Detection of Endangered Deer Species Using UAV Imagery: A Comparative Study Between Efficient Deep Learning Approaches

Personal use of this material is permitted. Abstract -- 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 UA V 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 UA V-based wildlife monitoring and conservation strategies through scalable and accurate AI-driven detection systems. Monitoring wildlife is crucial for understanding and preserving ecosystems. Traditional observation methods, however, are often labor-intensive, costly, and constrained in coverage [1], [2].