SelvaBox: A high-resolution dataset for tropical tree crown detection

TL;DR

SelvaBox is the largest open-access high-resolution dataset for tropical tree crown detection, enabling improved model training and zero-shot generalization across diverse tropical forest imagery.

Contribution

Introduces SelvaBox, the largest annotated dataset for tropical tree crowns, and demonstrates its effectiveness in training models with superior accuracy and generalization.

Findings

Higher-resolution inputs improve detection accuracy.

Models trained on SelvaBox perform well on unseen datasets.

Multi-resolution training yields top-ranked detection performance.

Abstract

Detecting individual tree crowns in tropical forests is essential to study these complex and crucial ecosystems impacted by human interventions and climate change. However, tropical crowns vary widely in size, structure, and pattern and are largely overlapping and intertwined, requiring advanced remote sensing methods applied to high-resolution imagery. Despite growing interest in tropical tree crown detection, annotated datasets remain scarce, hindering robust model development. We introduce SelvaBox, the largest open-access dataset for tropical tree crown detection in high-resolution drone imagery. It spans three countries and contains more than 83,000 manually labeled crowns - an order of magnitude larger than all previous tropical forest datasets combined. Extensive benchmarks on SelvaBox reveal two key findings: (1) higher-resolution inputs consistently boost detection accuracy; and (2) models trained exclusively on SelvaBox achieve competitive zero-shot detection performance on unseen tropical tree crown datasets, matching or exceeding competing methods. Furthermore, jointly training on SelvaBox and three other datasets at resolutions from 3 to 10 cm per pixel within a unified multi-resolution pipeline yields a detector ranking first or second across all evaluated datasets. Our dataset, code, and pre-trained weights are made public.