Analysis of Polarimetric Imaging in Target Identification

Date of Award

5-9-2026

Degree Name

M.S. in Computer Engineering

Department

Department of Electrical and Computer Engineering

Advisor/Chair

Bradley Ratliff

Abstract

The most common type of data that is widely used today is RGB intensity imagery. RGB imagery is widely used due to its abundance of available data and strong contrast between objects This is useful when trying to identify target vehicles, but it is not the only way to identify vehicles. Optical Polarization can provide key pieces of information about objects and targets. Using polarimetric information, we can highlight certain aspects of an image to provide better contrast and better determine what each object is. With this enhanced image, there is a potential to increase the accuracy of previous vehicle identification algorithms. This paper investigates this concept in greater detail. This paper will go over what polarization is, how it is useful, and how it can be applied to normal RGB images. From here this paper will look at previous algorithms to identify vehicles such as normalized cross correlation and spectrally shaped correlation. This paper will then describe the experiment that was done to provide proof that polarimetrically enhanced images result in improved accuracy than the majority of RGB images.

Keywords

Computer Engineering, Computer Science, Electrical Engineering, Experiments, Physics, Technology

Comments

OCLC No. 1591628021

Rights Statement

Copyright 2026, author.

Link to Full Text

Share

COinS
 
 
 

Links