CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification

Mohamed Ilyes Lakhal, Sergio Escalera, Hakan Cevikalp

2018

Abstract

Vehicle type classification is considered to be a central part of Intelligent Traffic Systems. In the recent years, deep learning methods have emerged in as being the state-of-the-art in many computer vision tasks. In this paper, we present a novel yet simple deep learning framework for the vehicle type classification problem. We propose an end-to-end trainable system, that combines convolution neural network for feature extraction and recurrent neural network as a classifier. The recurrent network structure is used to handle various types of feature inputs, and at the same time allows to produce a single or a set of class predictions. In order to assess the effectiveness of our solution, we have conducted a set of experiments in two public datasets, obtaining state of the art results. In addition, we also report results on the newly released MIO-TCD dataset.

Paper Citation

in Harvard Style

Lakhal M., Escalera S. and Cevikalp H. (2018). CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification. In Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP; ISBN 978-989-758-290-5, SciTePress, pages 137-144. DOI: 10.5220/0006533601370144

in Bibtex Style

@conference{visapp18,
author={Mohamed Ilyes Lakhal and Sergio Escalera and Hakan Cevikalp},
title={CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification},
booktitle={Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP},
year={2018},
pages={137-144},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006533601370144},
isbn={978-989-758-290-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP
TI - CRN: End-to-end Convolutional Recurrent Network Structure Applied to Vehicle Classification
SN - 978-989-758-290-5
AU - Lakhal M.
AU - Escalera S.
AU - Cevikalp H.
PY - 2018
SP - 137
EP - 144
DO - 10.5220/0006533601370144
PB - SciTePress