Saved in:
Bibliographic Details
Main Authors: Nataly, Melo Castillo Angie, Sergio, Martin Serrano, Carlota, Salinas, Angel, Sotelo Miguel
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.06549
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912149454979072
author Nataly, Melo Castillo Angie
Sergio, Martin Serrano
Carlota, Salinas
Angel, Sotelo Miguel
author_facet Nataly, Melo Castillo Angie
Sergio, Martin Serrano
Carlota, Salinas
Angel, Sotelo Miguel
contents Pedestrian detection is a critical task in autonomous driving, aimed at enhancing safety and reducing risks on the road. Over recent years, significant advancements have been made in improving detection performance. However, these achievements still fall short of human perception, particularly in cases involving occluded pedestrians, especially entirely invisible ones. In this work, we present the Occlusion-Rich Road Scenes with Pedestrians (OccluRoads) dataset, which features a diverse collection of road scenes with partially and fully occluded pedestrians in both real and virtual environments. All scenes are meticulously labeled and enriched with contextual information that encapsulates human perception in such scenarios. Using this dataset, we developed a pipeline to predict the presence of occluded pedestrians, leveraging Knowledge Graph (KG), Knowledge Graph Embedding (KGE), and a Bayesian inference process. Our approach achieves a F1 score of 0.91, representing an improvement of up to 42% compared to traditional machine learning models.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06549
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prediction of Occluded Pedestrians in Road Scenes using Human-like Reasoning: Insights from the OccluRoads Dataset
Nataly, Melo Castillo Angie
Sergio, Martin Serrano
Carlota, Salinas
Angel, Sotelo Miguel
Computer Vision and Pattern Recognition
Machine Learning
Pedestrian detection is a critical task in autonomous driving, aimed at enhancing safety and reducing risks on the road. Over recent years, significant advancements have been made in improving detection performance. However, these achievements still fall short of human perception, particularly in cases involving occluded pedestrians, especially entirely invisible ones. In this work, we present the Occlusion-Rich Road Scenes with Pedestrians (OccluRoads) dataset, which features a diverse collection of road scenes with partially and fully occluded pedestrians in both real and virtual environments. All scenes are meticulously labeled and enriched with contextual information that encapsulates human perception in such scenarios. Using this dataset, we developed a pipeline to predict the presence of occluded pedestrians, leveraging Knowledge Graph (KG), Knowledge Graph Embedding (KGE), and a Bayesian inference process. Our approach achieves a F1 score of 0.91, representing an improvement of up to 42% compared to traditional machine learning models.
title Prediction of Occluded Pedestrians in Road Scenes using Human-like Reasoning: Insights from the OccluRoads Dataset
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2412.06549