Deep tracks: Using deep learning and procedurally simulated data for automated vertebrate footprints classification

The study of vertebrate footprints provides useful information on animal behavior, locomotion, and ecology. However, automatically classifying these records using photographs is difficult due to the significant morphological variation in footprints and the lack of readily available labeled datasets....

Celý popis

Podrobná bibliografie

Hlavní autoři:	Carolina S. Marques, Afonso Mota, Matteo Belvedere, Diego Castanera, Ignacio Díaz-Martínez, Elisabete Malafaia, Soraia Pereira, Luís Miguel Rosalino, Vanda F. Santos, Lara Sciscio, Emmanuel Dufourq
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Elsevier 2026-02-01
Edice:	Ecological Informatics
Témata:	Simulated data Vertebrate footprints Transfer learning Deep learning Automatic classification
On-line přístup:	http://www.sciencedirect.com/science/article/pii/S1574954125005321
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!