PARALLEL IMAGE PROCESSING AND COMPUTER VISION ARCHITECTURE

of Undergraduate Thesis Presented to the Electrical and Computer Engineering Department of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Bachelor of Science summa cum laude PARALLEL IMAGE PROCESSING AND COMPUTER VISION ARCHITECTURE By James Greco May 2005 Chair: Dapeng Wu Major Department: Electrical and Computer Engineering Real-time image processing is limited with modern microprocessors. This thesis presents a novel method for the implementation of image processing and computer vision algorithms in hardware. Using pipelining methods from computer architecture, our system provides a flexible and fast platform for the development of image processing algorithms. The architecture’s computational power over a Pentium 4 microprocessor is shown through an analytical analysis of the simulated performance. Two demonstrations of the architecture’s implementation in a Field Programmable Gate Array are provided The position of an object is tracked by using the object’s color properties and the micro air vehicle on-board horizon tracking problem is solved. CHAPTER