Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer

Mohamed Amine Marnissi, Mohamed Amine Marnissi, Mohamed Amine Marnissi, Ikram Hattab, Ikram Hattab, Hajer Fradi, Hajer Fradi, Anis Sahbani, Najoua Essoukri Ben Amara, Najoua Essoukri Ben Amara

2022

Abstract

In this paper, we focus on the problem of automatic pedestrian detection for surveillance applications. Particularly, the main goal is to perform real-time detection from both visible and thermal cameras for complementary aspects. To handle that, a fusion network that uses features from both inputs and performs augmentation by means of visual saliency transformation is proposed. This fusion process is incorporated into YOLO-v3 as base architecture. The resulting detection model is trained in a paired setting in order to improve the results compared to the detection of each single input. To prove the effectiveness of the proposed fusion framework, several experiments are conducted on KAIST multi-spectral dataset. From the obtained results, it has been shown superior results compared to single inputs and to other fusion schemes. The proposed approach has also the advantage of a very low computational cost, which is quite important for real-time applications. To prove that, additional tests on a security robot are presented as well.

Paper Citation

in Harvard Style

Marnissi M., Hattab I., Fradi H., Sahbani A. and Ben Amara N. (2022). Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 275-284. DOI: 10.5220/0010913000003124

in Bibtex Style

@conference{visapp22,
author={Mohamed Amine Marnissi and Ikram Hattab and Hajer Fradi and Anis Sahbani and Najoua Essoukri Ben Amara},
title={Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={275-284},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010913000003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Bispectral Pedestrian Detection Augmented with Saliency Maps using Transformer
SN - 978-989-758-555-5
AU - Marnissi M.
AU - Hattab I.
AU - Fradi H.
AU - Sahbani A.
AU - Ben Amara N.
PY - 2022
SP - 275
EP - 284
DO - 10.5220/0010913000003124
PB - SciTePress