Blur Kernel Estimation and Non-Blind Super-Resolution for Power Equipment Infrared Images by Compressed Sensing and Adaptive Regularization

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.

Download Full-text

Research on Blind Super-Resolution Technology for Infrared Images of Power Equipment Based on Compressed Sensing Theory

Sensors ◽

10.3390/s21124109 ◽

2021 ◽

Vol 21 (12) ◽

pp. 4109

Author(s):

Yan Wang ◽

Lingjie Wang ◽

Bingcong Liu ◽

Hongshan Zhao

Keyword(s):

Compressed Sensing ◽

Estimation Method ◽

Kernel Estimation ◽

Super Resolution ◽

Reconstruction Algorithm ◽

Power Equipment ◽

Infrared Images ◽

Blur Kernel Estimation ◽

Resolution Algorithm ◽

Blur Kernel

Infrared images of power equipment play an important role in power equipment status monitoring and fault identification. Aiming to resolve the problems of low resolution and insufficient clarity in the application of infrared images, we propose a blind super-resolution algorithm based on the theory of compressed sensing. It includes an improved blur kernel estimation method combined with compressed sensing theory and an improved infrared image super-resolution reconstruction algorithm based on block compressed sensing theory. In the blur kernel estimation method, we propose a blur kernel estimation algorithm under the compressed sensing framework to realize the estimation of the blur kernel from low-resolution images. In the estimation process, we define a new norm to constrain the gradient image in the iterative process by analyzing the significant edge intensity changes before and after the image is blurred. With the norm, the salient edges can be selected and enhanced, the intermediate latent image generated by the iteration can move closer to the clear image, and the accuracy of the blur kernel estimation can be improved. For the super-resolution reconstruction algorithm, we introduce a blur matrix and a regular total variation term into the traditional compressed sensing model and design a two-step total variation sparse iteration (TwTVSI) algorithm. Therefore, while ensuring the computational efficiency, the boundary effect caused by the block processing inside the image is removed. In addition, the design of the TwTVSI algorithm can effectively process the super-resolution model of compressed sensing with a sparse dictionary, thereby breaking through the reconstruction performance limitation of the traditional regularized super-resolution method of compressed sensing due to the lack of sparseness in the signal transform domain. The final experimental results also verify the effectiveness of our blind super-resolution algorithm.

Download Full-text

Enhancing Blurred Low-Resolution Images via Exploring the Potentials of Learning-Based Super-Resolution

International Journal of Pattern Recognition and Artificial Intelligence ◽

10.1142/s021800141940007x ◽

2019 ◽

Vol 33 (07) ◽

pp. 1940007 ◽

Cited By ~ 3

Author(s):

Wen-Ze Shao ◽

Bing-Kun Bao ◽

Hai-Bo Li

Keyword(s):

Kernel Estimation ◽

Super Resolution ◽

Energy Functional ◽

Local Linear Regression ◽

Estimation Accuracy ◽

Deep Convolutional Neural Networks ◽

Candidate Solution ◽

Blur Kernel Estimation ◽

Blur Kernel ◽

Sr Method

This paper aims to propose a candidate solution to the challenging task of single-image blind super-resolution (SR), via extensively exploring the potentials of learning-based SR schemes in the literature. The task is formulated into an energy functional to be minimized with respect to both an intermediate super-resolved image and a nonparametric blur-kernel. The functional includes a so-called convolutional consistency term which incorporates a nonblind learning-based SR result to better guide the kernel estimation process, and a bi-[Formula: see text]-[Formula: see text]-norm regularization imposed on both the super-resolved sharp image and the nonparametric blur-kernel. A numerical algorithm is deduced via coupling the splitting augmented Lagrangian (SAL) and the conjugate gradient (CG) method. With the estimated blur-kernel, the final SR image is reconstructed using a simple TV-based nonblind SR method. The proposed blind SR approach is demonstrated to achieve better performance than [T. Michaeli and M. Irani, Nonparametric Blind Super-resolution, in Proc. IEEE Conf. Comput. Vision (IEEE Press, Washington, 2013), pp. 945–952.] in terms of both blur-kernel estimation accuracy and image ehancement quality. In the meanwhile, the experimental results demonstrate surprisingly that the local linear regression-based SR method, anchored neighbor regression (ANR) serves the proposed functional more appropriately than those harnessing the deep convolutional neural networks.

Download Full-text

A Unified Optimization Perspective to Single/Multi-observation Blur-Kernel Estimation with Applications to Camera-Shake Deblurring and Nonparametric Blind Super-Resolution

Journal of Mathematical Imaging and Vision ◽

10.1007/s10851-015-0598-4 ◽

2015 ◽

Vol 54 (2) ◽

pp. 216-239 ◽

Cited By ~ 1

Author(s):

Wen-Ze Shao ◽

Qi Ge ◽

Hai-Song Deng ◽

Zhi-Hui Wei ◽

Hai-Bo Li

Keyword(s):

Kernel Estimation ◽

Super Resolution ◽

Blur Kernel Estimation ◽

Camera Shake ◽

Blur Kernel

Download Full-text

Example-based image super-resolution via blur kernel estimation and variational reconstruction

Pattern Recognition Letters ◽

10.1016/j.patrec.2018.12.008 ◽

2019 ◽

Vol 117 ◽

pp. 83-89 ◽

Cited By ~ 1

Author(s):

Qi Yang ◽

Yanzhu Zhang ◽

Tiebiao Zhao

Keyword(s):

Kernel Estimation ◽

Super Resolution ◽

Blur Kernel Estimation ◽

Image Super Resolution ◽

Blur Kernel

Download Full-text

Single Image Super Resolution of Blurred Natural Images Using Blur Kernel Estimation Combined with Super Resolution Convolution Neural Network

10.21203/rs.3.rs-371694/v1 ◽

2021 ◽

Author(s):

LISHA P P ◽

Jayasree V K

Keyword(s):

Neural Network ◽

Optical Sensors ◽

Kernel Estimation ◽

Super Resolution ◽

Convolution Neural Network ◽

Natural Images ◽

Blur Kernel Estimation ◽

Blur Kernel ◽

Single Image Super Resolution

Abstract Image De-blurring and super-resolution (SR) are computer vision tasks aiming to restore image detail and spatial scale, respectively. Despite the significant improvement in image quality resulting from improvement in optical sensors and general electronics, camera shake blur significantly undermines the quality of hand-held photographs. We evaluated the state-of-the-art super-resolution convolution neural network(SR-CNN) architecture and proposed a new architecture for SR application inspired by SR-CNN combined with De-blurring. This paper focus super resolution of a de-focussed and motion blurred natural images. Unlike most de-blurring methods that attempt to solve an inverse problem through a variational formulation, deblurring method applied in this work directly estimates the blur kernel by modeling statistical irregularities in the power spectrum of blurred natural images. Extensive experiments indicate that the proposed method not only generates remarkably clear HR images, but also achieves compelling results in PSNR, MSE and SSIM quantitatively.

Download Full-text

Super Resolution with Kernel Estimation and Dual Attention Mechanism

Information ◽

10.3390/info11110508 ◽

2020 ◽

Vol 11 (11) ◽

pp. 508

Author(s):

Huan Liang ◽

Youdong Ding ◽

Fei Wang ◽

Yuzhen Gao ◽

Xiaofeng Qiu

Keyword(s):

Kernel Estimation ◽

Simulated Data ◽

Super Resolution ◽

Input Image ◽

Attention Mechanism ◽

High Quality ◽

Blur Kernel Estimation ◽

Internal Relations ◽

Blur Kernel ◽

Adaptively Adjusting

Convolutional Neural Networks (CNN) have led to promising performance in super-resolution (SR). Most SR methods are trained and evaluated on predefined blur kernel datasets (e.g., bicubic). However, the blur kernel of real-world LR image is much more complex. Therefore, the SR model trained on simulated data becomes less effective when applied to real scenarios. In this paper, we propose a novel super resolution framework based on blur kernel estimation and dual attention mechanism. Our network learns the internal relations from the input image itself, thus the network can quickly adapt to any input image. We add the blur kernel estimation structure into the network, correcting the inaccurate blur kernel to generate high quality images. Meanwhile, we propose a dual attention mechanism to restore the texture details of the image, adaptively adjusting the features of the image by considering the interdependencies both in channel and spatial. The combination of blur kernel estimation and attention mechanism makes our network perform well for complex blur images in practice. Extensive experiments show that our method (KASR) achieves promising accuracy and visual improvements against most existing methods.

Download Full-text