Please use this identifier to cite or link to this item:
https://doi.org/10.21256/zhaw-24927| Publication type: | Conference poster |
| Type of review: | Peer review (abstract) |
| Title: | Animal detection and species classification on Swiss camera trap images using AI |
| Authors: | Vidondo, Beatriz Glüge, Stefan Hubert, Laurtent Fischer, Claude Le Grand, Luc |
| et. al: | No |
| DOI: | 10.21256/zhaw-24927 |
| Conference details: | Bern Data Science Day (BDSD), Bern, 6 May 2022 |
| Issue Date: | 6-May-2022 |
| Publisher / Ed. Institution: | ZHAW Zürcher Hochschule für Angewandte Wissenschaften |
| Language: | English |
| Subjects: | Object detection; Computer vision |
| Subject (DDC): | 006: Special computer methods 590: Animals (Zoology) |
| Abstract: | Motion-triggered camera traps are essential for the monitoring and management of wildlife. As per today in Switzerland, a high number of pictures is manually processed (annotated and classified). We study the utilization of available detection and classification models to (semi-)automatize this process. Two main aspects were investigated: 1) evaluate the feasibility of a non-expert local application (with Microsoft's MegaDetector model), and 2) quantify model performance using several labelled datasets of varying quality and content. Our results show a highly accurate (sensitive and specific), and reliable, fast inference which efficiently allows the automatic pre-discarding of all non-animal images. Further, the MegaDetector turns out to be both, user-friendly and highly performant and thus, an ideal tool for Swiss wildlife experts and stakeholders. Incentives (educational and financial) are required to promote knowledge transfer to this field. |
| URI: | https://digitalcollection.zhaw.ch/handle/11475/24927 |
| Fulltext version: | Published version |
| License (according to publishing contract): | Licence according to publishing contract |
| Departement: | Life Sciences and Facility Management |
| Organisational Unit: | Institute of Computational Life Sciences (ICLS) |
| Appears in collections: | Publikationen Life Sciences und Facility Management |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 2022_Vidondo-etal_CameraTraps_Poster_BDSD.pdf | 622.15 kB | Adobe PDF |  View/Open |
Show full item record
Vidondo, B., Glüge, S., Hubert, L., Fischer, C., & Le Grand, L. (2022, May 6). Animal detection and species classification on Swiss camera trap images using AI. Bern Data Science Day (BDSD), Bern, 6 May 2022. https://doi.org/10.21256/zhaw-24927
Vidondo, B. et al. (2022) ‘Animal detection and species classification on Swiss camera trap images using AI’, in Bern Data Science Day (BDSD), Bern, 6 May 2022. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. Available at: https://doi.org/10.21256/zhaw-24927.
B. Vidondo, S. Glüge, L. Hubert, C. Fischer, and L. Le Grand, “Animal detection and species classification on Swiss camera trap images using AI,” in Bern Data Science Day (BDSD), Bern, 6 May 2022, May 2022. doi: 10.21256/zhaw-24927.
VIDONDO, Beatriz, Stefan GLÜGE, Laurtent HUBERT, Claude FISCHER und Luc LE GRAND, 2022. Animal detection and species classification on Swiss camera trap images using AI. In: Bern Data Science Day (BDSD), Bern, 6 May 2022. Conference poster. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. 6 Mai 2022
Vidondo, Beatriz, Stefan Glüge, Laurtent Hubert, Claude Fischer, and Luc Le Grand. 2022. “Animal Detection and Species Classification on Swiss Camera Trap Images Using AI.” Conference poster. In Bern Data Science Day (BDSD), Bern, 6 May 2022. ZHAW Zürcher Hochschule für Angewandte Wissenschaften. https://doi.org/10.21256/zhaw-24927.
Vidondo, Beatriz, et al. “Animal Detection and Species Classification on Swiss Camera Trap Images Using AI.” Bern Data Science Day (BDSD), Bern, 6 May 2022, ZHAW Zürcher Hochschule für Angewandte Wissenschaften, 2022, https://doi.org/10.21256/zhaw-24927.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.