A lightweight iterative error reconstruction network for infrared image super-resolution in smart grid. (March 2021)

• Record Type: Journal Article
• Authors: Chen, Lihui; Tang, Rui; Anisetti, Marco; Yang, Xiaomin
• Is Part Of: Sustainable cities and society. Volume 66(2021)
• Publication Date: 2021-03
• Subjects: Convolutional neural networks -- Deep learning -- Smart grid -- Infrared image super-resolution; Sustainable urban development -- Periodicals; Sustainable buildings -- Periodicals; Urban ecology (Sociology) -- Periodicals; 307.76
• DOI: 10.1016/j.scs.2020.102520
• Languages: English
• ISSNs: 2210-6707

Abstract

Highlights: A compact and effective network is proposed for infrared image super-resolution. Reduce the resource consumption of the vanilla dense link by an efficient version. Gradually obtain better results by an iterative error reconstruction mechanism. Abstract: Thermal infrared (IR) images are widely used in smart grids for numerous applications. These applications prefer high-resolution (HR) IR images since HR IR images benefit the performance. However, HR IR imaging devices are extremely expensive. To save the cost of upgrading imaging devices, an iterative error reconstruction network (IERN) is proposed to improve the resolution of IR images. We first achieve efficient dense connections based on linearly compressive skip links. Slightly sacrificing the performance, the efficient dense connections can markedly reduce the parameters and computations of the vanilla dense connections. Then, an iterative error reconstruction mechanism is proposed to boost the performance, which enables IERN to restore many more textures and edges. Specifically, an initial SR image, high-level features, and up-sampled features are obtained firstly. Secondly, a SR error image is acquired by reconstructing the errors between the initial high-level features and the back-projected features from the up-sampled features. Thirdly, a new SR image is obtained by adding the SR error image to the initial SR image. Iterating the above process, the final SR image is achieved when the number of iterations reaches to the iteration threshold. Experimental results reveal the superiority of the proposed method over state-of-the-art methods.