Classification, object detection and tracking in high resolution radar imagery for autonomous driving using deep learning

Downloads

Downloads per month over past year

Stroescu, Ana Raluca (2022). Classification, object detection and tracking in high resolution radar imagery for autonomous driving using deep learning. University of Birmingham. Ph.D.

[img]
Preview
Stroescu2022PhD.pdf
Text - Accepted Version
Available under License All rights reserved.

Download (53MB) | Preview

Abstract

Over the past years, there has been an increase in research for artificial intelligence methods in the field of autonomous driving. Significant advances have been made recently and public datasets for urban scenes are now available for object detection and segmentation on optical images for self-driving vehicles. However, the real world traffic environment is very complex and the development of a sensing system that can perform in adverse weather conditions, such as fog, heavy rain and snow, when the capabilities of the optical vision are diminished, still remains a challenge for the automotive industry.
Therefore, this thesis presents a method for classification, object detection and tracking of different roadside targets in high frequency radar imagery, using deep neural networks. The current work confirms that, despite their numerous applications, such as image and speech recognition, health care, finance, web search engines, advertising, etc., neural networks can also be successfully employed in high frequency automotive radar imagery. Classification and object detection methods using deep neural networks have the potential to overcome the current object identification issues in radar and can support the development of all-weather sensing systems for autonomous vehicles.

Type of Work: Thesis (Doctorates > Ph.D.)
Award Type: Doctorates > Ph.D.
Supervisor(s):
Supervisor(s)EmailORCID
Gashinova, MarinaUNSPECIFIEDUNSPECIFIED
Cherniakov, MikhailUNSPECIFIEDUNSPECIFIED
Daniel, LiamUNSPECIFIEDUNSPECIFIED
Licence: All rights reserved
College/Faculty: Colleges (2008 onwards) > College of Engineering & Physical Sciences
School or Department: School of Engineering, Department of Electronic, Electrical and Systems Engineering
Funders: Other
Other Funders: School of Engineering
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
URI: http://etheses.bham.ac.uk/id/eprint/12986

Actions

Request a Correction Request a Correction
View Item View Item

Downloads

Downloads per month over past year