Lightweight deep learning for real-time road distress detection on mobile devices

Nature Communications, vol. 16, pp. 4212

Abstract

Efficient and accurate road distress detection is crucial for infrastructure maintenance and transportation safety. Traditional manual inspections are labor-intensive and time-consuming, while increasingly popular automated systems often rely on computationally intensive devices, limiting widespread adoption. To address these challenges, this study introduces MobiLiteNet, a lightweight deep learning approach designed for mobile deployment on smartphones and mixed reality systems. Utilizing a diverse dataset collected from Europe and Asia, MobiLiteNet incorporates Efficient Channel Attention to boost model performance, followed by structural refinement, sparse knowledge distillation, structured pruning, and quantization to significantly increase the computational efficiency while preserving high detection accuracy. To validate its effectiveness, MobiLiteNet improves the existing MobileNet model. Test results show that the improved MobileNet outperforms baseline models on mobile devices. With significantly reduced computational costs, this approach enables real-time, scalable, and accurate road distress detection, contributing to more efficient road infrastructure management and intelligent transportation systems.

Authors 5

1. Yuanyuan Hu Aachen Institute of Highway Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute of Highway Engineering, RWTH Aachen University, Aachen, Germany

2. Ning Chen

   Beijing University of Technology

   Affiliation as printed

   Beijing Key Laboratory of Traffic Engineering, Beijing University of Technology, Beijing, China

3. Yue Hou corresponding

   Swansea University

   Affiliation as printed

   Department of Civil Engineering, Faculty of Science and Engineering, Swansea University, Swansea, UK. yue.hou@swansea.ac.uk

4. Baohong Jing
   Affiliation as printed

   Qingdao Yicheng Sichuang Link of Things Technology Co., Ltd., Qingdao, China

5. Pengfei Liu corresponding Aachen Institute of Highway Engineering

   RWTH Aachen University

   Affiliation as printed

   Institute of Highway Engineering, RWTH Aachen University, Aachen, Germany. liu@isac.rwth-aachen.de