Automatic Labelling for Low-Light Pedestrian Detection

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bouzoulas, Dimitrios, Alamikkotervo, Eerik, Ojala, Risto
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911510486319104
author Bouzoulas, Dimitrios
Alamikkotervo, Eerik
Ojala, Risto
author_facet Bouzoulas, Dimitrios
Alamikkotervo, Eerik
Ojala, Risto
contents Pedestrian detection in RGB images is a key task in pedestrian safety, as the most common sensor in autonomous vehicles and advanced driver assistance systems is the RGB camera. A challenge in RGB pedestrian detection, that does not appear to have large public datasets, is low-light conditions. As a solution, in this research, we propose an automated infrared-RGB labeling pipeline. The proposed pipeline consists of 1) Infrared detection, where a fine-tuned model for infrared pedestrian detection is used 2) Label transfer process from the infrared detections to their RGB counterparts 3) Training object detection models using the generated labels for low-light RGB pedestrian detection. The research was performed using the KAIST dataset. For the evaluation, object detection models were trained on the generated autolabels and ground truth labels. When compared on a previously unseen image sequence, the results showed that the models trained on generated labels outperformed the ones trained on ground-truth labels in 6 out of 9 cases for the mAP@50 and mAP@50-95 metrics. The source code for this research is available at https://github.com/BouzoulasDimitrios/IR-RGB-Automated-LowLight-Pedestrian-Labeling
format Preprint
id arxiv_https___arxiv_org_abs_2507_02513
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Automatic Labelling for Low-Light Pedestrian Detection
Bouzoulas, Dimitrios
Alamikkotervo, Eerik
Ojala, Risto
Computer Vision and Pattern Recognition
Pedestrian detection in RGB images is a key task in pedestrian safety, as the most common sensor in autonomous vehicles and advanced driver assistance systems is the RGB camera. A challenge in RGB pedestrian detection, that does not appear to have large public datasets, is low-light conditions. As a solution, in this research, we propose an automated infrared-RGB labeling pipeline. The proposed pipeline consists of 1) Infrared detection, where a fine-tuned model for infrared pedestrian detection is used 2) Label transfer process from the infrared detections to their RGB counterparts 3) Training object detection models using the generated labels for low-light RGB pedestrian detection. The research was performed using the KAIST dataset. For the evaluation, object detection models were trained on the generated autolabels and ground truth labels. When compared on a previously unseen image sequence, the results showed that the models trained on generated labels outperformed the ones trained on ground-truth labels in 6 out of 9 cases for the mAP@50 and mAP@50-95 metrics. The source code for this research is available at https://github.com/BouzoulasDimitrios/IR-RGB-Automated-LowLight-Pedestrian-Labeling
title Automatic Labelling for Low-Light Pedestrian Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.02513