Video-based Car Make, Model and Year Recognition

Diana George, Omar Shehata, Hossam El Munim, Sherif Hammad

2021

Abstract

Fine-grained car recognition requires extracting discriminating features and certain car parts which can be used to distinguish between similar cars. This paper represents a full system for car make, model and year recognition in videos. We followed a multi-step approach for automatically detecting, tracking and recognizing them using deep Convolutional Neural Network (CNN). We also focused on the recognition stage where we managed to compare 4 state-of-the art Convolution Neural Networks and adapted them for extracting those features. Moreover, we modified the InceptionResnetv2 network and our results show our success as we managed to elevate the Top 1 accuracy to 0.8617 and Top 5 accuracy to 0.9751.

Paper Citation

in Harvard Style

George D., Shehata O., El Munim H. and Hammad S. (2021). Video-based Car Make, Model and Year Recognition. In Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS, ISBN 978-989-758-537-1, pages 86-91. DOI: 10.5220/0010649900003061

in Bibtex Style

@conference{robovis21,
author={Diana George and Omar Shehata and Hossam El Munim and Sherif Hammad},
title={Video-based Car Make, Model and Year Recognition},
booktitle={Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,},
year={2021},
pages={86-91},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010649900003061},
isbn={978-989-758-537-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Robotics, Computer Vision and Intelligent Systems - Volume 1: ROBOVIS,
TI - Video-based Car Make, Model and Year Recognition
SN - 978-989-758-537-1
AU - George D.
AU - Shehata O.
AU - El Munim H.
AU - Hammad S.
PY - 2021
SP - 86
EP - 91
DO - 10.5220/0010649900003061