Manual Labelling Artificially Inflates Deep Learning-Based Segmentation Performance on RGB Images of Closed Canopy: Validation Using TLS

• URL: http://arxiv.org/abs/2503.14273v2
• Date: Wed, 19 Mar 2025 16:17:19 GMT
• Title: Manual Labelling Artificially Inflates Deep Learning-Based Segmentation Performance on RGB Images of Closed Canopy: Validation Using TLS
• Authors: Matthew J. Allen, Harry J. F. Owen, Stuart W. D. Grieve, Emily R. Lines,
• Abstract summary: Traditional methods relying on field-based forest inventories are labor-intensive and limited in spatial coverage.<n>We generate high-fidelity validation labels from co-located Terrestrial Laser Scanning (TLS) data for drone imagery of boreal and Mediterranean forests.<n>We evaluate the performance of two widely used deep learning ITC segmentation models - DeepForest (RetinaNet) and Detectree2 (Mask R-CNN)<n>Both models showed very poor localisation accuracy at stricter IoU thresholds, even when restricted to canopy trees.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monitoring forest dynamics at an individual tree scale is essential for accurately assessing ecosystem responses to climate change, yet traditional methods relying on field-based forest inventories are labor-intensive and limited in spatial coverage. Advances in remote sensing using drone-acquired RGB imagery combined with deep learning models have promised precise individual tree crown (ITC) segmentation; however, existing methods are frequently validated against human-annotated images, lacking rigorous independent ground truth. In this study, we generate high-fidelity validation labels from co-located Terrestrial Laser Scanning (TLS) data for drone imagery of mixed unmanaged boreal and Mediterranean forests. We evaluate the performance of two widely used deep learning ITC segmentation models - DeepForest (RetinaNet) and Detectree2 (Mask R-CNN) - on these data, and compare to performance on further Mediterranean forest data labelled manually. When validated against TLS-derived ground truth from Mediterranean forests, model performance decreased significantly compared to assessment based on hand-labelled from an ecologically similar site (AP50: 0.094 vs. 0.670). Restricting evaluation to only canopy trees shrank this gap considerably (Canopy AP50: 0.365), although performance was still far lower than on similar hand-labelled data. Models also performed poorly on boreal forest data (AP50: 0.142), although again increasing when evaluated on canopy trees only (Canopy AP50: 0.308). Both models showed very poor localisation accuracy at stricter IoU thresholds, even when restricted to canopy trees (Max AP75: 0.051). Similar results have been observed in studies using aerial LiDAR data, suggesting fundamental limitations in aerial-based segmentation approaches in closed canopy forests.

Related papers

• Dual-Task Learning for Dead Tree Detection and Segmentation with Hybrid Self-Attention U-Nets in Aerial Imagery [1.693687279684153]
  This study introduces a hybrid postprocessing framework that refines deep learning-based tree segmentation. Tested on high-resolution aerial imagery from boreal forests, the framework improved instance-level segmentation accuracy by 41.5%. The framework's computational efficiency supports scalable applications, such as wall-to-wall tree mortality mapping.
  arXiv  Detail & Related papers  (2025-03-27T12:25:20Z)
• Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point clouds [1.6633665061166945]
  This study proposes a fully unsupervised deep learning method for leaf-wood separation of high-density laser scanning point clouds.<n>GrowSP-ForMS achieved a mean accuracy of 84.3% and a mean intersection over union (mIoU) of 69.6% on our MS test set.
  arXiv  Detail & Related papers  (2025-02-10T07:58:49Z)
• NeRF-Accelerated Ecological Monitoring in Mixed-Evergreen Redwood Forest [0.0]
  We present a comparison of MLS and NeRF forest reconstructions for the purpose of trunk diameter estimation in a mixed-evergreen Redwood forest. We propose an improved DBH-estimation method using convex-hull modeling.
  arXiv  Detail & Related papers  (2024-10-09T20:32:15Z)
• A Deep Learning Approach to Estimate Canopy Height and Uncertainty by Integrating Seasonal Optical, SAR and Limited GEDI LiDAR Data over Northern Forests [0.0]
  This study introduces a methodology for generating spatially continuous, high-resolution canopy height and uncertainty estimates. We integrate multi-source, multi-seasonal satellite data from Sentinel-1, Landsat, and ALOS-PALSAR-2 with spaceborne GEDI LiDAR as reference data. Using seasonal data instead of summer-only data improved variability by 10%, reduced error by 0.45 m, and decreased bias by 1 m.
  arXiv  Detail & Related papers  (2024-10-08T20:27:11Z)
• Comparing remote sensing-based forest biomass mapping approaches using new forest inventory plots in contrasting forests in northeastern and southwestern China [6.90293949599626]
  Large-scale high spatial resolution aboveground biomass (AGB) maps play a crucial role in determining forest carbon stocks and how they are changing. GEDI is a sampling instrument, collecting dispersed footprints, and its data must be combined with that from other continuous cover satellites to create high-resolution maps. We developed local models to estimate forest AGB from GEDI L2A data, as the models used to create GEDI L4 AGB data incorporated minimal field data from China.
  arXiv  Detail & Related papers  (2024-05-24T11:10:58Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Exploring the Effectiveness of Dataset Synthesis: An application of Apple Detection in Orchards [68.95806641664713]
  We explore the usability of Stable Diffusion 2.1-base for generating synthetic datasets of apple trees for object detection. We train a YOLOv5m object detection model to predict apples in a real-world apple detection dataset. Results demonstrate that the model trained on generated data is slightly underperforming compared to a baseline model trained on real-world images.
  arXiv  Detail & Related papers  (2023-06-20T09:46:01Z)
• Vision Transformers, a new approach for high-resolution and large-scale mapping of canopy heights [50.52704854147297]
  We present a new vision transformer (ViT) model optimized with a classification (discrete) and a continuous loss function. This model achieves better accuracy than previously used convolutional based approaches (ConvNets) optimized with only a continuous loss function.
  arXiv  Detail & Related papers  (2023-04-22T22:39:03Z)
• Classification of Single Tree Decay Stages from Combined Airborne LiDAR Data and CIR Imagery [1.4589991363650008]
  This study, for the first time, automatically categorizing individual trees (Norway spruce) into five decay stages. Three different Machine Learning methods - 3D point cloud-based deep learning (KPConv), Convolutional Neural Network (CNN), and Random Forest (RF) All models achieved promising results, reaching overall accuracy (OA) of up to 88.8%, 88.4% and 85.9% for KPConv, CNN and RF, respectively.
  arXiv  Detail & Related papers  (2023-01-04T22:20:16Z)
• Neuroevolution-based Classifiers for Deforestation Detection in Tropical Forests [62.997667081978825]
  Millions of hectares of tropical forests are lost every year due to deforestation or degradation. Monitoring and deforestation detection programs are in use, in addition to public policies for the prevention and punishment of criminals. This paper proposes the use of pattern classifiers based on neuroevolution technique (NEAT) in tropical forest deforestation detection tasks.
  arXiv  Detail & Related papers  (2022-08-23T16:04:12Z)
• Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations [58.442103936918805]
  We show that Attention Mask Consistency produces superior visual grounding results than previous methods. AMC is effective, easy to implement, and is general as it can be adopted by any vision-language model.
  arXiv  Detail & Related papers  (2022-06-30T17:55:12Z)
• Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Bayesian Deep Learning [74.94436509364554]
  We propose a Bayesian deep learning approach to densely estimate forest structure variables at country-scale with 10-meter resolution. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic aperture radar images into maps of five different forest structure variables. We train and test our model on reference data from 41 airborne laser scanning missions across Norway.
  arXiv  Detail & Related papers  (2021-11-25T16:21:28Z)
• Potato Crop Stress Identification in Aerial Images using Deep Learning-based Object Detection [60.83360138070649]
  The paper presents an approach for analyzing aerial images of a potato crop using deep neural networks. The main objective is to demonstrate automated spatial recognition of a healthy versus stressed crop at a plant level. Experimental validation demonstrated the ability for distinguishing healthy and stressed plants in field images, achieving an average Dice coefficient of 0.74.
  arXiv  Detail & Related papers  (2021-06-14T21:57:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.