Main content

SIF Tracking: Novel Estimation Filter for Object Detection and Tracking

Show full item record

Title: SIF Tracking: Novel Estimation Filter for Object Detection and Tracking
Author: Moksyakov, Alexander
Department: School of Engineering
Program: Engineering
Advisor: Gadsden, Andrew
Abstract: Object detection is currently one of the most heavily researched topics with its potential for object tracking. The research presented here will serve as an introduction to the novel Sliding and Extended Sliding Innovation filter for object tracking. The experiment successfully implements YOLOv4 into Keras to replicate the neural network while integrating the respective code for each filter to perform object tracking and detection on surveillance video. The experiment conducted provided a benchmark for comparing the different filters while introducing a method on integrating new ones for future work. The results demonstrate that the Sliding Innovation Filter had the lowest reported RMSE (root mean square error) out of the 4 filters compared.
URI: https://hdl.handle.net/10214/23743
Date: 2021
Rights: Attribution-NonCommercial-ShareAlike 4.0 International
Terms of Use: All items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.


Files in this item

Files Size Format View
Moksyakov_Alexander_202101_MASc.pdf 8.443Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Attribution-NonCommercial-ShareAlike 4.0 International Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 4.0 International