From Orthomosaics to Raw UAV Imagery: Enhancing Palm Detection and Crown-Center Localization
This work addresses the challenge of field deployment for UAV-based forest management, offering incremental improvements in detection and localization methods for tropical forest monitoring.
This study tackled the problem of accurate tree mapping for ecological monitoring by comparing orthomosaic and raw UAV imagery for palm detection and crown-center localization, finding that raw imagery yields superior performance in deployment scenarios while orthomosaics offer better cross-domain generalization, with crown-center annotations further improving localization accuracy.
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.