Thesis Defense Announcement for Caleb Merchant
April 30, 2019
Faculty and Students,
You are cordially invited to my thesis defense.
Title: Low-Power High-Resolution Image Detection
When: Tuesday, May 21st at 10:00 a.m.
Where: Simrall Hall, Room 228 (Conference Room)
Candidate: Caleb Merchant
Degree: Masters, Electrical and Computer Engineering
Committee:
Dr. John Ball
(Major Professor )
Dr. Christopher Archibald
(Committee Member)
Dr. Ali Gurbuz
(Committee Member)
Abstract:
Many image processing algorithms exist that can accurately detect humans and other objects such as vehicles and animals. Many of these algorithms require large amounts of processing often requiring hardware acceleration with powerful central processing units (CPUs), graphics processing units (GPUs), field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), etc. Implementing an algorithm that can detect objects such as humans at longer ranges makes these hardware requirements even greater as the amount of pixels necessary to detect objects at both close ranges an long ranges is greatly increased. Comparing the performance of different low-power implementations can be used to determine a trade off between performance and power. An image differencing algorithm is proposed along with low-power hardware selected that is capable of detected humans at ranges of 500 m. The use of simple image differencing means that desktop or server grade hardware accelerators are not required for real-time performance. Multiple versions of the detection algorithm are implemented on the selected hardware and compared for run-time performance on a low-power system. Further classification of objects is not explored, but recommendations and future work is given that could help answer the question of low-power target detection and classification using images. The goal of this work is define an approach to detect and classify targets using a camera that can be integrated into a network of other sensors to provide detailed information about an environment.