Building classification using multitemporal object-based image analysis approach : a case study of public state land in Haiya, Chiang Mai, Thailand | |
| Author | Katanchalee Taweepornwattanakul |
| Call Number | AIT Thesis no.RS-20-05 |
| Subject(s) | Remote-sensing images|--Thailand--Chiang Mai--Haiya Image analysis--Data processing Building--Classification |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Remote Sensing and Geographic Information Systems, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | This study represents the practical procedure to identify the building objects in public state land in Haiya, Chiang Mai, Thailand. The research focused on developing a procedure for extracting the building objects in the study area. This research used historical aerial photography and digital aerial photography in 1987, 1995, 2012, and 2015 with object-based image analysis to identify land use changes. This study is focused on the building class to the strategies solving a problem about land encroachment in case of invasion by building a permanent object in the public state land. The results showed two critical findings in this study. First, automatic multi- temporal orthophoto fine coregistration provided higher reliability of the orthophotos in 1987, 1995, and 2012 (RMSE errors less than 0.5 meters in a pixel). While aerotriangulation provided higher accuracy of the orthophoto in 2015 (RMSE error less than 0.2 meters in a pixel. Also, the results from the multiresolution segmentation algorithm demonstrated suitable parameters for creating the building segmentation of historical aerial photography at scale 20, shape 0.9, compactness 0.1 with accuracy 95% of 1987 and 92% of 1995. The digital aerial photographs at scale 500, shape 0.9, compactness 0.5 with spatial accuracy 87% of2012 and 82% of2015. |
| Year | 2020 |
| 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) | Sarawut Ninsawat ; Miyazaki, Hiroyuki |
| Scholarship Donor(s) | His Majesty the King's Scholarships (Thailand) |
| Degree | Thesis (M. Sc.) - Asian Institute of Technology, 2020 |