Abstract
Infrared sensing technology is more and more widely used in the construction of power Internet of Things. However, due to cost constraints, it is difficult to achieve the large-scale installation of high-precision infrared sensors. Therefore, we propose a blind super-resolution method for infrared images of power equipment to improve the imaging quality of low-cost infrared sensors. If the blur kernel estimation and non-blind super-resolution are performed at the same time, it is easy to produce sub-optimal results, so we chose to divide the blind super-resolution into two parts. First, we propose a blur kernel estimation method based on compressed sensing theory, which accurately estimates the blur kernel through low-resolution images. After estimating the blur kernel, we propose an adaptive regularization non-blind super-resolution method to achieve the high-quality reconstruction of high-resolution infrared images. According to the final experimental demonstration, the blind super-resolution method we proposed can effectively reconstruct low-resolution infrared images of power equipment. The reconstructed image has richer details and better visual effects, which can provide better conditions for the infrared diagnosis of the power system.
Highlights
The concept of the Internet of Things is proposed, and the era of the Internet of Everything is coming
In order to improve the quality of SR reconstructed images, to meet the actual needs of the power industry, we propose a blind SR method
In order to improve the quality of SR reconstructed images, so as to facilitate the status monitoring and fault analysis of power equipment, we propose a blind SR method of compressed sensing
Summary
The concept of the Internet of Things is proposed, and the era of the Internet of Everything is coming. This type of method constructs the model based on the principle of image degradation, and realizes the SR reconstruction of the image by combining prior information in the Bayesian framework or introducing regularization in its inverse problem [11,12,13,14,15,16,17] Such methods are not limited by samples, are flexible in application and have good reconstruction effects, which are easy to be widely applied in the power grid. The third type of method is the blind SR method, which simultaneously solves the problem of blur kernel estimation and HR image reconstruction. The final experimental results show that our proposed blind SR reconstruction method for infrared images of power equipment can effectively reconstruct LR infrared images through successive blur kernel estimation and non-blind reconstruction. Sensors 2021, 21, 4820 image has richer details and better visual effects, which can provide better conditions for the infrared diagnosis of the power system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
