Benchmarking airborne laser scanning tree segmentation algorithms in broadleaf forests shows high accuracy only for canopy trees

Abstract

Individual tree segmentation from airborne laser scanning data is a longstanding and important challenge in forest remote sensing. Tree segmentation algorithms are widely available, but robust intercomparison studies are rare due to the difficulty of obtaining reliable reference data. Here we provide a benchmark data set for temperate and tropical broadleaf forests generated from labelled terrestrial laser scanning data. We compared the performance of four widely used tree segmentation algorithms against this benchmark data set. All algorithms performed reasonably well on the canopy trees. The point cloud-based algorithm AMS3D (Adaptive Mean Shift 3D) had the highest overall accuracy, closely followed by the 2D raster based region growing algorithm Dalponte2016+. However, all algorithms failed to accurately segment the understory trees. This result was consistent across both forest types. This study emphasises the need to assess tree segmentation algorithms directly using benchmark data, rather than comparing with forest indices such as biomass or the number and size distribution of trees. We provide the first openly available benchmark data set for tropical forests and we hope future studies will extend this work to other regions.