Towards Automatic Animal Classification in Wildlife Environments for Native Species Monitoring in the Amazon

Producción científica: Capítulo del libro/informe/acta de congresoContribución a la conferenciarevisión exhaustiva

Resumen

Although critical for habitat and species conservation, camera trap image analysis is often manual, time-consuming, and expensive. Thus, automating this process would allow large-scale research on biodiversity hotspots of large conspicuous mammals and bird species. This paper explores the use of deep learning species-level object detection and classification models for this task, using two state-of-The-Art architectures, YOLOv5 and Faster R-CNN, for two species: white-lipped peccary and collared peccary. The dataset contains 7,733 images obtained after data augmentation from the Tiputini Biodiversity Station. The models were trained in 70% of the dataset, validated in 20%, and tested in 10% of the available data. The YOLOv5 model proved to be more robust, having lower losses and a higher overall mAP (Mean Average Precision) value than Faster-RCNN. This is one of the first steps towards developing an automated camera trap analysis tool, allowing a large-scale analysis of population and habitat trends to benefit their conservation. The results suggest that hyperparameter fine-Tuning would improve our models and allow us to extend this tool to other native species.

Idioma originalInglés
Título de la publicación alojada2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Proceedings
EditoresAlvaro David Orjuela-Canon
EditorialInstitute of Electrical and Electronics Engineers Inc.
ISBN (versión digital)9798350316599
DOI
EstadoPublicada - 2023
Evento2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023 - Bogota, Colombia
Duración: 26 jul. 202328 jul. 2023

Serie de la publicación

Nombre2023 IEEE Colombian Conference on Applications of Computational Intelligence (ColCACI)

Conferencia

Conferencia2023 IEEE Colombian Conference on Applications of Computational Intelligence, ColCACI 2023
País/TerritorioColombia
CiudadBogota
Período26/07/2328/07/23

Huella

Profundice en los temas de investigación de 'Towards Automatic Animal Classification in Wildlife Environments for Native Species Monitoring in the Amazon'. En conjunto forman una huella única.

Citar esto