This is what ENEA has experienced together with Civil Protection, Sapienza University of Rome and the Red-Tech company as part of a series of exercises in the Roccaraso ski area (L'Aquila).
The missions, conceived and coordinated by Valentino Arillo of the Civil Protection of Civitavecchia, were completed thanks to the use of various drones also equipped with thermal and 360 ° cameras, making corrections and changes at the end of each session.
"For about a year our laboratory has begun to focus its experience on technologies based on drones, to extend its applications in the field of safety e security, radiological and chemical, monitoring of nuclear plants and oil platforms and three-dimensional detection of medium and large-sized works of art, ”explains Massimiliano Guarneri, ENEA researcher at the Diagnostics and Metrology Laboratory, contact person for the project with which colleague Massimiliano Ciaffi also collaborated.
The emerging activity combines more consolidated technologies developed within the laboratory with the aim of evaluating the limits and potential offered by existing technologies through training in the field in order to extend or improve them with the development of specific instrumentation and algorithms for data processing, also based on the use of Artificial Intelligence.
“At the end of the two days of training, an unexpected case arose of a woman who felt ill on the slopes and whose exact location was not known. At the request of the local authorities, a reconnaissance with a drone was carried out and in a few minutes it was possible to give the coordinates to allow the rescuers to reach the precise place ”, continues Guarneri.
Through the use of an FPV (First Person View) drone for the three-dimensional reconstruction of a snowy area on which an exercise was carried out to find missing people, data was acquired at an altitude of over 30 m and it was It is possible to detect some traces left by the snow cats passed a little earlier.
Furthermore, the adaptation of a Neural Network for the identification of people on films obtained from 360 ° cameras is being completed. The same technologies and methodologies were also used in the INCLUDING project coordinated by Luigi De Dominicis, head of the ENEA Division of Physical Technologies for Safety and Health. In this case it was a demo in the forensic field on CBRN (chemical-biological-radiological-nuclear) issues for the survey by drone and neural networks of both objects and people in the field and for the almost real-time reconstruction of the 3D scene. through the use of “Instant Neural Graphics Primitives” algorithms, recently introduced by the US company NVIDIA Corporation. Although not yet ripe for intensive use in the professional field, these algorithms have characteristics that allow images rich in optical-physical information to be clearly superior to the standards of professional programs for the reconstruction of 3D models.
Massimiliano Guarneri, ENEA Diagnostics and Metrology Laboratory, Maximilian.guarneri@enea.it
An ophthalmoplasty operation using the Apple Vision Pro commercial viewer was performed at the Catania Polyclinic…
Developing fine motor skills through coloring prepares children for more complex skills like writing. To color…
The naval sector is a true global economic power, which has navigated towards a 150 billion market...
Last Monday, the Financial Times announced a deal with OpenAI. FT licenses its world-class journalism…
