When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xiao, Dong, Chen, Guangyao, Peng, Peixi, Huang, Yangru, Zhao, Yifan, Dai, Yongxing, Tian, Yonghong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908415125618688
author Xiao, Dong
Chen, Guangyao
Peng, Peixi
Huang, Yangru
Zhao, Yifan
Dai, Yongxing
Tian, Yonghong
author_facet Xiao, Dong
Chen, Guangyao
Peng, Peixi
Huang, Yangru
Zhao, Yifan
Dai, Yongxing
Tian, Yonghong
contents Anomaly detection is essential for the safety and reliability of autonomous driving systems. Current methods often focus on detection accuracy but neglect response time, which is critical in time-sensitive driving scenarios. In this paper, we introduce real-time anomaly detection for autonomous driving, prioritizing both minimal response time and high accuracy. We propose a novel multimodal asynchronous hybrid network that combines event streams from event cameras with image data from RGB cameras. Our network utilizes the high temporal resolution of event cameras through an asynchronous Graph Neural Network and integrates it with spatial features extracted by a CNN from RGB images. This combination effectively captures both the temporal dynamics and spatial details of the driving environment, enabling swift and precise anomaly detection. Extensive experiments on benchmark datasets show that our approach outperforms existing methods in both accuracy and response time, achieving millisecond-level real-time performance.
format Preprint
id arxiv_https___arxiv_org_abs_2506_17457
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
Xiao, Dong
Chen, Guangyao
Peng, Peixi
Huang, Yangru
Zhao, Yifan
Dai, Yongxing
Tian, Yonghong
Computer Vision and Pattern Recognition
Anomaly detection is essential for the safety and reliability of autonomous driving systems. Current methods often focus on detection accuracy but neglect response time, which is critical in time-sensitive driving scenarios. In this paper, we introduce real-time anomaly detection for autonomous driving, prioritizing both minimal response time and high accuracy. We propose a novel multimodal asynchronous hybrid network that combines event streams from event cameras with image data from RGB cameras. Our network utilizes the high temporal resolution of event cameras through an asynchronous Graph Neural Network and integrates it with spatial features extracted by a CNN from RGB images. This combination effectively captures both the temporal dynamics and spatial details of the driving environment, enabling swift and precise anomaly detection. Extensive experiments on benchmark datasets show that our approach outperforms existing methods in both accuracy and response time, achieving millisecond-level real-time performance.
title When Every Millisecond Counts: Real-Time Anomaly Detection via the Multimodal Asynchronous Hybrid Network
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.17457