Automation in image orientation and dense point cloud reconstruction is reaching very high standards, but image quality is a fundamental pre-requisite to produce successful and photo-realistic 3D products. We investigate a productive pre-processing strategy, the various detector/descriptor operators for tie point extraction and dense matching algorithms to find out all open issues in the actual photogrammetric pipeline for 3D reconstruction purposes.
You are here
Go to the closed projects pages.
The project aims to improve the governance of energy efficiency (EE) in existing public buildings and reduce energy consumption in different central European areas, especially those less advanced in low carbon approach. For this purpose a OnePlace platform, embedding a 3D energy management system, will be developed and tested in the various pilot areas of the project.
Various countries are digitizing their archives of aerial images as they are a unique and relatively unexplored means to analyze the territorial changes over the past 100 years with very high spatial resolution. In this activity we want to investigate the geo-processing of historical aerial images, including automatic geo-referencing, DSM generation, automatic detection of bomb craters and LULC maps generation.
We applied precise and reliable measurements - based on photogrammetry or active sensing - to manufacturing, quality control, inspection and product development.
The airborne market for area-wide 3D data acquisition is experiencing a noticeable trend towards a hybrid mapping concept. Indeed many airborne data collections are increasingly be performed by a combination of active and passive sensors. We investigate the latest developments in the field of airborne hybrid systems, including both data acquisition and processing.
The activity analyzes the potential of multispectral imaging for various applications fields. Particularly, terrestrial and UAV acquisitions are acquired and processed in the heritage and agricultural field to derive "invisible" information useful for better investigations, restoration, precision farming, etc.
The project aims to investigate the potentialities of oblique aerial camera systems for building 3D reconstruction, cadaster applications, structural damage classification, land administration services, etc.
Classification and segmentation of 3D data is nowadays a very active research field. Methods try to provide enriched 3D information useful in many fields and applications. We are developing methodologies useful in various fields (city modeling, heritage, autonomous driving, etc.), exploiting modern machine learning methods.
If the field of photogrammetry has witnessed incremental technological developments in the last years, the field of airborne laser scanning is now seeing a potentially revolutionary change through the introduction of Single Photon LiDAR (SPL) and Geiger-Mode LiDAR technologies. SPL / Geiger-Mode arguably provide a more efficient approach to perform high-resolution 3D mapping. They offer higher efficiency with respect to traditional linear LiDAR and additional 3D mapping capability in terms of swath width, spatial resolution, acquisition time and density of range returns.
VirtualArch will contribute to a sustainable use and protection of non-visible and little known archaeological heritage underground or submerged by increasing the capacities of public heritage actors to protect, valorize and communicate such sites. The project will rely on innovative visualization approaches and methods such as 3D models and Virtual Reality (VR) tools.
The project aims to improve automated 3D reconstruction methods via vision metrology solutions. We want to demonstrate a step towards narrowing the gap between traditional Vision Metrology (VM) approaches and fully automated 3D reconstruction methods.
VOLTA – innoVation in geOspatiaL and 3D daTA - is an EU Marie Skłodowska-Curie RISE which will develop, thought secondments, training and networking activities, innovative solutions in the field of photogrammetry, data / sensor fusion, semantic segmentation and cloud computing for geospatial data. VOLTA has 13 partners and will run for 4 years.