Efficient Endangered Deer Species Monitoring with UAV Aerial Imagery and Deep Learning
🤖 AI Summary
Traditional ground-based monitoring of endangered South American deer—specifically the marsh deer (Blastocerus dichotomus) and pampas deer (Ozotoceros bezoarticus)—is costly, labor-intensive, and inefficient. Method: We propose the first UAV-based AI monitoring framework tailored to these endemic cervids, featuring a habitat-adaptive YOLOv8 detection model trained on multi-temporal, high-resolution RGB imagery captured from low-altitude UAVs. The model integrates ecological constraints as prior knowledge and employs occlusion-aware data augmentation. Cross-habitat validation was conducted across the Pampas grasslands and Paraná River Delta. Results: The system achieves 89.3% mAP for marsh deer detection—enabling automated, sub-minute per km² population counts—and 72.1% mAP for pampas deer, demonstrating preliminary generalizability. It significantly improves robustness for small-object detection and occluded targets in dense vegetation, offering a scalable, field-deployable intelligent monitoring solution for endangered South American ungulates.
Application Category
📝 Abstract
This paper examines the use of Unmanned Aerial Vehicles (UAVs) and deep learning for detecting endangered deer species in their natural habitats. As traditional identification processes require trained manual labor that can be costly in resources and time, there is a need for more efficient solutions. Leveraging high-resolution aerial imagery, advanced computer vision techniques are applied to automate the identification process of deer across two distinct projects in Buenos Aires, Argentina. The first project, Pantano Project, involves the marsh deer in the Paraná Delta, while the second, WiMoBo, focuses on the Pampas deer in Campos del Tuyú National Park. A tailored algorithm was developed using the YOLO framework, trained on extensive datasets compiled from UAV-captured images. The findings demonstrate that the algorithm effectively identifies marsh deer with a high degree of accuracy and provides initial insights into its applicability to Pampas deer, albeit with noted limitations. This study not only supports ongoing conservation efforts but also highlights the potential of integrating AI with UAV technology to enhance wildlife monitoring and management practices.
Problem
Research questions and friction points this paper is trying to address.
Automating endangered deer detection using UAVs and deep learning
Reducing costly manual labor in wildlife monitoring processes
Improving accuracy in identifying marsh and Pampas deer species
Innovation
Methods, ideas, or system contributions that make the work stand out.
UAV aerial imagery for deer monitoring
Deep learning with YOLO framework
High-resolution automated identification process
🔎 Similar Papers
No similar papers found.
