| Author | Zhang, Haoran |
| Call Number | AIT Thesis no.RS-11-04 |
| Subject(s) | Brown rice--Remote sensing
|
| Note | A thesis submitted in partial fulfillment of the requirements fo r the degree of Master of Science in Remote Sensing and Geographic lnfonnation Systems, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Series Statement | Thesis ; no. RS-11-04 |
| Abstract | It is well known that rice is an impmtant world crop, particularly in Asia. The
population of Asia accounts for approximately 60% of the global population, about 92%
of the world's rice production, and 90% of global rice consumption. With such a large
population and high levels of rice consumption, an effective rice crop monitoring tool is
needed.
Currently monitoring on rice disease is becoming important through Remote Sensing
technology especially in Thailand. Due to the structure and composition of various
substances in rice area, reflection characteristics of the spectrum presented in various
forms (mixture). Large mistaken on pixel-based classification and interpretation has
been still occurred. Then, specific classification approach, object based image analysis
(OBIA), is going to be developed in order to achieve higher accuracy with confidential
level.
By experiment, the result of pixel based classification reported in accuracy of 73.3%
and 86.67% for unsupervised and supervised classification. However, when OBIA
classification was applied, it was found that the percentage of accuracy increased to
93.33% for unsupervised classification. There were based on texture, shape, and context
consideration. This is very useful to identify disease of crops. This study demonstrates
that the object-based classifier is a significantly better approach than the classical perpixel
classifiers.
However, the spatial resolution of this study was in middle level, Landsat. Regarding
this coarse resolution, it caused some error after OBIA was applied. This could be a
major concern when the middle level of resolution is manipulated. By result, very high
spatial resolution is suggested to be implemented through OBIA concept. |
| Keyword | RS; GIS; OBIA; PBIA; NOVI; image; agriculture; rice; brown spot;
classification; accuracy assessment; Thailand; Pathumtbani |
| Year | 2011 |
| Corresponding Series Added Entry | Asian Institute of Technology. Thesis ; no. RS-11-04 |
| Type | Thesis |
| School | School of Engineering and Technology |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Remote Sensing and Geographic Information Systems (RS) |
| Chairperson(s) | Tripathi, Nitin Kumar; |
| Examination Committee(s) | Taravudh Tipdecho; Soni, Peeyush ; |
| Scholarship Donor(s) | AIT Fellowship; |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 2011 |