Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization

Rongkun Zhu, Kangning Cui, Wei Tang, Rui-Feng Wang, Sarra Alqahtani, David Lutz, Fan Yang, Paul Fine, Jordan Karubian, Robert Plemmons, Jean-Michel Morel, Victor Pauca, Miles Silman

Abstract

Accurate mapping of individual trees is essential for ecological monitoring and forest management. Orthomosaic imagery from unmanned aerial vehicles (UAVs) is widely used, but stitching artifacts and heavy preprocessing limit its suitability for field deployment. This study explores the use of raw UAV imagery for palm detection and crown-center localization in tropical forests. Two research questions are addressed: (1) how detection performance varies across orthomosaic and raw imagery, including within-domain and cross-domain transfer, and (2) to what extent crown-center annotations improve localization accuracy beyond bounding-box centroids. Using state-of-the-art detectors and keypoint models, we show that raw imagery yields superior performance in deployment-relevant scenarios, while orthomosaics retain value for robust cross-domain generalization. Incorporating crown-center annotations in training further improves localization and provides precise tree positions for downstream ecological analyses. These findings offer practical guidance for UAV-based biodiversity and conservation monitoring.

From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization

Abstract

Accurate mapping of individual trees is essential for ecological monitoring and forest management. Orthomosaic imagery from unmanned aerial vehicles (UAVs) is widely used, but stitching artifacts and heavy preprocessing limit its suitability for field deployment. This study explores the use of raw UAV imagery for palm detection and crown-center localization in tropical forests. Two research questions are addressed: (1) how detection performance varies across orthomosaic and raw imagery, including within-domain and cross-domain transfer, and (2) to what extent crown-center annotations improve localization accuracy beyond bounding-box centroids. Using state-of-the-art detectors and keypoint models, we show that raw imagery yields superior performance in deployment-relevant scenarios, while orthomosaics retain value for robust cross-domain generalization. Incorporating crown-center annotations in training further improves localization and provides precise tree positions for downstream ecological analyses. These findings offer practical guidance for UAV-based biodiversity and conservation monitoring.

Paper Structure

This paper contains 12 sections, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Palm Detection and Localization
  4. Keypoint Detection
  5. Data and Method
  6. Study Site and Data Collection
  7. Datasets and Annotation Protocol
  8. Research Questions and Method
  9. Experiments
  10. Experiment Settings and Metrics
  11. Result Analysis
  12. Conclusion and Future Work

Figures (2)

  • Figure 1: Study site and UAV survey at FCAT. Left: location in Ecuador. Top-right: survey block for raw image annotations. Bottom-right: trigger map of image captures at 90 m altitude.
  • Figure 2: Comparison of crown-center predictions across YOLO pose models. Each panel shows ground-truth centers (blue dots), predicted crown centers (red triangles), and predicted bounding box centroids (yellow triangles).