Industrial-AdaVAD: Adaptive Industrial Video Anomaly Detection Empowered by Edge Intelligence

Jie Xiao, Haocheng Shen, Yasan Ding () and Bin Guo ()
Additional contact information
Jie Xiao: School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
Haocheng Shen: ZTE Corporation, Xi’an 710126, China
Yasan Ding: School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China
Bin Guo: School of Computer Science, Northwestern Polytechnical University, Xi’an 710072, China

Mathematics, 2025, vol. 13, issue 17, 1-23

Abstract: The rapid advancement of Artificial Intelligence of Things (AIoT) has driven an urgent demand for intelligent video anomaly detection (VAD) to ensure industrial safety. However, traditional approaches struggle to detect unknown anomalies in complex and dynamic environments due to the scarcity of abnormal samples and limited generalization capabilities. To address these challenges, this paper presents an adaptive VAD framework powered by edge intelligence tailored for resource-constrained industrial settings. Specifically, a lightweight feature extractor is developed by integrating residual networks with channel attention mechanisms, achieving a 58% reduction in model parameters through dense connectivity and output pruning. A multidimensional evaluation strategy is introduced to dynamically select optimal models for deployment on heterogeneous edge devices. To enhance cross-scene adaptability, we propose a multilayer adversarial domain adaptation mechanism that effectively aligns feature distributions across diverse industrial environments. Extensive experiments on a real-world coal mine surveillance dataset demonstrate that the proposed framework achieves an accuracy of 86.7% with an inference latency of 23 ms per frame on edge hardware, improving both detection efficiency and transferability.

Keywords: video anomaly detection; edge intelligence; domain adaptation (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/17/2711/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/17/2711/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:17:p:2711-:d:1730670

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().