The Multi-fusion U-Net network based on U-Net is proposed to attain pixel-level detection of sealed cracks. The multi-fusion module, dual attention mechanism, and Atrous Spatial Pyramid Pooling (ASPP) are designed to efficiently capture the details of sealed cracks. The 3163 image set is divided into training, validation, and testing datasets. The training data consist of 2463 image sets. The Multi-fusion U-Net outperforms U-Net and DANet during the training process. The test experimental results indicate that the F-measure and IOU of the Multi-fusion U-Net on the 200 test images are 84.36 % and 72.95 % respectively. Compared with seven state-of-the-art models (i.e., DANet, MACSNet, U-Net, SegNet, DeepLabV3+, PSPNet, SegFormer), the proposed network exhibits higher detection accuracy on the 200 testing images. The average time to process the images for all networks was 49.78 ms/frame, and the proposed network processed the images in 57 ms/frame. Real-time detection of sealed cracks is feasible.

Jing Shang

Jie Xu

Allen A. Zhang

Yang Liu

Kelvin C.P. Wang

Dongya Ren

Hang Zhang

Zishuo Dong

Anzheng He

Measurement

邀请对测量和仪器科学与技术各个领域的新成果进行投稿。鼓励作者提交新颖材料，其最终目标是在以下领域取得进步：测量和计量基础、传感器、测量仪器、测量和估计技术、测量数据处理和融合算法、评估程序和工厂方法和工业过程，系统、过程和算法的性能分析，面向测量的数学模型，互联世界中的分布式测量系统。

This journal invites submissions of new findings in all areas of measurement and instrumentation science and technology. We encourage authors to submit innovative materials aimed at advancing progress in the following fields: fundamentals of measurement and metrology, sensors, measuring instruments, measurement and estimation techniques, measurement data processing and fusion algorithms, evaluation procedures and factory methods, performance analysis of industrial processes, mathematical models for measurement, and distributed measurement systems in a connected world.

本期刊欢迎对测量和仪器科学与技术各个领域的新成果进行投稿。我们鼓励作者提交新颖的研究材料，旨在推动以下领域的进步：测量和计量基础、传感器、测量仪器、测量和估计技术、测量数据处理与融合算法、评估程序与工厂方法、工业过程的性能分析、面向测量的数学模型，以及在互联世界中的分布式测量系统。

Category	Quartile
工程技术	2
工程技术, 工程综合	2
工程技术, 仪器仪表	2

Automatic Pixel-level pavement sealed crack detection using Multi-fusion U-Net network

ivySCI AI Smartly Parses PDF, Answers Researchers' Questions, and Helps You Understand Papers in Seconds

Journal Info

Category	Quartile
INSTRUMENTS & INSTRUMENTATION	1