Accurate delineation of individual tree crowns in tropical forests from aerial RGB imagery using Mask R‐CNN

Abstract

Tropical forests are a major component of the global carbon cycle and home to two‐thirds of terrestrial species. Upper‐canopy trees store the majority of forest carbon and can be vulnerable to drought events and storms. Monitoring their growth and mortality is essential to understanding forest resilience to climate change, but in the context of forest carbon storage, large trees are underrepresented in traditional field surveys, so estimates are poorly constrained. Aerial photographs provide spectral and textural information to discriminate between tree crowns in diverse, complex tropical canopies, potentially opening the door to landscape monitoring of large trees. Here we describe a new deep convolutional neural network method, Detectree2, which builds on the Mask R‐CNN computer vision framework to recognize the irregular edges of individual tree crowns from airborne RGB imagery. We trained and evaluated this model with 3797 manually delineated tree crowns at three sites in Malaysian Borneo and one site in French Guiana. As an example application, we combined the delineations with repeat lidar surveys (taken between 3 and 6 years apart) of the four sites to estimate the growth and mortality of upper‐canopy trees. Detectree2 delineated 65 000 upper‐canopy trees across 14 km2 of aerial images. The skill of the automatic method in delineating unseen test trees was good (F1 score = 0.64) and for the tallest category of trees was excellent (F1 score = 0.74). As predicted from previous field studies, we found that growth rate declined with tree height and tall trees had higher mortality rates than intermediate‐size trees. Our approach demonstrates that deep learning methods can automatically segment trees in widely accessible RGB imagery. This tool (provided as an open‐source Python package) has many potential applications in forest ecology and conservation, from estimating carbon stocks to monitoring forest phenology and restoration.Python package available to install at https://github.com/PatBall1/Detectree2.

Towards comprehensive individual tree species mapping in diverse tropical forests by harnessing temporal and spectral dimensions

“…We used detectree2, a tool based on the Mask R-CNN deep learning architecture for automated tree crown delineation (Ball et al 2023), which has been shown to outperform another leading CNN method for tree crown detection (Gan, Wang, and Iio 2023).…”

BAMFORESTS: Bamberg Benchmark Forest Dataset of Individual Tree Crowns in Very-High-Resolution UAV Images

“…Schiefer et al [25] used the U-Net architecture to map tree species via semantic segmentation. Ball et al [13] developed Detectree2, an instance segmentation DCNN based on Facebook's Detectron2 architecture. While Schiefer et al [25] published their dataset and code, Deepforest and Detectree2 are publicly available Python packages, including pre-trained weights and pre-and post-processing steps.…”

“…Overview papers such as Kattenborn et al [11] showed that very-high-resolution UAV data with a ground sampling distance (GSD) of below 2 cm and deep neural networks (DNNs) from the computer vision domain yield good results. For example, Gan et al [12] compared the widely used Python deep learning packages Detectree2 [13] and Deepforest [14] on different very-high-resolution GSDs. Xi et al [15] tested different dimensionality reductions to overcome the drawbacks of multispectral images for ITCD approaches, which can yield better results than just RGB-imagery.…”

UAV‐derived greenness and within‐crown spatial patterning can detect ash dieback in individual trees

“…For example, the Forest Structural Complexity Tool, used here to segment TLS trees, could work more efficiently with UAV data with additional training data (Krisanski et al, 2021). The recently released Segment Anything model (SAM; Kirillov et al, 2023) and Detectree2 (Ball et al, 2023), as well as multiple neural network applications based on the PointNet architecture (e.g. Wielgosz et al, 2023;Yu et al, 2022) show promise to accurately segment trees in 2D and 3D F I G U R E 5 Linear mixed models showing the relationship between cluster path length and cluster g cc in 35 healthy (solid line) and 85 infected (dashed line) trees.…”