1 AIT Asian Institute of Technology

Knowledge-based identification of linear objects in remotely sensed data

AuthorChuan, Yeo Siok
Call NumberAIT Thesis no. CS-88-10
Subject(s)Remote sensing
NoteA thesis submitted in partial fulfillment. of the requirements for the degree of Master of Engineering, School of Engineering and Technology
PublisherAsian Institute of Technology
AbstractThis study provides a framework of knowledge - based system for identifying the linear objects in the low resolution, remotely sensed data. The proposed system creates a working environment based on the artificial intelligence and expert systems techniques to utilize knowledge from sources such as spatial domain, spectral response, and remote sensing environment . The system consists of three components: ( 1) a preprocessing module for detecting the linear objects and extracting useful information; . ( 2 ) a clause form converter for transforming the information into clause form; and ( 3 ) a knowledge - based module for simulating the visual identification process and providing a dialogue system for user interaction on linear objects. The categories and uncertainty of knowledge concerning the linear objects are taken into account in order to have a deeper insight for the issues. The effective ness of t he proposed system was verified by an implemented prototype. The separation between knowledge and control structure reduces the user ' s effort to construal the rules , and helps in adjusting the system for domain knowledge and therefore the system is capable of performing the identification up to the level of a conceptual linear object.
Year1988
TypeThesis
SchoolSchool of Engineering and Technology (SET)
DepartmentOther Field of Studies (No Department)
Academic Program/FoSComputer Science (CS)
Chairperson(s)Sadananda, Ramakoti
Examination Committee(s)Galtier, Bertrand ;Kanchana Kanchanasut
Scholarship Donor(s)The King ' s Scholarship of the Royal Thai Government
DegreeThesis (M.Eng.) - Asian Institute of Technology, 1988


Usage Metrics
View Detail0
Read PDF0
Download PDF0