Student information

Msc thesis subject: Individual tree detection and segmentation with Terrestrial Lidar point clouds of tropical forests

Point clouds of forests acquired with Terrestrial Laser Scanning (TLS) contain a wealth of information on tree structural properties. However, segmenting individual trees from the point clouds is time intense especially when complex tropical forests are investigated.

Automatic segmentation routines exist, but have mostly been developed in structurally simple temperate forests and are unlikely to perform well in tropical forests.

The goal of this project is to evaluate a new segmentation routine that has shown potential in first test cases in a tropical environment.

Objectives

  • Review literature on state-of-the-art tree segmentation algorithms
  • Co-registration (pre-processing) of TLS scan projects to form whole plot point clouds
  • Application of (different) segmentation algorithm(s)
  • Evaluation of segmenation results based on manually segmented trees

Literature

  • Raumonen, P., Casella, E., Calders, K., Murphy, S., Åkerblom, M., Kaasalainen, M., … Kaasalainen, M. (2015). MASSIVE-SCALE TREE MODELLING FROM TLS DATA. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3/W4(March), 189–196. doi:10.5194/isprsannals-II-3-W4-189-2015

Requirements

  • Scripting skills (e.g. R, Python, MatLab) are a preference
  • Basic knowledge of Cloudcompare software
  • Completion GRS-32306 Advanced Earth Observation

Theme(s): Sensing & measuring; Modelling & visualisation