Please use this identifier to cite or link to this item:
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.
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 SizeFormat 
2022_Vidondo-etal_CameraTraps_Poster_BDSD.pdf622.15 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.