Generalized data-driven method for separating wood and leaves in terrestrial lidar point clouds from diverse tree species | |
| Author | Nguyen Thai Anh |
| Call Number | AIT Thesis no.DSAI-24-03 |
| Subject(s) | Forest management--Data processing Machine learning Optical radar |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Data Science and Artificial Intelligence |
| Publisher | Asian Institute of Technology |
| Abstract | In agroforestry research, the integration of Light Detection and Ranging (LiDAR) technology has become indispensable. LiDAR’s ability to produce high-density, three dimensional point clouds facilitates the accurate measurement of forest structure. A pivotal application in forestry management is the precise estimation of forest volume and biomass. The accurate determination of timber volume, above-ground biomass, and canopy characteristics necessitates the segregation of leaves from wood. This study develops a fully automated method for separating foliage and wood based on the spatial geometric information of TLS point clouds. Utilizing full point cloud data, this method yields optimal clustering results and visualizes the outcomes. The approach achieves high overall accuracy with a voxel size set to 1 cm. This research not only provides a reliable method for estimating forest volume and biomass but also contributes to sustainable forest management and climate change mitigation strategies. |
| Year | 2024 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Data Science and Artificial Intelligence (DSAI) |
| Chairperson(s) | Virdis, Salvatore G.P.; |
| Examination Committee(s) | Chutiporn Anutariya;Chantri Polprasert; |
| Scholarship Donor(s) | AITCV, Vietnam;AIT Scholarships; |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2024 |