City Research Online

Abstract

This thesis describes research directed towards extracting information sufficient to guide a vehicle through a street, using individual monochromatic street scene images. This description emphasizes more the procedures and the techniques, used during the analysis, than the structure of the FORTRAN programs in which they were implemented.

The research consists of a study in three principal parts. A sequence of processes capable of distinguishing the street from the remainder of the scene is presented and illustrated to describe the first part. The second part involved the development of a technique, based on photogrammetric principles, to measure distances inside the street. The third and final part involved locating the obstacles inside the street.

The first chapter attempts to place the work in the wider field of artificial intelligence, analyses the task of driving, and defines the principal aims of the research. The second chapter identifies the different facets of image analysis, and reviews in depth the state of the art in this field. The third chapter reviews the different techniques which are available for image processing. Because of the importance of the human eye-brain system for future developments in machine vision, chapter outlines the physiological structure and the psychological bevaviour of the human visual system. The chapter five discusses the many computational facilities used during the research.

The chapters six, seven and eight, describe the three principal parts of the research. The chapter six describes the extraction of the street from the remainder of the street scene. The chapter seven describes the principles and the technique used for calculating distances. The chapter eight describes a technique for locating obstacles inside the street.

The conclusion and general discussions are presented in chapter nine. In the conclusion, the results are discussed, the need for further research is emphasized, and suggestions for future work are outlined.

Publication Type:	Thesis (Doctoral)
Subjects:	T Technology > TA Engineering (General). Civil engineering (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TL Motor vehicles. Aeronautics. Astronautics
Departments:	School of Science & Technology > Department of Engineering School of Science & Technology > School of Science & Technology Doctoral Theses Doctoral Theses

Export

Downloads