Feature Extraction from Multi-modal Mobile Mapping Data
MetadataShow full item record
This thesis investigates many different feature extraction methods and machine learning algorithms for their usefulness in detecting objects from vehicle-based mobile mapping systems datasets. A comprehensive analysis using performances measures and graphical techniques are applied to identify the best combination of features and classifiers. A system was built enable users who are not programmers to manage image data and to customise their analyses by combining common data analysis tools to fit their needs.