Use this URL to cite or link to this record in EThOS:
Title: The detection and reconstruction of landscape objects using multi-sensor fusion
Author: Kim, Jung Rack
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2005
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Automatic object detection and reconstruction has been one of the main objectives of remote sensing applications. The primary goal of this research work is to develop techniques for the automated production of dense landscape object models by combining various optical imagery with 3D information. It seeks to focus object- identification ratio updating to an applicable level through multi source data fusion with a two fold application building detection and tree detection in urban areas, and impact crater detection on planetary surfaces. The system for urban-area object detection involves focusing by DTM construction, refinement of Rol by data fusion of 3D range data and multi-spectral signatures, and object identification by boundary generalisation and fitting. On the other hand, the impact crater detection system consists of three sub stages: region of interest definition by texture analysis and by edge direction analysis, optimal ellipse generation as a second processing step, and final verification and refinement by template matching. Both systems are applied to four different data sets, after which quality assessments are made by comparing the results with ground truth and show reasonable detection accuracies. In addition, several 3D range data extraction algorithms including efficient image matchers have been developed and tested in both applications.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available