Supporting Detection of Near and Far Pedestrians in a Collision Prediction System

Lucas Cambuim, Edna Barros

Abstract

This paper proposes a multi-window-based detector to locate pedestrians near and distant. This detector is introduced in a pedestrian collision prediction (PCP) system. We developed an evaluation strategy for the proposed PCP system based on a synthetic collision database, which allowed us to analyze collision prediction quality improvements. Results demonstrate that the combination of different window subdetectors outperforms individual subdetectors’ accuracy and YOLO-based detector. Once our system achieved a processing rate of 30 FPS when processing images in HD resolution, results demonstrated an increase in the number of scenarios that the system could entirely avoid a collision compared to a YOLO-based system.

Download


Paper Citation


in Harvard Style

Cambuim L. and Barros E. (2021). Supporting Detection of Near and Far Pedestrians in a Collision Prediction System.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 669-676. DOI: 10.5220/0010253706690676


in Bibtex Style

@conference{visapp21,
author={Lucas Cambuim and Edna Barros},
title={Supporting Detection of Near and Far Pedestrians in a Collision Prediction System},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={669-676},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010253706690676},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Supporting Detection of Near and Far Pedestrians in a Collision Prediction System
SN - 978-989-758-488-6
AU - Cambuim L.
AU - Barros E.
PY - 2021
SP - 669
EP - 676
DO - 10.5220/0010253706690676