You are here

Dense Image Matching

Project researchers

The project deals with automated image matching methods for the generation of dense and accurate 3D point clouds from aerial and terrestrial imagery. Actual image matching techniques can provide for dense and reliable point clouds, geometrically comparable to LiDAR ones in terms of accuracy and completeness. Data from new digital frame cameras (e.g. ULTRACAM, DMC, etc.), oblique multi-camera systems (VisionMap, BlomOblique, MIDAS, etc.) or high-resolution reflex cameras are processed with in-house and open-source tools for the production of very dense geometric models, exploiting the very high radiometric quality, the potentialities of GPU programming and the highly overlapping image blocks.

Representative Publications:
- 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, DOI: 10.1111/phor.12063

Duration: 
1 year (2014)
Funding: 
Internal
Research topics: