Real-Time Person Detection in Wooded Areas Using Thermal Images from an Aerial Perspective
Oscar Ramírez-Ayala, Iván González-Hernández, Sergio Salazar, Jonathan Flores, Rogelio Lozano, Rossitza Goleva, Radosveta Sokullu, Ciprian Dobre, Nuno M Garcia · 2023
Read Real-Time Person Detection in Wooded Areas Using Thermal Images from an Aerial Perspective by Oscar Ramírez-Ayala, Iván González-Hernández, Sergio Salazar, Jonathan Flores, Rogelio Lozano, Rossitza Goleva, Radosveta Sokullu, Ciprian Dobre, Nuno M Garcia (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10675173.txt.
Description
Oscar Ramírez-Ayala and co-authors built a thermal image data set in 2023 for spotting lost people in wooded country from a drone, where leaves hide bodies from ordinary cameras. Heat cameras see through some of that cover, but a person is tiny in the frame and often partly blocked.
Their set deliberately includes blocked and partly blocked figures, shot from a height controlled quadcopter. Deep learning models trained on it learned to pick out the warm shape of a person even when trees cut across it. The work runs in real time on the drone prototype. The authors aim the system at search and rescue teams working forests after accidents or disasters.
Catalog record
| CREATOR | Oscar Ramírez-Ayala, Iván González-Hernández, Sergio Salazar, Jonathan Flores, Rogelio Lozano, Rossitza Goleva, Radosveta Sokullu, Ciprian Dobre, Nuno M Garcia |
|---|---|
| YEAR | 2023 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 27 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |