Benchmarking Individual Tree Mapping with Sub-meter Imagery

TL;DR

This paper introduces a standardized evaluation framework for individual tree mapping using sub-meter imagery, comparing various deep learning approaches and proposing a new effective method for dense canopy environments.

Contribution

It provides a comprehensive evaluation protocol and compares multiple architectures, introducing a new method that balances segmentation and detection for tree mapping.

Findings

The new method outperforms existing approaches in dense canopy scenarios.

Object detection approaches struggle with small, dense trees.

The evaluation framework facilitates standardized comparison across methods.

Abstract

There is a rising interest in mapping trees using satellite or aerial imagery, but there is no standardized evaluation protocol for comparing and enhancing methods. In dense canopy areas, the high variability of tree sizes and their spatial proximity makes it arduous to define the quality of the predictions. Concurrently, object-centric approaches such as bounding box detection usuallyperform poorly on small and dense objects. It thus remains unclear what is the ideal framework for individual tree mapping, in regards to detection and segmentation approaches, convolutional neural networks and transformers. In this paper, we introduce an evaluation framework suited for individual tree mapping in any physical environment, with annotation costs and applicative goals in mind. We review and compare different approaches and deep architectures, and introduce a new method that we experimentally prove to be a good compromise between segmentation and detection.