Accuracy-efficiency trade-off for using event-based data when performing bounding box-based object detection

Bachelor thesis (2022)

Authors

P. Benschop Electrical Engineering, Mathematics and Computer Science

Contributors

N. Tömen Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
O. Strafforello Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
X. Liu Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
L. Cavalcante Siebert Interactive Intelligence - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2022 Pascal Benschop
Object detection Event-based vision Trade-off Analysis
More Info
expand_more

Published Date

22-06-2022

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

Event-based cameras do not capture frames like an RGB camera, only data from pixels that detect a change in light intensity, making it a better alternative for processing videos. The sparse data acquired from event-based video only captures movement in an asynchronous way. In this paper an evaluation is made on the efficiency and accuracy of object detection, specifically localization, between sparse and dense representations of data. Convolutional Neural Networks are used to train and test on images and event-based data. The results show a positive trade-off in terms of accuracy and efficiency for using sparse event-based data instead of dense data like images. These results provide a basis for an argument to use event-based cameras instead of RGB cameras when dealing with object detection.