You are here

Semantic photogrammetry and classification of 3D data

Project researchers

The use of 3D data (point clouds, polygonal models, etc.) is nowadays widely diffused for various applications and in different fields, from the documentation of cultural heritage to autonomous driving, from urban planning to semantic 3D modeling. Nevertheless, to provide useful 3D data, it is necessary to associate some semantic information that can help operators to better understand and interpret the data. The research activity aims at carrying out an optimal, repeatable and reliable segmentation and classification procedure to manage various types of 3D survey data and associate them with heterogeneous information and attributes to characterize and describe the surveyed scene. The developed methods are based on supervised / data-driven machine learning methods and were tested on various scenarios, from small heritage objects to architectures or part of cities, providing for 3D classified (labbeled) data.

Representative publications:

- E. Grilli, E. Özdemir and F. Remondino, 2019: Application of machine and deep learning strategis for the classification of heritage point cloudsISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-4/W18, pp. 447–454

- E. Özdemir, F. Remondino, A. Golkar, 2019: Aerial point cloud classification with with deep learning and machine learning algorithmsISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-4/W18, pp. 843-849

E.K. Stathopoulou and F. Remondino, 2019: Multi-view stereo with semantic priorsISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-2/W15, 1157–1162. 27th CIPA Symposium, Avila, Spain

- E. Özdemir and F. Remondino, 2019: Classification of aerial point clouds with deep learning. ISPRS;Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol.  XLII-2/W13, pp. 103-110. ISPRS Geospatial Week 2019, Enschede (NL)

- Grilli, E., Remondino, F., 2019: Classification of 3D Digital Heritage. MDPI Remote Sensing, Vol. 11(7), 847; https://doi.org/10.3390/rs11070847

- E.-K. Stathopoulou and F. Remondino, 2019: Semantic Photogrammetry - Boosting image-based 3D reconstruction with semantic labelling. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W9, 685-690. ISPRS/CIPA Workshop 3D-ARCH 2019, Bergamo (Italy)

- Grilli, E., Dininno, M., Marsicano, L., Petrucci, G., Remondino, F., 2018: Supervised segmentation of 3D cultural heritage. IEEE Proc. of Digital Heritage 2018 3rd International Congress & Expo, San Francisco (USA), in press

- E. Ozdemir, F. Remondino, 2018: Segmentation of 3D photogrammetric point cloud for 3D building modeling. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.,, Vol. XLII-4/W10, pp. 135-142

- E. Grilli, D. Dininno, G. Petrucci, F. Remondino, 2018: From 2D to 3D supervised segmentation and classification for cultural heritage applications. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-2, pp. 399-406

- Grilli, E., Menna, F., Remondino, F., 2017: A review of point clouds segmentation and classification algorithms. ISPRS Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., Vol. XLII-2-W3, pp. 339-344

Videos:

https://youtu.be/8-muH633ud8

https://youtu.be/ZmjUh3xn6eA

https://youtu.be/0EfDTrpoXZg

Research topics: