FPGA Implementation of Blob Recognition

Real-time embedded vision systems can be used in a wide range of applications and therefore the demand has been increasing for them. In this thesis, an FPGA-based embedded vision system capable of recognizing objects in real time is presented. The proposed system architecture consists of multiple Intellectual Properties (IPs), which are used as a set of complex instructions by an integrated 32-bit CPU Microblaze. Each IP is tailored specifically to meet the needs of the application and at the same time to consume the minimum FPGA logic resources. Integrating both hardware and software on a single FPGA chip, this system can achieve the real-time performance of full VGA video processing at 32 frames per second (fps). In addition, this work comes up with a new method called Dual Connected Component Labelling (DCCL) suitable for FPGA implementation.

Name thesis:degree_name

M.A.Sc.

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Electrical and Computer Engineering

Grantor

University of Windsor

Year dc:date.issued

2011

Author dc:creator

• Xiong, Jian

Advisor dc:contributor.advisor

• Q. M. Jonathan, Wu (Electrical and Computer Engineering)

Licence

• http://creativecommons.org/licenses/by-nc-nd/4.0/

Language dc:language.iso

en_CA

Handle dc:identifier.uri

https://hdl.handle.net/20.500.14776/1038

OAI identifier oai:identifier

oai:uwindsor.scholaris.ca:20.500.14776/1038