CVEMP 2023
1st International Workshop on Computer Vision for Environment Monitoring and Preservation
Embedded Files
Keynote Speakers
Marco Scaioni
Marco Scaioni, Civil Engineering MSc Degree (Politecnico Milano, Italy, 1995), PhD on Geodetic and Mapping Sciences (Politecnico Milano, 1999). Full Professor of Geomatics at Politecnico Milano, Dept. of Architecture, Built Environment and Construction Engineering (ABC). Head of ABC-PhD programme. Formerly, Full Professor in the College of Surveying and Geo-Informatics at Tongji University, Shanghai (2011-2014). Main research interests: Photogrammetry and Laser scanning from multiple platforms, Integration GIS/BIM for buildings and infrastructures, Geomatics for Geosciences and Cultural Heritage, Geodatabases for urban planning, Deep Learning classification of point clouds. Associate Editor of Applied Geomatics (Springer) and the ISPRS Journal of Photogrammetry and Remote Sensing (Elsevier). He published more than 320 scientific papers, including 67 papers on WoS-indexed journals (H-index: 24), 187 Scopus-indexed papers (H-index: 33) and two edited books.
MONITORING OF ALPINE GLACIERS BASED ON MULTI-TEMPORAL STRUCTURE-FROM-MOTION AND ARCHIVE AERIAL PHOTOS
The measurement of geometric changes in Alpine glaciers is an essential aspect to assess their reaction to climate change effects. Archive aerial images may integrate valuable information to this purpose at times when other types of remotely sensed data are not available. The application of Structure-from-Motion (SfM) and Multi-View-Stereo matching allows the extraction of dense point clouds to model the glacier environment. Multitemporal SfM (MSfM) is presented and tested on a dataset including six different aerial blocks collected by means of analogue and digital airborne cameras from 1967 to 2006. These images have been downloaded from the IGNF online repository and cover the area of the Val Veny (Brenva and Miage glaciers) in the Mount Blanc massif, at the border between Italy and France. Coupled with other solutions (i.e., extraction of GCPs from maps and DTMs and ICP co-registration of point clouds), MSfM has revealed as a suitable technique for coregistration of multiple photogrammetric blocks of aerial photos with minimum ground control. Some tests carried out in the case study area demonstrated that the integration of MSfM and ICP coregistration for refinement may significantly improve the comparison between multiple point clouds, which is a fundamental pre-requisite for the analysis of glacier changes over time.
Mail at: marco.scaioni(at)polimi.it
Erica Nocerino
Erica Nocerino is currently a tenure-track assistant professor (RTDb) in Geomatics at the Department of Humanities and Social Sciences of the University of Sassari (Italy). For more than ten years, her research has focused on photogrammetry, 3D reconstruction, underwater modeling, and vision metrology. In particular, she is interested in all aspects related to quality improvement and assessment of the generated 3D to meet the specific application's requirements. She is a member of International Society for Photogrammetry and Remote Sensing, where she serves as a Secretary for the Commission II Working Group WG II/7.
Image-based techniques for underwater 3D mapping and monitoring: challenges and opportunities
Water covers the 70% of the earth’s surface, with the 50% represented by deep sea. Ocean also means biodiversity, oxygen production, heat and carbon absorption, all essential factors at such a critical time for our future and the health of our planet.
Image-based techniques, such as photogrammetry, visual odometry and visual SLAM (simultaneous localization and mapping), have become very popular in the exploration and study of the ocean depths, seabed, and species that populate it. However, the 'water' medium poses significant challenges in the application of techniques originally developed to perform best in 'air'.
This presentation will dive into the critical aspects of underwater image-based techniques, with a specific emphasis on their use as 3D surveying and mapping methods for monitoring benthic habitat. In addition to an overview of the principles of underwater image formation and the most common methods of underwater camera calibration, we will focus on approaches for accuracy assessment and quality control in a continuously mutable environment. These concepts will be illustrated in two study cases of coral reef and Antarctic benthic species monitoring, showing the great potential of image-based techniques. The presentation will conclude by drawing future research perspectives.
Mail at: enocerino(at)uniss.it
Page updated
Report abuse