mlsanityData to 14 Oct 2026

NormalView: tree species classification from backpack and aerial lidar data using geometric projections

arXiv 2512.05610 ↗First posted 5 Dec 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Laser scanning has proven to be an invaluable tool in assessing the decomposition of forest environments. Mobile laser scanning (MLS) has shown to be highly promising for extremely accurate, tree level inventory. In this study, we present NormalView, a projection-based deep learning method for classifying tree species from point cloud data. NormalView embeds local geometric information into two-dimensional projections, in the form of normal vector estimates, and uses the projections as inputs to an image classification network, YOLOv11. In addition, we inspected the effect of multispectral radiometric intensity information on classification performance. We trained and tested our model on high-density MLS data (7 species, ~5000 pts/m2), as well as high-density airborne laser scanning (ALS) data (9 species, >1000 pts/m2). On the MLS data, NormalView achieves an overall accuracy (macro-average accuracy) of 95.5 % (94.8 %), and 91.8 % (79.1 %) on the ALS data. We found that having intensity information from multiple scanners provides benefits in tree species classification, and the best model on the multispectral ALS dataset was a model using intensity information from all three channels of the multispectral ALS. This study demonstrates that projection-based methods, when enhanced with geometric information and coupled with state-of-the-art image classification backbones, can achieve exceptional results. Crucially, these methods rely only on geometric information, and thus are compatible with most sensors. Additionally, we publically release the MLS dataset used in the study, containing 1915 samples.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 90 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

18 of 90 references.

References · 18

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,223
  6. 2020Point Transformercited by 1,470
  7. 20173D Semantic Segmentation with Submanifold Sparse Convolutional Networkscited by 748
  8. 2022Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Frameworkcited by 379
  9. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  10. 2021Revisiting Point Cloud Shape Classification with a Simple and Effective Baselinecited by 145
  11. 2014DenseNet: Implementing Efficient ConvNet Descriptor Pyramidscited by 66
  12. 2023Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learningcited by 23
6 more
  1. 2024SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning datacited by 17
  2. 2023TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point cloudscited by 14
  3. 2025ForestFormer3D: A Unified Framework for End-to-End Segmentation of Forest LiDAR 3D Point Cloudscited by 13
  4. 2024Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K datasetcited by 12
  5. 2025Unsupervised deep learning for semantic segmentation of multispectral LiDAR forest point cloudscited by 7
  6. 2025Multispectral airborne laser scanning for tree species classification: a benchmark of machine learning and deep learning algorithmscited by 6

Built on by

Not cited yet.