Multi-scene auxiliary network-based road crack detection under the framework of distributed edge Intelligence

Author Identifier

Jianxin Li: https://orcid.org/0000-0002-9059-330X

Document Type

Journal Article

Publication Title

IEEE Internet of Things Journal

Publisher

IEEE

School

School of Business and Law

RAS ID

77413

Funders

National Natural Science Foundation of China (62076224)

Comments

Chen, S., Yao, K., Wang, Y., Huang, X., Chen, Y., Yang, A., ... & Min, G. (2025). Multi-scene auxiliary network-based road crack detection under the framework of distributed edge intelligence. IEEE Internet of Things Journal, 12(5), 4613-4628. https://doi.org/10.1109/JIOT.2025.3527233

Abstract

The Internet of Vehicles (IoV) significantly enhances the capabilities for road information collection and processing by enabling real-time connectivity between vehicles, infrastructure, and cloud systems. Leveraging these technological advantages, multi-vehicle collaborative real-time crack detection is expected to become a crucial method to guarantee the health and safety of infrastructures. Due to different vehicles being equipped with various types of sensors, the collected data are heterogeneous, and the limited computational resources of onboard units obstacle the efficient data processing and effective crack detection in infrastructures. To address these challenges, this study proposes a novel Distributed Edge Computing for Crack detection (DECCD), vehicle serve as edge nodes that locally collect and analyze data. The central node continuously aggregates and processes data from multiple edge nodes to train a robust model. This model is periodically refined and then distributed to edge nodes, where it is further training to detect cracks. A multi-scene dataset, called CrackMS, is constructed by integrating multi-scene datasets of different modalities, and the data are enhanced by Deep Convolutional Generative Adversarial Network (DCGAN) to simulate the complexity of crack data acquired by vehicles. A crack detection model, called the Multi-Scene Auxiliary Prediction Network (MSA-Net), which includes an AUX module and a Scene module is proposed to optimize feature extraction and processing of scene changes. Then a lightweight student model with similar performance is trained by knowledge distillation. Experimental results show that the proposed model, while maintaining a lightweight design, achieves a significant improvement in detection accuracy compared to baseline models.

DOI

10.1109/JIOT.2025.3527233

Access Rights

subscription content

Link to Full Text

Share

 
COinS