Knowledge-Aware Object Detection in Traffic Scenes

Jean-Francois Nies, Jean-Francois Nies, Syed Tahseen Raza Rizvi, Mohsin Munir, Ludger van Elst, Andreas Dengel, Andreas Dengel

2024

Abstract

Autonomous driving is a widely popular domain that empowers the autonomous vehicle to make crucial decisions in a constantly evolving traffic scenario. The role of perception is pivotal in the secure operation of the autonomous vehicle in a complex traffic scene. Recently, several approaches have been proposed for the task of object detection. In this paper, we demonstrate that the concept of Semantic Consistency and the ensuing method of Knowledge-Aware Re-Optimization can be adapted for the problem of object detection in intricate traffic scenes. Moreover, we also introduce a novel method for extracting a knowledge graph encoding the semantic relationship between the traffic participants from an autonomous driving dataset. We also conducted an investigation into the efficacy of utilizing diverse knowledge graph generation methodologies and in- and out-domain knowledge sources on the efficacy of the outcomes. Finally, we investigated the effectiveness of knowledge-aware re-optimization on the Faster-RCNN and DETR object detection models. Results suggest that modest but consistent improvements in precision and recall can be achieved using this method.

Paper Citation

in Harvard Style

Nies J., Rizvi S., Munir M., van Elst L. and Dengel A. (2024). Knowledge-Aware Object Detection in Traffic Scenes. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 617-624. DOI: 10.5220/0012378100003636

in Bibtex Style

@conference{icaart24,
author={Jean-Francois Nies and Syed Tahseen Raza Rizvi and Mohsin Munir and Ludger van Elst and Andreas Dengel},
title={Knowledge-Aware Object Detection in Traffic Scenes},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={617-624},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012378100003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Knowledge-Aware Object Detection in Traffic Scenes
SN - 978-989-758-680-4
AU - Nies J.
AU - Rizvi S.
AU - Munir M.
AU - van Elst L.
AU - Dengel A.
PY - 2024
SP - 617
EP - 624
DO - 10.5220/0012378100003636
PB - SciTePress