Comparative Analysis of Deep Learning Models for Olive Tree Crown and Shadow Segmentation Towards Biovolume Estimation

TL;DR

This study compares deep learning models U-Net, YOLOv11m-seg, and Mask R-CNN for segmenting olive tree crowns and shadows in UAV imagery to estimate biovolume, aiding precision agriculture.

Contribution

It provides a comprehensive comparison of three deep learning models for olive tree segmentation and biovolume estimation using UAV data, highlighting their strengths and trade-offs.

Findings

Mask R-CNN achieved highest accuracy (F1=0.86, mIoU=0.72).

YOLOv11m-seg offered fastest processing speed (0.12 sec/image).

Biovolume ranged from 4 to 24 cubic meters, reflecting structural differences.

Abstract

Olive tree biovolume estimation is a key task in precision agriculture, supporting yield prediction and resource management, especially in Mediterranean regions severely impacted by climate-induced stress. This study presents a comparative analysis of three deep learning models U-Net, YOLOv11m-seg, and Mask RCNN for segmenting olive tree crowns and their shadows in ultra-high resolution UAV imagery. The UAV dataset, acquired over Vicopisano, Italy, includes manually annotated crown and shadow masks. Building on these annotations, the methodology emphasizes spatial feature extraction and robust segmentation; per-tree biovolume is then estimated by combining crown projected area with shadow-derived height using solar geometry. In testing, Mask R-CNN achieved the best overall accuracy (F1 = 0.86; mIoU = 0.72), while YOLOv11m-seg provided the fastest throughput (0.12 second per image). The estimated biovolumes spanned from approximately 4 to 24 cubic meters, reflecting clear structural differences among trees. These results indicate Mask R-CNN is preferable when biovolume accuracy is paramount, whereas YOLOv11m-seg suits large-area deployments where speed is critical; U-Net remains a lightweight, high-sensitivity option. The framework enables accurate, scalable orchard monitoring and can be further strengthened with DEM or DSM integration and field calibration for operational decision support.