Using Continual Learning on Edge Devices for Cost-Effective, Efficient License Plate Detection

Reshawn Ramjattan, Rajeev Ratan, Shiva Ramoudith, Patrick Hosein, Daniele Mazzei

2023

Abstract

Deep learning networks for license plate detection can produce exceptional results. However, the challenge lies in real-world use where model performance suffers when exposed to new variations and distortions of images. Rain occlusion, low lighting, glare, motion blur and varying camera quality are a few among many possible data shifts that can occur. If portable edge devices are being used then the change in location or the angle of the device also results in reduced performance. Continual learning (CL) aims to handle shifts by helping models learn from new data without forgetting old knowledge. This is particularly useful for deep learning on edge devices where resources are limited. Gdumb is a simple CL method that achieves state-of-the-art performance results. We explore the potential of using continual learning for license plate detection through experiments using an adapted Gdumb approach. Our data was collected for a license plate recognition system using edge devices and consists of images split into 3 categories by quality and distance. We evaluate the application for data shifts, forward/backward transfer, accuracy and forgetting. Our results show that a CL approach under limited resources can attain results close to full retraining for our application.

Paper Citation

in Harvard Style

Ramjattan R., Ratan R., Ramoudith S., Hosein P. and Mazzei D. (2023). Using Continual Learning on Edge Devices for Cost-Effective, Efficient License Plate Detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 544-550. DOI: 10.5220/0011656300003417

in Bibtex Style

@conference{visapp23,
author={Reshawn Ramjattan and Rajeev Ratan and Shiva Ramoudith and Patrick Hosein and Daniele Mazzei},
title={Using Continual Learning on Edge Devices for Cost-Effective, Efficient License Plate Detection},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={544-550},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011656300003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Using Continual Learning on Edge Devices for Cost-Effective, Efficient License Plate Detection
SN - 978-989-758-634-7
AU - Ramjattan R.
AU - Ratan R.
AU - Ramoudith S.
AU - Hosein P.
AU - Mazzei D.
PY - 2023
SP - 544
EP - 550
DO - 10.5220/0011656300003417
PB - SciTePress