An improved POCS super-resolution infrared image reconstruction algorithm based on visual mechanism

Liu, Jinsong; Dai, Shaosheng; Guo, Zhongyuan; Zhang, Dezhou

doi:10.1016/j.infrared.2016.07.010

Cited by 11 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…i i e λ − = + (14) It accelerates at the beginning of the iteration, slows down in the middle, and adapts to the high requirements for precision in the later stage. Based on Section 3, an alternating direction projections algorithm can be presented as follows.…”

Section: Dynamic Relax Factormentioning

confidence: 99%

“…The blur PSF centered at an edge pixel is weighted by an exponential function, so the PSF coefficients decrease along the orthogonal direction of the edge and reduce the quantity of Gibbs artifacts present [37]. Based on the visual mechanism, Liu proposed the variability threshold to deal with the super-resolution reconstruction of infrared images, improved contrast of results [14]. After introducing fractional calculus to convex set projection, Lei proposed a super-resolution enhancement algorithm for UAV images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Alternating Direction Projections onto Convex Sets for Super-Resolution Image Reconstruction

Zhou

Wei

et al. 2020

ITC

View full text Add to dashboard Cite

Image reconstruction is important in computer vision and many technologies have been presented to achieve better results. In this paper, gradient information is introduced to define new convex sets. A novel POCS-based model is proposed for super resolution reconstruction. The projection on the convex sets is alternative according to the gray value field and the gradient field. Then the local noise estimation is introduced to determine the threshold adaptively. The efficiency of our proposed model is verified by several numerical experiments. Experimental results show that, the PSNR and the SSIM can be both significantly improved by the proposed model.

show abstract

Section: Dynamic Relax Factormentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Alternating Direction Projections onto Convex Sets for Super-Resolution Image Reconstruction

Zhou

Wei

et al. 2020

ITC

View full text Add to dashboard Cite

show abstract

“…pointy edges into curves. The third consists of reconstruction methods [4] that establish an observation model and solve it using the inverse process to implement image reconstruction. Because the degradation of images is complex and diverse, it is difficult to define for humans to comprehensively define the observation model.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging

et al. 2020

View full text Add to dashboard Cite

To address problems that the loss function does not correlate well with perceptual vision in super-resolution methods based on the convolutional neural network(CNN), a novel model called the ADTV-SRGAN is designed based on the adaptive diagonal total-variation generative adversarial network. Combined with global perception and the local structure adaptive method, spatial loss based on the diagonal variation model is proposed to make the loss function can be adjusted according to the spatial features. Pixel loss and characteristic loss are in combination with the spatial loss for the fusing optimization of the total loss function such that high-frequency details of the images are maintained to improve their quality. The results of experiment show that the proposed method can obtain competitive results in objective evaluations. In subjective assessment, images reconstructed by it are clear, delicate, and natural, and it preserved edgeand texture-related details.

show abstract

Multi-visual Tasks Based on Night-Vision Data Structure and Feature Analysis

Bai

Han

Yue

2019

Night Vision Processing and Understanding

View full text Add to dashboard Cite

An improved POCS super-resolution infrared image reconstruction algorithm based on visual mechanism

Cited by 11 publications

References 16 publications

Alternating Direction Projections onto Convex Sets for Super-Resolution Image Reconstruction

Alternating Direction Projections onto Convex Sets for Super-Resolution Image Reconstruction

Adaptive Diagonal Total-Variation Generative Adversarial Network for Super-Resolution Imaging

Multi-visual Tasks Based on Night-Vision Data Structure and Feature Analysis

Contact Info

Product

Resources

About