ADSCN: Adaptive dense skip connection network for railway infrastructure displacement monitoring images super-resolution
- PDF / 4,413,145 Bytes
- 16 Pages / 439.642 x 666.49 pts Page_size
- 61 Downloads / 172 Views
ADSCN: Adaptive dense skip connection network for railway infrastructure displacement monitoring images super-resolution Hui Yin1 · Jin Wan1 · Shi-Jie Zhang2 · Zhi-Yuan Xu1 Received: 2 December 2019 / Revised: 3 August 2020 / Accepted: 29 September 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Railway infrastructure displacement monitoring (RIDM) has a pivotal role in the safety of train operation. However, due to the limitations of monitoring distance and instrument cost, the visual displacement monitoring system tends to obtain low-resolution and low-quality images, especially for key monitoring regions, which can seriously affect the monitoring performance. Improving RIDM image quality and resolution thus becomes a critically important task. In this paper, we present a novel Adaptive Dense Skip Connection Network (ADSCN) for image super-resolution to improve the quality of displacement monitoring image and the precision of displacement measurement. Specifically, by embedding dense skip connection into the generator, the low-level feature information can be fully utilized to generate high-quality super-resolution (SR) image. Furthermore, we introduce the adaptive mechanism into each skip connection to select low-level features for further performance enhancement. Finally, the discriminator is used to discriminate whether the input is a real high-resolution image or a generated SR image, which helps the generator learn to achieve better performance. Experimental results using nature images and different types of RIDM images demonstrate that our ADSCN is superior to interpolation-based and deep learning-based image SR algorithms, both in image quality and interpretation precision. Keywords Railway infrastructure displacement monitoring · Image super-resolution · Adaptive dense skip connection network
1 Introduction Railway infrastructure displacement monitoring (RIDM) is a most important task in railway safety. The obvious expansion displacement of railway infrastructure can directly affect the safety of train operation. Therefore, it is necessary to monitor the expansion displacement of railway infrastructure with high frequently and precision. Visual measurement has been applied to the railway infrastructure monitoring because of its non-contact and Hui Yin
[email protected]
Extended author information available on the last page of the article.
Multimedia Tools and Applications
non-destructive advantages. As the displacement of railway infrastructure is mostly relative displacement, a ruler is usually attached as a reference to observe the relative position change of the infrastructure, which is the key monitoring region, as shown in Fig. 1. As a result, the visual displacement monitoring task is equivalent to interpreting the value of the ruler in the image. Image spatial resolution is one of the key influencing factors of the RIDM images, especially for key monitoring regions, which greatly affects the displacement monitoring performance of real world. However, due
Data Loading...
