Date of Award

Summer 2008

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Electrical & Computer Engineering

Program/Concentration

Electrical Engineering

Committee Director

Zia-ur Rahman

Committee Member

Vijayan K. Asari

Committee Member

Jiang Li

Call Number for Print

Special Collections LD4331.E55 V87 2008

Abstract

It can be dangerous for a pilot to attempt to land an aircraft safely in poor visibility conditions such as rain, fog, haze, snow and low light, but external imagery of a runway can be enhanced to provide increased situational awareness. Objects that are detected in a scene may or may not be a hazard, so interpretation is left to the pilot. In order to detect whether an object is a hazard to safe landing, it is necessary to determine whether the object is on the runway. For this purpose, two image segmentation algorithms: histogram based d-peak algorithm and local feature based quadtree algorithm have been implemented in this thesis. The purpose of image segmentation here is to separate the objects of interest from the background. Several algorithms and techniques have been developed for image segmentation, but there is no general solution. Several of these techniques may be combined to effectively solve an image segmentation problem. The d-peak algorithm is a histogram based method. Histogram Based methods are very efficient when compared with the other image segmentation techniques because they require only one pass through the pixels. In the quadtree segmentation algorithm, a full tree is formed by splitting a single parent node into four children or quadrants, and all descendants are recursively split by iteratively testing conditions for splitting the blocks until some minimum bound is reached. The parameters considered for splitting the parental blocks here are mean, standard deviation and the size of the block.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/s4nw-pc58

Download

Share

COinS