Wegner, Jan Dirk, Dr.

Dr.  Jan Dirk Wegner

HIL  D 44.2 

Stefano-Franscini-Platz 5

8093 Zürich

Switzerland

  • phone +41 44 633 68 08 
  • mail
  • vcard V-Card (vcf, 1kb)

Additional information

Research area

Geospatial Computer Vision, Photogrammetry, Remote Sensing, Large-Scale Machine Learning, Deep Convolutional Neural Networks

Curriculum Vitae

Jan Dirk Wegner was born in Oldenburg (Germany). He received the Dipl.-Ing. (Univ.) degree in geodesy and geoinformatics in September 2007 and the Dr.-Ing. degree in August 2011, both from Leibniz Universität Hannover (LUH).

In 2005 he studied two semesters abroad at the University of Melbourne (Australia) with focus on close range photogrammetry. Between November 2006 and September 2007 he did an internship at the French Space Agency (CNES) in Toulouse (France) specializing on automatic co-registration of high-resolution optical and synthetic aperture radar (SAR) images of urban areas. From October 2007 until December 2011 he was a full-time scientific collaborator at the Institute of Photogrammetry and GeoInformation (IPI) at LUH working on object recognition in high-resolution optical and SAR data. His doctoral thesis, which he passed with distinction, was part of the bundle project AnalySAR funded by the German Science Foundation (DFG).

In December 2011 he was granted an ETH Postdoctoral fellowship and held a PostDoc position at Konrad Schindler`s group at Photogrammetry and Remote Sensing (ETH Zurich) between April 2012 and March 2015. Since April 2015 he is senior scientist in the same group. His main interests are in the interdisciplinary field of photogrammetry, remote sensing, computer vision, and machine learning. He is currently involved in six different projects (see our project page for further information):

(1) cataloging public objects at city-scale from aerial and street-level images (with Pietro Perona, Steve Branson, and David Hall at Caltech),

(2) large-scale deep learning for automatic generation of online maps (with Aurélien Lucchi and Martin Jaggi),

(3) joint dense matching and semantic segmentation of oblique, aerial images to generate 3D city models (with Maros Bláha and Audrey Richard),

(4) classification of large-scale terrestrial laser scans (with Timo Hackel),

(5) underwater 3D reconstruction of corals (with Paul Beardsley, Tejaswi Digumarti (both Disney Research), Silvano Galliani, and Mathias Rothermel),

(6) pixel-accurate semantic segmentation of aerial images with fully convolutional neural nets.

He was awarded the "Wissenschaftspreis der Deutschen Geodätischen Kommission" (science award of the German Geodetic Commission) in 2014; awarded every two years to an internationally recognized young researcher.

He is lecturing the image processing course (at BSc level), the Photogrammetry and 3D Vision Lab, and the Image Interpretation course (both at MSc level) .

He serves as associate editor of La Revue Française de Photogrammétrie et de Télédétection, and was secretary of ISPRS commission III/WG 4 "3D Scene Analysis" from 2012 to 2016. Since 2016 he is chairing the newly founded ISPRS II/WG 6 "Large-scale machine learning for geospatial data analysis", where he aims at fostering research on large-scale multi-view, multi-scale, and multi-temporal geospatial computer vision problems.

Together with colleagues he is running the 1) ISPRS benchmark challenge for 2D pixel-wise semantic segmentation, object recognition, and 3D reconstruction using very high-resolution aerial images and airborne laser scans and 2) the Large-Scale Point Cloud Classification Benchmark that contains terrestrial laser scans of urban scenes with over one billion labeled points.

In 2015 he was a SNSF visiting scientist at Prof. Pietro Perona's Computer Vision group at the California Institute of Technology. Together with the Caltech group he is since then running the RegisTree project to develop new methods to automatically build rich inventories of trees at city-scale based on aerial and street-level images (Demo), (LA Times article, KPCC radio interview, Caltech Press release, Futurity Research News).

In 2016 he was an invited scientist at IGN MATIS Lab (fully funded by Univerité Paris Est) working on large-scale, deep learning methods for geospatial computer vision.

Additional information

List of Publications (my publications on Google Scholar)

 

Dissertation

WEGNER, J.D.: DETECTION AND HEIGHT ESTIMATION OF BUILDINGS FROM SAR AND OPTICAL IMAGES USING CONDITIONAL RANDOM FIELDS, DISSERTATION, 2011.

 

Book chapter

Thiele, A., Wegner, J.D., Soergel, U.: Building Reconstruction from Multi-Aspect InSAR Data, In: Soergel, U. (ed.): Radar Remote Sensing of Urban Areas, Berlin: Springer, 2010, pp. 187-214.

 

Soergel, U., Wegner, J.D., Thiele, A.: Fusion von optischen und Radardaten, In: Heipke, C. (publisher), Freeden, W., Rummel, R. (ed.): Handbuch der Geodäsie, Berlin Heidelberg: Springer, 2016, pp. 1-37.

 

Peer reviewed journal papers

Marmanis, D., Schindler, K., Wegner, J.D., Galliani, S., Datcu, M., Stilla, U. : Classification with an edge: improving semantic image segmentation with boundary detection, arXiv:1612.01337v1, 2016.

Theiler, P., Wegner, J.D., Schindler, K.: Globally Consistent Registration of Terrestrial Laser Scans via Graph Optimization (PDF, 18.2 MB), ISPRS Journal of Photogrammetry and Remote Sensing, vol. 109, 2015, pp. 126 - 136.

Wegner, J.D., Montoya, J., Schindler, K.: Road networks as collections of minimum cost paths, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 108, 2015, pp. 128-137.

Tokarczyk, P., Wegner, J.D., Walk, S., Schindler, K.: Features, color spaces, and boosting: New insights on semantic classification of remote sensing images, IEEE Transactions on Geoscience and Remote Sensing, vol. 53(1), 2015, pp. 280-295.

Theiler, P., Wegner, J.D., Schindler, K.: Keypoint-based 4-Points Congruent Sets - automated marker-less registration of laser scans, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 96, 2014, pp. 149-163.

Wegner, J.D., Ziehn, J.R., Soergel, U.: Combining high-resolution optical and InSAR features for height estimation of buildings with flat roofs, IEEE Transactions on Geoscience and Remote Sensing, vol. 52(9), 2014, pp. 5840-5854.

Rottensteiner, F., Sohn, G., Gerke, M., Wegner, J.D., Breitkopf, U., Jung, J.: Results of the ISPRS Benchmark on Urban Object Detection and 3D Building Reconstruction, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 93, 2014, pp. 256–271.

Kohoutek, T., Mautz, R., Wegner, J.D.: Fusion of Building Information and Range Imaging for Autonomous Location Estimation in Indoor Environments, Sensors, vol. 13(2), 2013, pp. 2430-2446.

Ok, A. O., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., Toprak, V.: Matching of Straight Line Segments from Aerial Stereo Images of Urban Areas, ISPRS Journal of Photogrammetry and Remote Sensing, vol. 74, 2012, pp. 133–152.

Ok, A. O., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., Toprak, V.: Accurate Reconstruction of Near-Epipolar Line Segments from Stereo Aerial Images, Photogrammetrie, Fernerkundung, Geoinformation (PFG), vol. 4, 2012, pp. 341–354.

Wegner, J.D., Hänsch, R., Thiele, A., Soergel, U.: Building Detection From One Orthophoto and High-Resolution InSAR Data Using Conditional Random Fields, IEEE Journal of selected topics in applied Earth Observations and Remote Sensing, vol. 4(1), 2011, pp. 83-91.

Wegner, J.D., Auer, S., Soergel, U.: Extraction and Geometrical Accuracy of Double-bounce Lines in High-Resolution SAR Images, Photogrammetric Engineering & Remote Sensing, vol. 76(9), 2010, pp. 1071-1080.

 

Peer reviewed conference papers

 

Blaha, M., Vogel, C., Richard, A., Wegner, J.D., Schindler, K., Pock, T.: Large-Scale Semantic 3D Reconstruction: an Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling (PDF, 3.6 MB), (supplementary (PDF, 8.8 MB)), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. oral

 

Wegner*, J.D., Branson*, S., Hall, D., Schindler, K., Perona, P.: Cataloging Public Objects Using Aerial and Street-Level Images – Urban Trees (PDF, 1.7 MB) (supplementary (PDF, 11.9 MB) (RegisTree project website), (Demo), (LA Times article, KPCC radio interview, Caltech Press release, Futurity Research News), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. (* authors contributed equally to this publication)

 

Hackel, T., Wegner, J.D., Schindler, K.: Contour detection in unstructured 3D point clouds (PDF, 1.4 MB), IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. oral

 

Marmanis, D., Wegner, J.D., Galliani, S., Schindler, K., Datcu, M., Stilla, U.: Semantic segmentation of aerial images with an ensemble of fully convolutional neural networks (PDF, 1.4 MB), ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016.

 

Hackel, T., Wegner, J.D., Schindler, K.: Fast semantic segmentation of 3d point clouds with strongly varying density (PDF, 5.6 MB).  ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016.

 

Montoya, J., Wegner, J.D., Ladický, L., Schindler, K.: On the evaluation of higher-order cliques for road network extraction, In: Joint Urban Remote sensing Event (JURSE), Lausanne, Switzerland, 2015.

Montoya, J., Wegner, J.D., Ladický, L., Schindler, K.: Semantic segmentation of aerial images in urban areas with class-specific higher-order cliques, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. II(3/W4), 2015, pp. 127-133. PIA15+HRIGI15 best paper award

Theiler, P., Wegner, J.D., Schindler, K.: Fast registration of laser scans with 4-points congruent sets - what works and what doesn't, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. II-3, 2014, pp. 149-156.

Montoya, J., Wegner, J.D., Ladický, L., Schindler, K.: Mind the gap: modeling local and global context in (road) networks, German Conference on Pattern Recognition (GCPR), Münster, Germany, 2014.

Theiler, P., Wegner, J.D., Schindler, K.: Markerless point cloud registration with keypoint-based 4-points congruent sets, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. II(5/W2), 2013, pp. 283-288.

Sasagawa, A., Baltsavias, E., Kocaman Aksakal, S., Wegner, J.D.: Investigation on automatic change detection using pixel-changes and DSM-changes with ALOS-PRISM triplet images, ISPRS Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XL(7/W2), 2013, pp. 213-217.

Tokarczyk, P., Wegner, J.D., Walk, S., Schindler, K.: Beyond hand-crafted features in remote sensing, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. II(3/W1), 2013, pp. 35-40.

Wegner, J.D., Montoya, J., Schindler, K.: A higher-order CRF model for road network extraction, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, USA, 2013

Wegner, J.D., Rosenhahn, B., Soergel, U.: Segmentation and classification of objects with implicit scene context, In: Dellaert, F., Frahm, J.-M., Pollefeys, M., Rosenhahn, B. (eds.), Outdoor and Large-Scale Real-World Scene Analysis, Dagstuhl Seminar 11261, LNCS 7474, Berlin: Springer, 2012, pp. 264-284.

Niemeyer, J., Wegner, J.D., Mallet, C., Rottensteiner, F., Soergel, U.: Conditional Random Fields For Urban Scene Classification With Full Waveform LiDAR Data, In: Stilla, U., Rottensteiner, F., Mayer, H., Jutzi, B., Butenuth, M. (eds.), Photogrammetric Image Analysis, LNCS 6952, Berlin: Springer, 2011, pp. 233-244.

Ok, A.O., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., Toprak, V.: In-Strip Matching and Reconstruction of Line Segments from UHR Aerial Image Triplets, In: Stilla, U., Rottensteiner, F., Mayer, H., Jutzi, B., Butenuth, M. (eds.), Photogrammetric Image Analysis, LNCS 6952, Berlin: Springer, 2011, pp. 61-72.

Wegner, J.D., Rosenhahn, B., Soergel, U.: Implicit scene context for object segmentation and classification, In: Mester, R., Felsberg, M. (eds.), DAGM, LNCS 6835, Berlin: Springer, 2011, pp. 31-40.

Wegner, J.D., Rosenhahn, B., Soergel, U.: Segment-based building detection with Conditional Random Fields, In: Stilla, U., Gamba, P., Juergens, C., Maktav, D. (eds.), Proceedings of 6th IEEE/GRSS/ISPRS Joint Urban Remote Sensing Event, Munich, 2011, pp. 205-208.

Wegner, J.D., Ok, A.O., Thiele, A., Rottensteiner, F., Soergel, U.: Urban building detection from optical and InSAR features exploiting context, In: Paparoditis, N., Pierrot-Deseilligny, M., Mallet, C., Tournaire, O. (eds.), Proceedings of Photogrammetric Computer Vision and Image Analysis Conference, Paris, IAPRS, vol. 38(3A), 2010, pp. 239-244.

Ok, A.O., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., Toprak, V.: A new straight line reconstruction methodology from multi-spectral stereo aerial images, In: Paparoditis, N., Pierrot-Deseilligny, M., Mallet, C., Tournaire, O. (eds.), Proceedings of Photogrammetric Computer Vision and Image Analysis Conference, Paris, IAPRS, vol. 38(3A), 2010, pp. 25-30.

Wegner, J.D., Thiele, A., Soergel, U.: Fusion of optical and InSAR features for building recognition in urban areas, In: Stilla, U., Rottensteiner, F., Paparoditis, N. (eds.), Proceedings of City Models, Roads and Traffic Conference, Paris, IAPRS, vol. 38(3/W4), 2009, pp. 169-174.

 

Invited conference contributions

Wegner, J.D., Hänsch, R.,Thiele, A., Soergel, U.: Fusion of high-resolution InSAR data and optical imagery for building detection using Conditional Random Fields, In: Ender, J., Riegger, S., Weiß, M. (eds.), Proceedings of 8th European Conference on Synthetic Aperture Radar, Aachen, 2010, pp. 1090-1093.

Wegner, J.D., Thiele, A., Soergel, U.: Building extraction in urban scenes from high-resolution InSAR data and optical imagery, In: Qingxi, T., Gamba, P., Juergens, C., Maktav, D. (eds.), Proceedings of 5th IEEE/GRSS/ISPRS Joint Urban Remote Sensing Event, Shanghai, 2009, 6 p., CD.

 

Abstract-reviewed conference papers

Marmanis, D., Kerr, Grégoire H. G., Wegner, Jan D., Schindler, Konrad, Datcu, Mihai, Stilla, Uwe: Learning Class-Contours of Very High Spatial Resolution Aerial Images Using Convolutional Neural Networks (PDF, 6.4 MB), ODAS-2016, 16th Onera-DLR Aerospace Symposium, Oberpfaffenhofen, 2016.

 

Maros Blahá, Christoph Vogel, Audrey Richard, Jan D. Wegner, Thomas Pock, Konrad Schindler. Towards integrated 3d reconstruction and semantic interpretation of urban scenes (PDF, 10.6 MB). In Dreiländertagung, D-A-CH Photogrammetry Meeting, Bern, Switzerland, 2016.

 

Wegner, J.D., Montoya, J., Schindler, K.: Extract of road networks from aerial photos with minimum cost paths and P^N-Potts potentials, In: Proceedings of 12th Swiss Geoscience Meeting, Fribourg, 2014.

Wegner, J.D., Soergel, U.: A contextual approach to building extraction combining high-resolution InSAR and optical data, In: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Vancouver, 2011, 4 p., CD.

Ok, A.O., Wegner, J.D., Heipke, C.,Rottensteiner, F., Soergel, U., Toprak, V.:Accurate Matching and Reconstruction of Line Features from ultra high resolution Stereo Aerial Images, In: Heipke, C., Jacobsen, K., Rottensteiner, F., Müller, S., Soergel, U. (eds.), Proceedings of ISPRS Hannover Workshop, Hannover, IAPRS, vol. 38(4/W19), 2011, 6 p., CD.

Schunert, A., Michaelsen, E., Wegner, J.D., Soergel, U.: Erkennung von Gebäudestrukturen anhand von Mustern punktförmiger Reflektoren in SAR-Bildern, In: Busch, W., Niemeier, W., Soergel, U. (eds.), Proceedings of Geomonitoring, Clausthal, 2011, pp. 91-100.

Balz, T., Wegner, J.D., Schunert, A., Liu, K., Soergel, U., Liao, M.: Persistent Scatterer localization and prediction technique, In: Proceedings of International Workshop Spatial Information Technologies for Monitoring the Deformation of Large-Scale Man-made Linear Features, Hongkong, 2010, 7 p., CD.

Ok, A.O., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., Toprak, V.: A Stereo Line Matching Technique For Aerial Images Based On A Pair-Wise Relation Approach, In: ISPRS Istanbul Workshop, Istanbul, IAPRS, vol. 38(1/W17), 2010, 7 p., CD.

Schunert, A., Balz, T., Liu, K., Liao, M., Soergel, U., Wegner, J.D.: Simulation Assisted High-Resolution PSI Analysis, In: ISPRS Technical Commission 7 Symposium, Vienna, IAPRS, vol. 38(7B), 2010, pp. 498-503.

Wegner, J.D., Nezam, S., Müller, S., Soergel, U.: Comparison of land cover classification using high-resolution TerraSAR-X and optical imagery, In: Ender, J., Riegger, S., Weiß, M. (eds.), Proceedings of 8th European Conference on Synthetic Aperture Radar, Aachen, 2010, pp. 238-241.

Wegner, J.D., Schunert, A., Soergel, U.: Recognition of building features in high-resolution SAR and optical imagery, In: Reiterer, A., Egly, U., Heinert, M., Riedel, B. (eds.), Proceedings of 2nd International Workshop Application of Artificial Intelligence and Innovations in Engineering Geodesy, Braunschweig, 2010, pp. 42-46.

Wegner, J.D., Ziehn, J.R., Soergel, U.: Building detection and height estimation from high-resolution InSAR and optical data, In: Proceedings of IEEE International Geoscience and Remote Sensing Symposium, Honolulu, 2010, pp. 1928-1931.

Wegner, J.D., Ziehn, J.R., Soergel, U.: Building detection in urban areas from combined optical and InSAR data exploiting context, In: Proceedings of EARSeL Workshop, Gent, 2010, 8 p., CD.

Wegner, J.D., Auer, S., Soergel, U.: Analyse urbaner Gebiete mit optischen Bildern und SAR-Bildern sehr hoher Auflösung, In: Proceedings of DGPF Jahrestagung, Jena, vol. 18, 2009, pp. 387-398.

Wegner, J.D., Auer, S., Thiele, A., Soergel, U.: Analysis of urban areas combining high-resolution optical and SAR imagery, In: Proceedings of 29th EARSeL Symposium, Chania, 2009, 8 p., CD.

Wegner, J.D., Inglada, J., Tison, C.: Automatic Fusion of SAR and Optical Imagery based on Line Features, In: Riegger, S., Moreira, A., Heer, C. (eds.), Proceedings of 7th European Conference on Synthetic Aperture Radar, Friedrichshafen, 2008, pp. 171-174.

Wegner, J.D., Soergel, U.: Registration of SAR and optical images containing bridges over land, In: Proceedings of EARSeL Workshop, Bochum, 2008, 8 p., CD.

Wegner, J.D., Soergel, U.: Bridge height estimation from combined high-resolution optical and SAR imagery, In: Proceedings of ISPRS Symposium, Beijing, IAPRS, vol. 37(B7/3), 2008, pp. 1071-1076.

 

Reviewer for Journals

  • ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (IJPRS)
  • IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (TGRS)
  • IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (GRSL)
  • IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (JSTARS)
  • PHOTOGRAMMETRIC ENGINEERING AND REMOTE SENSING (PE&RS)
  • INTERNATIONAL JOURNAL OF REMOTE SENSING (IJRS)

Course Catalogue

Autumn Semester 2017

Number Unit
103-0254-AAL Photogrammetry 
103-0274-AAL Image Processing 
 
 
Page URL: http://www.prs.igp.ethz.ch/group/people/person-detail.html
27.05.2017
© 2017 Eidgenössische Technische Hochschule Zürich