Anomaly Detection on Roads Using an LSTM and Normal Maps

Yusuke Nonaka, Hideo Saito, Hideaki Uchiyama, Kyota Higa, Masahiro Yamaguchi

2024

Abstract

Detecting anomalies on the road is crucial for generating hazard maps within factory premises and facilitating navigation for visually impaired individuals or robots. This paper proposes a method for anomaly detection on road surfaces using normal maps and a Long Short-Term Memory (LSTM). While existing research primarily focuses on detecting anomalies on the road based on variations in height or color information of images, our approach leverages anomaly detection to identify changes in the spatial structure of the walking scenario. The normal (non-anomaly) data consists of time series normal maps depicting previously traversed roads, which are utilized to predict the upcoming road conditions. Subsequently, an anomaly score is computed by comparing the predicted normal map with the normal map at t +1. If the anomaly score exceeds a dynamically set threshold, it indicates the presence of anomalies on the road. The proposed method employs unsupervised learning for anomaly detection. To assess the effectiveness of the proposed method, we conducted accuracy assessments using a custom dataset, taking into account a qualitative comparison with the results of existing methods. The results confirm that the proposed method effectively detects anomalies on road surfaces through anomaly detection.

Paper Citation

in Harvard Style

Nonaka Y., Saito H., Uchiyama H., Higa K. and Yamaguchi M. (2024). Anomaly Detection on Roads Using an LSTM and Normal Maps. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8, SciTePress, pages 244-255. DOI: 10.5220/0012458900003660

in Bibtex Style

@conference{visapp24,
author={Yusuke Nonaka and Hideo Saito and Hideaki Uchiyama and Kyota Higa and Masahiro Yamaguchi},
title={Anomaly Detection on Roads Using an LSTM and Normal Maps},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={244-255},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012458900003660},
isbn={978-989-758-679-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Anomaly Detection on Roads Using an LSTM and Normal Maps
SN - 978-989-758-679-8
AU - Nonaka Y.
AU - Saito H.
AU - Uchiyama H.
AU - Higa K.
AU - Yamaguchi M.
PY - 2024
SP - 244
EP - 255
DO - 10.5220/0012458900003660
PB - SciTePress