Pedestrian Detector Domain Shift Robustness Evaluation, And Domain Shift Error Mitigation Proposal

Thumbnail Image
Files
181_EEICT_2021_2.pdf(1.26 MB)
Date
2021
Authors
ORCID
Advisor
Referee
Mark
Journal Title
Journal ISSN
Volume Title
Publisher
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Altmetrics
Abstract
This paper evaluates daytime to nighttime traffic image domain shift on Faster R-CNNand SSD based pedestrian and cyclist detectors. Daytime image trained detectors are applied on anewly compiled nighttime image dataset and their performance is evaluated against detectors trainedon both daytime and nighttime images. Faster R-CNN based detectors proved relatively robust, butstill clearly inferior to the models trained on nighttime images, the SSD based model proved noncompetitive.Approaches to the domain shift deterioration mitigation were proposed and future workoutlined.
Description
Keywords
Object detection, Pedestrian detection, Cyclist detection, ADAS, AV, Faster R-CNN,SSD, Domain shift, Domain adaptation, Data augmentation
Citation
Proceedings II of the 27st Conference STUDENT EEICT 2021: Selected Papers. s. 181-187. ISBN 978-80-214-5943-4
https://conf.feec.vutbr.cz/eeict/index/pages/view/ke_stazeni
Document type
Peer-reviewed
Document version
Published version
Date of access to the full text
Language of document
en
Study field
Comittee
Date of acceptance
Defence
Result of defence
Document licence
© Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
DOI
10.13164/eeict.2021.181
URI
http://hdl.handle.net/11012/200837
Collections
Student EEICT 2021: Selected Papers
Citace PRO