ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-2-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 59–66, 2021
https://doi.org/10.5194/isprs-annals-V-2-2021-59-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-2-2021, 59–66, 2021
https://doi.org/10.5194/isprs-annals-V-2-2021-59-2021

  17 Jun 2021

17 Jun 2021

TOWARDS MESH-BASED DEEP LEARNING FOR SEMANTIC SEGMENTATION IN PHOTOGRAMMETRY

M. Knott1,2 and R. Groenendijk1 M. Knott and R. Groenendijk
  • 1University of Amsterdam, The Netherlands
  • 2Cloudflight Germany GmbH, Germany

Keywords: Semantic Segmentation, Textured Meshes, 3D Computer Vision, Deep Learning, MeshCNN

Abstract. This research is the first to apply MeshCNN – a deep learning model that is specifically designed for 3D triangular meshes – in the photogrammetry domain. We highlight the challenges that arise when applying a mesh-based deep learning model to a photogrammetric mesh, especially w.r.t. data set properties. We provide solutions on how to prepare a remotely sensed mesh for a machine learning task. The most notable pre-processing step proposed is a novel application of the Breadth-First Search algorithm for chunking a large mesh into computable pieces. Furthermore, this work extends MeshCNN such that photometric features based on the mesh texture are considered in addition to the geometric information. Experiments show that including color information improves the predictive performance of the model by a large margin. Besides, experimental results indicate that segmentation performance could be advanced substantially with the introduction of a high-quality benchmark for semantic segmentation on meshes.