Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Roca, Agustín, Castro, Gastón, Torre, Gabriel, Colombo, Leonardo J., Mas, Ignacio, Pereira, Javier, Giribet, Juan I.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.00154
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909630255333376
author Roca, Agustín
Castro, Gastón
Torre, Gabriel
Colombo, Leonardo J.
Mas, Ignacio
Pereira, Javier
Giribet, Juan I.
author_facet Roca, Agustín
Castro, Gastón
Torre, Gabriel
Colombo, Leonardo J.
Mas, Ignacio
Pereira, Javier
Giribet, Juan I.
contents This study compares the performance of state-of-the-art neural networks including variants of the YOLOv11 and RT-DETR models for detecting marsh deer in UAV imagery, in scenarios where specimens occupy a very small portion of the image and are occluded by vegetation. We extend previous analysis adding precise segmentation masks for our datasets enabling a fine-grained training of a YOLO model with a segmentation head included. Experimental results show the effectiveness of incorporating the segmentation head achieving superior detection performance. This work contributes valuable insights for improving UAV-based wildlife monitoring and conservation strategies through scalable and accurate AI-driven detection systems.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Detection of Endangered Deer Species Using UAV Imagery: A Comparative Study Between Efficient Deep Learning Approaches
Roca, Agustín
Castro, Gastón
Torre, Gabriel
Colombo, Leonardo J.
Mas, Ignacio
Pereira, Javier
Giribet, Juan I.
Computer Vision and Pattern Recognition
Artificial Intelligence
This study compares the performance of state-of-the-art neural networks including variants of the YOLOv11 and RT-DETR models for detecting marsh deer in UAV imagery, in scenarios where specimens occupy a very small portion of the image and are occluded by vegetation. We extend previous analysis adding precise segmentation masks for our datasets enabling a fine-grained training of a YOLO model with a segmentation head included. Experimental results show the effectiveness of incorporating the segmentation head achieving superior detection performance. This work contributes valuable insights for improving UAV-based wildlife monitoring and conservation strategies through scalable and accurate AI-driven detection systems.
title Detection of Endangered Deer Species Using UAV Imagery: A Comparative Study Between Efficient Deep Learning Approaches
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.00154