Event Details
Accelerating a Non-binary Descriptor: a Novel Hardware–Software Co-Design of the HOG Algorithm
Presenter: Sina Ghaffari
Supervisor:
Date: Thu, August 12, 2021
Time: 10:00:00 - 00:00:00
Place: ZOOM - Please see below.
ABSTRACT
Zoom Meeting
Link:
Meeting ID: 885 1123 4481
Password: 902320
Dial by your location
+1 778 907 2071 Canada
+1 647 558 0588 Canada
Meeting ID: 885 1123 4481
Password: 902320
Find your local number:
Note: Please log in to Zoom via SSO and your UVic Netlink ID
Abstract: Image matching is one of the fundamental problems in computer vision which has many applications such as object recognition, structure from motion, and visual simultaneous localization and mapping (vSLAM). One of the important steps in image matching is image description. In this work, we aim to enhance the speed of a well-known non-binary description algorithm, histogram of oriented gradients. HOG is a commonly used feature extraction algorithm in many applications. Hardware acceleration can boost the speed of this algorithm due to its large number of computations. We propose a hardware–software co-design of the histogram of oriented gradients and the subsequent support vector machine classifier. Our main focus is to minimize the resource usage of the algorithm while maintaining its accuracy and speed. Our proposed design attains a frame rate of 115 frames per second on a Xilinx® Kintex® Ultrascale™ FPGA while using less hardware resources, and only losing accuracy marginally, in comparison with other existing work.