Pregled bibliografske jedinice broj: 1173345
Classification Efficiency of Pre-Trained Deep CNN Models on Camera Trap Images
Classification Efficiency of Pre-Trained Deep CNN Models on Camera Trap Images // MDPI Journal of Imaging, 8 (2022), 2; jimaging-1418653, 26 doi:10.3390/jimaging8020020 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 1173345 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Classification Efficiency of Pre-Trained Deep CNN
Models on Camera Trap Images
Autori
Stančić, Adam ; Vyroubal, Vedran ; Slijepčević, Vedran
Izvornik
MDPI Journal of Imaging (2313-433X) 8
(2022), 2;
Jimaging-1418653, 26
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
classification ; CNN ; efficiency ; pre-trained ; camera trap
Sažetak
This paper presents the evaluation of 36 convolutional neural network (CNN) models, which were trained on the same dataset (ImageNet). The aim of this research was to evaluate the performance of pre-trained models on the binary classification of images in a “real-world” application. The classification of wildlife images was the use case, in particular, those of the Eurasian lynx (lat. “Lynx lynx”), which were collected by camera traps in various locations in Croatia. The collected images varied greatly in terms of image quality, while the dataset itself was highly imbalanced in terms of the percentage of images that depicted lynxes.
Izvorni jezik
Engleski
Znanstvena područja
Računarstvo, Interdisciplinarne tehničke znanosti
POVEZANOST RADA
Ustanove:
Veleučilište u Karlovcu
Citiraj ovu publikaciju:
Časopis indeksira:
- Web of Science Core Collection (WoSCC)
- Emerging Sources Citation Index (ESCI)
- Scopus
