The tutorial will review the basics of 3D imaging and dense image matching, with theoretical and practical sessions.
- Introduction to 3D recording techniques and pipelines: sensors, platforms & techniques
- Photogrammetric pipeline: image collection, image orientation, 3D reconstruction, orthophoto creation
- Dense Image Matching: history, methods, algorithms
- Evaluation of matching methods & accuracy analysis
- Examples, demos, exercises
- Conclusions / Summary
Exercises / Lab:
Two software packages (one commercial, one open source) will be employed for the dense matching tests: SURE (nFrames) and MicMac (IGN France).
Various datasets will be distributed with known interior / exterior orientation parameters. Test will be run changing the input parameters and evaluating the obtained results.
During the lab, the participants would need a middle-high performance laptop where running the exercises.
Tutor: Fabio Remondino – FBK Trento, Italy (http://3dom.fbk.eu).
Fabio Remondino received his PhD in Photogrammetry in 2006 from ETH Zurich, Switzerland and now leads the 3D Optical Metrology Unit (http://3dom.fbk.eu) of the Bruno Kessler Foundation (http://www.fbk.eu), a public research center in Trento, Italy. His research interests include heritage documentation, 3D modeling, sensor and data integration, geospatial data collection and processing. He is the author of over 150 scientific publications in journals and international conferences, he has written five books and edited eight Special Issues in journals. He has received 10 awards for best papers at conferences and organized 26 scientific events and 29 summer schools and tutorials. He is currently acting as President of ISPRS Technical Commission II “Photogrammetry”, President of EuroSDR Commission I “Data Acquisition”, and Vice-President of CIPA Heritage Documentation.
Tutorial requirements: Basic of photogrammetry, image processing, 3D reconstruction, computer vision.
Expected audience: researchers and practitioners in heritage 3D documentation and modelling with lack of knowledge on automated procedures and interest in understanding processing methods and bottlenecks.
- Remondino, F., Spera, M.G., Nocerino, E., Menna, F., Nex, F., 2014. State of the art in high density image matching. The Photogrammetric Record, Vol. 29(146), pp. 144-166
- Haala, N., 2013. The landscape of dense image matching algorithms. Photogrammetric Week ‘13 (Ed. D. Fritsch). Wichmann, Berlin/Offenbach, Germany. 271–284
- Rothermel, M., Wenzel, K., Fritsch, D. and Haala, N., 2012. SURE: photogrammetric surface reconstruction from imagery. LC3D Workshop, Berlin, Germany
- Haala, N. and Rothermel, M., 2012. Dense multi-stereo matching for high quality digital elevation models. Photogrammetrie, Fernerkundung. Geoinformation (PFG), Vol.4, pp. 331–343
- Hirschmueuller, H., 2008. Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 30(2), pp. 328–342