EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Recognition of European mammals and birds in camera trap images using deep neural networks

Daniel Schneider, Kim Lindner, Markus Vogelbacher, Hicham Bellafkir, Nina Farwig, Bernd Freisleben

IET Computer Vision · 2024-12 · 18 (8) · 1162-1192

DOI: 10.1049/cvi2.12294 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Computer Vision, online erschienen am 03.07.2024. Verfasst von Daniel Schneider und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Hessisches Ministerium für Wissenschaft und Kunst.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Most machine learning methods for animal recognition in camera trap images are limited to mammal identification and group birds into a single class. Machine learning methods for visually discriminating birds, in turn, cannot discriminate between mammals and are not designed for camera trap images. The authors present deep neural network models to recognise both mammals and bird species in camera trap images. They train neural network models for species classification as well as for predicting the animal taxonomy, that is, genus, family, order, group, and class names. Different neural network architectures, including ResNet, EfficientNetV2, Vision Transformer, Swin Transformer, and ConvNeXt, are compared for these tasks. Furthermore, the authors investigate approaches to overcome various challenges associated with camera trap image analysis. The authors’ best species classification models achieve a mean average precision (mAP) of 97.91% on a validation data set and mAPs of 90.39% and 82.77% on test data sets recorded in forests in Germany and Poland, respectively. Their best taxonomic classification models reach a validation mAP of 97.18% and mAPs of 94.23% and 79.92% on the two test data sets, respectively.

Förderung

  • Deutsche Forschungsgemeinschaft
  • Hessisches Ministerium für Wissenschaft und Kunst

Zitieren

APA

Schneider, D., Lindner, K., Vogelbacher, M., Bellafkir, H., Farwig, N., & Freisleben, B. (2024). Recognition of European mammals and birds in camera trap images using deep neural networks. IET Computer Vision, 18(8), 1162-1192. https://doi.org/10.1049/cvi2.12294

Vancouver

Schneider D, Lindner K, Vogelbacher M, Bellafkir H, Farwig N, Freisleben B. Recognition of European mammals and birds in camera trap images using deep neural networks. IET Computer Vision. 2024;18(8):1162-1192. doi:10.1049/cvi2.12294

BibTeX
@article{Schneider2024,
  author = {Schneider, Daniel and Lindner, Kim and Vogelbacher, Markus and Bellafkir, Hicham and Farwig, Nina and Freisleben, Bernd},
  title = {Recognition of European mammals and birds in camera trap images using deep neural networks},
  journal = {IET Computer Vision},
  year = {2024},
  volume = {18},
  number = {8},
  pages = {1162--1192},
  doi = {10.1049/cvi2.12294}
}
Kostenlos starten →