Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection
IEEE Transactions on Intelligent Transportation Systems · 2024-01 · 25 (1) · 237-250
DOI: 10.1109/tits.2023.3307286 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-01. Verfasst von Kai Li und 6 weiteren Autor:innen. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 62 Literaturangaben. Gefördert von: National Natural Science Foundation of China, University of International Business and Economics (UIBE) Excellent Young Scholar Project, Scientific Research Laboratory of Artificial Intelligence (AI) Technology and Applications, University of International Business and Economics.
Abstract (Originalsprache)
Pixel-level road crack detection has always been a challenging task in intelligent transportation systems. Due to the external environments, such as weather, light, and other factors, pavement cracks often present low contrast, poor continuity, and different sizes in length and width. However, most of the existing studies pay less attention to crack data under different situations. Meanwhile, recent algorithms based on deep convolutional neural networks (DCNNs) have promoted the development of cutting-edge models for crack detection. Nevertheless, they usually focus on complex models for good performance, but ignore detection efficiency in practical applications. In this article, to address the first issue, we collected two new databases (i.e. Rain365 and Sun520) captured on rainy and sunny days respectively, which enrich the data of the open source community. For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet. Specifically, we introduce a novel olive-shaped structure for the encoder network, a lightweight multi-scale block and a new up-sampling method in the decoder network. Numerous experiments show that our model can better balance detection performance and efficiency compared with previous models. Especially, on the Sun520 dataset, our CarNet significantly advances the state-of-the-art performance with ODS F-score from 0.488 to 0.514. Meanwhile, it does so with an improved detection speed (104 frames per second) which is orders of magnitude faster than some recent DCNNs-based algorithms specially designed for crack detection.
Förderung
- National Natural Science Foundation of China
- University of International Business and Economics (UIBE) Excellent Young Scholar Project
- Scientific Research Laboratory of Artificial Intelligence (AI) Technology and Applications, University of International Business and Economics
- Science and Technology Plan Project in Basic Public Welfare Class of Shaoxing City
Zitieren
APA
Li, K., Yang, J., Ma, S., Wang, B., Wang, S., Tian, Y., & Qi, Z. (2024). Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection. IEEE Transactions on Intelligent Transportation Systems, 25(1), 237-250. https://doi.org/10.1109/tits.2023.3307286
Vancouver
Li K, Yang J, Ma S, Wang B, Wang S, Tian Y, et al. Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection. IEEE Transactions on Intelligent Transportation Systems. 2024;25(1):237-250. doi:10.1109/tits.2023.3307286
BibTeX
@article{Li2024,
author = {Li, Kai and Yang, Jie and Ma, Siwei and Wang, Bo and Wang, Shanshe and Tian, Yingjie and Qi, Zhiquan},
title = {Rethinking Lightweight Convolutional Neural Networks for Efficient and High-Quality Pavement Crack Detection},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2024},
volume = {25},
number = {1},
pages = {237--250},
doi = {10.1109/tits.2023.3307286}
}
EUVIMED