Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors

Intelligent transportation systems (ITS) are revolutionizing road safety, particularly in urban areas. Innovative sensors like LiDAR are being deployed to monitor traffic flow in real-time, providing precise data on vehicle movements, road conditions, and congestion patterns. These advancements open...

Full description

Saved in:
Bibliographic Details
Main Authors: Nourhen Sboui, Hakim Ghazzai, Mohamed Hadded, Mourad Elhadef, Gianluca Setti
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10994438/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850272708516904960
author Nourhen Sboui
Hakim Ghazzai
Mohamed Hadded
Mourad Elhadef
Gianluca Setti
author_facet Nourhen Sboui
Hakim Ghazzai
Mohamed Hadded
Mourad Elhadef
Gianluca Setti
author_sort Nourhen Sboui
collection DOAJ
description Intelligent transportation systems (ITS) are revolutionizing road safety, particularly in urban areas. Innovative sensors like LiDAR are being deployed to monitor traffic flow in real-time, providing precise data on vehicle movements, road conditions, and congestion patterns. These advancements open the path for safer roads and more efficient transportation, with the potential for autonomous driving in the future. In this context, since various environmental factors, such as weather fluctuations and terrain diversity, can introduce anomalies that pose risks and malfunctions to a variety of sensor driving systems, the detection of anomalies in spatial-temporal (ST) preprocessed LiDAR data becomes crucial to ensuring safety. In this paper, we propose a novel low-complex unsupervised model for anomaly detection (AD) within ST preprocessed LiDAR data named CNN-BiLSTM VAE that combines variational auto-encoder (VAE) reconstruction capabilities, convolutional neural networks (CNN) spatial characteristic learning capabilities, and bidirectional long-short-term memory (BiLSTM) networks time series learning capabilities in a symmetric mirror-to-mirror (M2M) architecture. Our method aims to detect abnormal behavior and unusual ST patterns in preprocessed, unlabeled LiDAR data without any prior knowledge of the presence of anomalies by learning complex patterns and dependencies within the ST data, while considering the effects of multiple environmental factors. Experimental validation against benchmark models demonstrates the effectiveness of our proposed model in detecting anomalies within preprocessed multidimensional ST LiDAR data. The model strikes a good balance between complexity and efficiency, achieving a 10% accuracy improvement compared to existing models, with an accuracy of 95.1% and an F1-score of 82.6%. Additionally, injecting diverse environmental anomalies enables testing the model’s performance and reliability in real-world scenarios influenced by environmental factors, ensuring robustness across various conditions.
format Article
id doaj-art-35fac5eac862443cb266f34aea7934f0
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-35fac5eac862443cb266f34aea7934f02025-08-20T01:51:42ZengIEEEIEEE Access2169-35362025-01-0113818358184710.1109/ACCESS.2025.356839510994438Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR SensorsNourhen Sboui0https://orcid.org/0009-0000-1698-6394Hakim Ghazzai1https://orcid.org/0000-0002-8636-4264Mohamed Hadded2https://orcid.org/0000-0003-2294-2237Mourad Elhadef3https://orcid.org/0000-0003-4085-7634Gianluca Setti4https://orcid.org/0000-0002-2496-1856Abu Dhabi University, Abu Dhabi, United Arab EmiratesKing Abdullah University of Science and Technology, Thuwal, Saudi ArabiaAbu Dhabi University, Abu Dhabi, United Arab EmiratesAbu Dhabi University, Abu Dhabi, United Arab EmiratesKing Abdullah University of Science and Technology, Thuwal, Saudi ArabiaIntelligent transportation systems (ITS) are revolutionizing road safety, particularly in urban areas. Innovative sensors like LiDAR are being deployed to monitor traffic flow in real-time, providing precise data on vehicle movements, road conditions, and congestion patterns. These advancements open the path for safer roads and more efficient transportation, with the potential for autonomous driving in the future. In this context, since various environmental factors, such as weather fluctuations and terrain diversity, can introduce anomalies that pose risks and malfunctions to a variety of sensor driving systems, the detection of anomalies in spatial-temporal (ST) preprocessed LiDAR data becomes crucial to ensuring safety. In this paper, we propose a novel low-complex unsupervised model for anomaly detection (AD) within ST preprocessed LiDAR data named CNN-BiLSTM VAE that combines variational auto-encoder (VAE) reconstruction capabilities, convolutional neural networks (CNN) spatial characteristic learning capabilities, and bidirectional long-short-term memory (BiLSTM) networks time series learning capabilities in a symmetric mirror-to-mirror (M2M) architecture. Our method aims to detect abnormal behavior and unusual ST patterns in preprocessed, unlabeled LiDAR data without any prior knowledge of the presence of anomalies by learning complex patterns and dependencies within the ST data, while considering the effects of multiple environmental factors. Experimental validation against benchmark models demonstrates the effectiveness of our proposed model in detecting anomalies within preprocessed multidimensional ST LiDAR data. The model strikes a good balance between complexity and efficiency, achieving a 10% accuracy improvement compared to existing models, with an accuracy of 95.1% and an F1-score of 82.6%. Additionally, injecting diverse environmental anomalies enables testing the model’s performance and reliability in real-world scenarios influenced by environmental factors, ensuring robustness across various conditions.https://ieeexplore.ieee.org/document/10994438/Intelligent transportation systemautonomous drivingITS sensorsLiDAR dataanomaly detectionvariational auto-encoder
spellingShingle Nourhen Sboui
Hakim Ghazzai
Mohamed Hadded
Mourad Elhadef
Gianluca Setti
Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
IEEE Access
Intelligent transportation system
autonomous driving
ITS sensors
LiDAR data
anomaly detection
variational auto-encoder
title Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
title_full Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
title_fullStr Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
title_full_unstemmed Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
title_short Unsupervised Hybrid VAE-Based Anomaly Detection for Vehicle Onboard LiDAR Sensors
title_sort unsupervised hybrid vae based anomaly detection for vehicle onboard lidar sensors
topic Intelligent transportation system
autonomous driving
ITS sensors
LiDAR data
anomaly detection
variational auto-encoder
url https://ieeexplore.ieee.org/document/10994438/
work_keys_str_mv AT nourhensboui unsupervisedhybridvaebasedanomalydetectionforvehicleonboardlidarsensors
AT hakimghazzai unsupervisedhybridvaebasedanomalydetectionforvehicleonboardlidarsensors
AT mohamedhadded unsupervisedhybridvaebasedanomalydetectionforvehicleonboardlidarsensors
AT mouradelhadef unsupervisedhybridvaebasedanomalydetectionforvehicleonboardlidarsensors
AT gianlucasetti unsupervisedhybridvaebasedanomalydetectionforvehicleonboardlidarsensors