Automated approach for classifying point cloud data using DBSCAN and OPTICS algorithms in R | |
| Author | Aditya, Rambhatla Sai Satya |
| Call Number | AIT Thesis no.RS-18-15 |
| Subject(s) | Image processing--Digital techniques Optical radar Clouds--Classification |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Remote Sensing and Geographic Information System, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | LIDAR data was used for exploring horizontal and vertical canopies and at high resolutions and spatial accuracy. Terrestrial laser scanner (TLS) is a type of ground based LIDAR system, which is being recently used in the Agroforestry for analysis of basic parameters like diameter of breast size (DBH), height, and shape of stem and crown. TLS provides a fast and efficient way for classification and determination of basic properties of tree. In this study, we use DBSCAN and OPTICS algorithm for classifying the point cloud which is obtained from the TLS. Algorithm classifies the point cloud data and the second most frequent clus-ter is considered and used for forming combinations and the combinations with the highest accuracy(MCC)value is considered for finding the height and shape of stem and crown. In this study, we have considered two trees where one tree is from Italy, other tree is from Thailand, same procedure was applied to both the tree, and desired result was obtained. |
| Year | 2018 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing (RS) |
| Chairperson(s) | Virdis, Salvatore G. P. |
| Examination Committee(s) | Nakamura, Tai ;Miyazaki, Hiroyuki |
| Scholarship Donor(s) | AIT Fellowship |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2018 |