Hannes; Zhu, Xiao Xiang: Building instance classification using street view images. ISPRS Journal of Photogrammetry and Remote Sensing, 2018 more… BibTeX Full text ( DOI )
  • Liebel, Lukas; Körner, Marco: Auxiliary Tasks in Multi-task Learning. arXiv preprint arXiv:1805.06334, 2018 more… BibTeX
  • Rußwurm, Marc; Körner, Marco: Multi-Temporal Land Cover Classification with Sequential Recurrent Encoders. ISPRS International Journal of Geo-Information 7 (4), 2018, 129 more… BibTeX Full text ( DOI )
  • Rußwurm, Marc; Körner, Marco: Convolutional LSTMs for Cloud-Robust Segmentation of Remote Sensing Imagery. Proceedings of the Conference on Neural Information Processing Systems Workshops (NeurIPSW), 2018 more… BibTeX
  • Schmitt, Michael; Hughes, Lloyd; Körner, Marco; Zhu, Xiao Xiang: COLORIZING SENTINEL-1 SAR IMAGES USING A VARIATIONAL AUTOENCODER CONDITIONED ON SENTINEL-2 IMAGERY. ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2, 2018, 1045--1051 more… BibTeX Full text ( DOI )

2017

  • Kang, Jian; Wang, Yuanyuan; Körner, Marco; Zhu, Xiao Xiang: Robust Object-Based Multipass InSAR Deformation Reconstruction. IEEE Transactions on Geoscience and Remote Sensing (TGRS) 8 (55), 2017, 4239--4251 more… BibTeX Full text ( DOI )
  • Kang, Jian; Wang, Yuanyuan; Körner, Marco; Zhu, Xiao Xiang: Improve Multi-baseline InSAR Parameter Retrieval by Semantic Information from Optical Images. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2017 more… BibTeX
  • Kang, Jian; Wang, Yuanyuan; Körner, Marco; Zhu, Xiao Xiang: Robust Object-based Multi-Baseline InSAR. Advances in the Science and Applications of SAR Interferometry and Sentinel-1 InSAR (FRINGE), 2017 more… BibTeX
  • Rußwurm, Marc; Körner, Marco: Multitemporal Crop Identification from Medium-Resolution Multi-Spectral Satellite Images based on Long Short-Term Memory Neural Networks. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) XLII-1/W1, 2017, 551--558 more… BibTeX Full text ( DOI )
  • Rußwurm, Marc; Körner, Marco: Temporal Vegetation Modelling using Long Short-Term Memory Networks for Crop Identification from Medium-Resolution Multi-Spectral Satellite Images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017 more… BibTeX

2016

  • Kang, Jian; Wang, Yuanyuan; Körner, Marco; Zhu, Xiao Xiang: Object-based InSAR deformation reconstruction with application to bridge monitoring. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2016 more… BibTeX Full text ( DOI )
  • Koch, Tobias; d'Angelo, Pablo; Kurz, Franz; Fraundorfer, Friedrich; Reinartz, Peter; Körner, Marco: The TUM-DLR Multimodal Earth Observation Evaluation Benchmark. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016 more… BibTeX
  • Koch, Tobias; Körner, Marco; Fraundorfer, Friedrich: Automatic Alignment of Indoor and Outdoor Building Models using 3D Line Segments. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2016 more… BibTeX
  • Liebel, Lukas; Körner, Marco: Single-Image Super Resolution for Multispectral Remote Sensing Data Using Convolutional Neural Networks. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) XLI-B3, 2016, 883--890 more… BibTeX Full text ( DOI )

2015

  • Körner, Marco; Krishna, Mahesh Venkata; Süße, Herbert; Ortmann, Wolfang; Denzler, Joachim: Regularized Geometric Hulls for Bio-medical Image Segmentation. Annals of the BMVA 2015 (5), 2015, 1--12 more… BibTeX

2014

  • Jiang, Xiaoyan; Körner, Marco; Haase, Daniel; Denzler, Joachim: A Graph-based MAP Solution for Multi-Person Tracking Using Multi-Camera Systems. Proceedings of the 9th International Conference on Computer Vision Theory and Applications (VISAPP), 2014 more… BibTeX
  • Krishna, Mahesh Venkata; Bodesheim, Paul; Körner, Marco; Denzler, Joachim: Temporal Video Segmentation by Event Detection: A Novelty Detection Approach. Pattern Recognition and Image Analysis (PRIA) 24 (2), 2014, 243--255 more… BibTeX
  • Körner, Marco; Krishna, Mahesh Venkata; Süße, Herbert; Ortmann, Wolfgang; Denzler, Joachim: Regularized Geometric Hulls for Robust Cell Nucleus Segmentation from Microscopy Images. Proceedings of the 18th Annual Conference on Medical Image Understanding and Analysis (MIUA), 2014 more… BibTeX
  • Süße, Herbert; Ortmann, Wolfgang; Lautenschläger, Janin; Lautenschläger, Christian; Körner, Marco; Großkreutz, Julian; Denzler, Joachim: Quantitative Analysis of Pathological Mitochondrial Morphology in Neuronal Cells in Confocal Laser Scanning Microscopy Images. Proceedings of the 2th International Work-Conference on Bioinformatics and Biomedical Engineering (IWBBIO), 2014 more… BibTeX

2013

  • Jiang, Xiaoyan; Haase, Daniel; Körner, Marco; Bothe, Wolfgang; Denzler, Joachim: Accurate 3D Multi-Marker Tracking in X-ray Cardiac Sequences Using a Two-Stage Graph Modeling Approach. Computer Analysis of Images and Patterns (CAIP) (Lecture Notes in Computer Science), Springer, 2013 more… BibTeX
  • Krishna, Mahesh Venkata; Körner, Marco; Denzler, Joachim: Hierarchical Dirichlet Processes for Unsupervised Online Multi-View Action Perception using Temporal Self-Similarity Features. Proceedings of the 7th ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), 2013 more… BibTeX
  • Körner, Marco; Denzler, Joachim: JAR-Aibo: A Multi-View Dataset for Evaluation of Model-Free Action Recognition Systems. New Trends in Image Analysis and Processing (ICIAP) (Lecture Notes in Computer Science), Springer, 2013 more… BibTeX
  • Körner, Marco; Denzler, Joachim: Temporal Self-Similarity for Appearance-Based Action Recognition in Multi-View Setups. Computer Analysis of Images and Patterns (CAIP) (Lecture Notes in Computer Science), Springer, 2013 more… BibTeX
  • Süße, Herbert; Ortmann, Wolfgang; Lautenschläger, Christian; Körner, Marco; Schmidt, Carsten; Stallmach, Andreas; Denzler, Joachim: Oriented Differences of Boxes Operators for Blood Vessel Segmentation and Analysis in Confocal Laser Endomicroscopy Images with Minimal User Interaction. Proceedings of the 17th Annual Conference on Medical Image Understanding and Analysis (MIUA), 2013 more… BibTeX

2012

  • Bredereck, Michael; Jiang, Xiaoyan; Körner, Marco; Denzler, Joachim: Data Association for Multi-Object Tracking-by-Detection in Multi-Camera Networks. Proceedings of the 6th ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC), 2012 more… BibTeX
  • Körner, Marco; Denzler, Joachim: Analyzing the Subspaces Obtained by Dimensionality Reduction for Human Action Recognition from 3d Data. Proceedings of the 9th IEEE International Conference on Advanced Video and Signal-Based Surveillance (AVSS), 2012 more… BibTeX
  • Körner, Marco; Haase, Daniel; Denzler, Joachim: Scale-Independent Spatio-Temporal Statistical Shape Representations for 3d Human Action Recognition. Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods (ICPRAM), SciTePress, 2012 more… BibTeX

2011

  • Körner, Marco; Süße, Herbert; Ortmann, Wolfgang; Denzler, Joachim: A Method for Fast Composing of Images Captured from Deformed Documents by a Quadocular Scanner Setup. Proceedings of the 12th IAPR Conference on Machine Vision Applications (MVA), 2011 more… BibTeX

Supervisions

PhD theses

  • 3D Building Model Alignment from UAV Imagery (Tobias Koch)
  • Traffic Infrastructure Modeling (Sandra Aigner)
  • Video Frame Prediction from ADAS Imagery (Lukas Liebel)
  • Building Type Classification from Satellite Imagery (Ksenia Bittner)

Master theses

  • Deep Convolutional Neural Networks for Semantic Segmentation of Multispectral Sentinel-2 Satellite Imagery: An Open Data Approach to Large-Scale Land Use and Land Cover Classification (Lukas Liebel, M.Sc. Geodesy and Geoinformation)

Diploma theses

  • Data Association of Multi-Object Tracking in Multi-Camera Systems (Michael Bredereck, Diploma in Computer Sciences)

Bachelor theses

  • 3D Surface Reconstruction using Polarisation Cues (Lea Albrecht, B.Sc. Geodesy and Geoinformation)
  • Gesture Recognition from Real-Time Depth Data (Marcel Simon, B.Sc. Computer Sciences, FSU Jena)
  • Generic Object Detection in Multi-Camera Systems (Sebastian Krautwurst, B.Sc. Computer Sciences, FSU Jena)

Curriculum Vitæ

  • seit 2015: akademischer Rat an der TU München und stellvertretender Leuter des Lehrstuhls für Methodik der Fernerkundung
  • 2015: Dr. rer. nat.; Dissertation "Methods for Model-based and Model-free Recognition of Articulated Actions in Multi-View Environments"
  • 2014: Forschungsaufenthalt an der UC San Diego, USA
  • 2008–2014: wissenschaftlicher Mitarbeiter am Lehrstuhl für Digitale Bildverarbeitung, FSU Jena
  • 2012: Forschungsaufenthalt am CIC-IPN Mexico City und am CIMAT Guanajuato, Mexico
  • 2008: Dipl.-Inf.; Diplomarbeit "Methoden zur 3D-Kartierung des Fahrzeugumfeldes mittels Echtzeit-Tiefensensorik"
  • 2007: Studienarbeit "Merkmale in Echtzeit-Tiefendaten"
  • 2003–2008: Studium der Informatik mit Nebenfach Psychologie an der Friedrich-Schiller-Universität Jena
  • 2003: Abitur am Geschwister-Scholl-Gymnasium in Gardelegen