{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:15:55Z","timestamp":1757542555527,"version":"3.40.5"},"reference-count":40,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["International Journal of Digital Multimedia Broadcasting"],"published-print":{"date-parts":[[2021,7,21]]},"abstract":"<jats:p>The convolutional neural network has achieved good results in the superresolution reconstruction of single-frame images. However, due to the shortcomings of infrared images such as lack of details, poor contrast, and blurred edges, superresolution reconstruction of infrared images that preserves the edge structure and better visual quality is still challenging. Aiming at the problems of low resolution and unclear edges of infrared images, this work proposes a two-stage generative adversarial network model to reconstruct realistic superresolution images from four times downsampled infrared images. In the first stage of the generative adversarial network, it focuses on recovering the overall contour information of the image to obtain clear image edges; the second stage of the generative adversarial network focuses on recovering the detailed feature information of the image and has a stronger ability to express details. The infrared image superresolution reconstruction method proposed in this work has highly realistic visual effects and good objective quality evaluation results.<\/jats:p>","DOI":"10.1155\/2021\/5519508","type":"journal-article","created":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T22:05:09Z","timestamp":1626905109000},"page":"1-12","source":"Crossref","is-referenced-by-count":1,"title":["Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0091-1624","authenticated-orcid":true,"given":"Yuqing","family":"Zhao","sequence":"first","affiliation":[{"name":"Xi\u2019an Research Institute of High-Tech, Shaanxi 710025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyuan","family":"Fu","sequence":"additional","affiliation":[{"name":"Xi\u2019an Research Institute of High-Tech, Shaanxi 710025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Research Institute of High-Tech, Shaanxi 710025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaolei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xi\u2019an Research Institute of High-Tech, Shaanxi 710025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Yue","sequence":"additional","affiliation":[{"name":"Xi\u2019an Research Institute of High-Tech, Shaanxi 710025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","reference":[{"key":"1","article-title":"Infrared imaging system and applications","volume":"3","author":"L. Xiang-di","year":"2014","journal-title":"Laser & Infrared"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2013.12.022"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/j.infrared.2013.06.007"},{"key":"4","first-page":"5","article-title":"An overview of computational photography","volume":"6","author":"J. L. Suo","year":"2012","journal-title":"Science China(Information Sciences)"},{"key":"5","article-title":"Learning a Deep Convolutional Network for Image Super-Resolution","volume-title":"European Conference on Computer Vision","author":"D. Chao","year":"2014"},{"issue":"2","key":"6","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"C. Dong","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"7","first-page":"1637","volume-title":"Deeply-Recursive Convolutional Network for Image Super-Resolution, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE","author":"J. Kim","year":"2016"},{"author":"W. Shi","key":"8","article-title":"Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network"},{"key":"9","first-page":"2672","article-title":"Generative Adversarial Networks","volume-title":"Advances in Neural Information Processing Systems","author":"I. Goodfellow","year":"2014"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2945362"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2785879"},{"article-title":"Deep De-Aliasing for Fast Compressive Sensing MRI","year":"2017","author":"S. Yu","key":"12"},{"article-title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","author":"C. Ledig","key":"13","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.19"},{"key":"14","article-title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","volume-title":"Lecture Notes in Computer Science","author":"X. Wang","year":"2018"},{"author":"Q. Mao","key":"15","article-title":"Enhanced Image Decoding Via Edge-Preserving Generative Adversarial Networks"},{"first-page":"3637","article-title":"ESRGAN+: further improving enhanced super-resolution generative adversarial network","author":"N. C. Rakotonirina","key":"16"},{"article-title":"Performance Analysis on Multi-Frame Image Super-Resolution Via Sparse Representation","author":"C. Kraichan","key":"17","doi-asserted-by":"crossref","DOI":"10.1109\/iEECON.2014.6925844"},{"issue":"12","key":"18","first-page":"2898","article-title":"Multimorphology Sparsity regularized image super-resolution","volume":"38","author":"S. Yu-bao","year":"2010","journal-title":"Acta Electronica Sinica"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2201491"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2012.02.003"},{"issue":"5","key":"21","first-page":"920","article-title":"Image super-resolution algorithms based on sparse representation of classified image patches","volume":"40","author":"L. Qiu-sheng","year":"2012","journal-title":"Acta Electronica Sinica"},{"article-title":"StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks","author":"H. Zhang","key":"22","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.629"},{"key":"23","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TPAMI.2018.2856256","article-title":"StackGAN++: realistic image synthesis with stacked generative adversarial networks","volume":"41","author":"H. Zhang","year":"2018","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"first-page":"770","article-title":"Deep Residual Learning for Image Recognition","author":"K. He","key":"24"},{"first-page":"11","article-title":"A Roi Focused Multi-Scale Super-Resolution Method for the Diffusion Tensor Cardiac Magnetic Resonance","author":"J. Zhu","key":"25"},{"author":"J. Zhu","key":"26","article-title":"Lesion Focused Super Resolution"},{"author":"J. Zhu","key":"27","article-title":"How Can We Make GAN Perform Better in Single Medical Image Super-Resolution? A Lesion Focused Multi-Scale Approach"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00928-1_27"},{"key":"29","article-title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","volume-title":"International conference on machine learning","author":"S. Ioffe","year":"2015"},{"issue":"2","key":"30","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"A. Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","year":"2015","author":"A. Radford","key":"31"},{"first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","author":"A. L. Maas","key":"32"},{"key":"33","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","volume-title":"Computer Science","author":"K. Simonyan","year":"2014"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"35","article-title":"Adam: A Method for Stochastic Optimization","volume-title":"Computer Science","author":"D. P. Kingma","year":"2014"},{"issue":"5","key":"36","first-page":"484","article-title":"Image fusion and image quality assessment of fused images","volume":"4","author":"M. Deshmukh","year":"2010","journal-title":"International Journal of Image Processing (IJIP)"},{"key":"37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2061859"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.08.002"},{"article-title":"You Only Look Once: Unified, Real-Time Object Detection","author":"J. Redmon","key":"40","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.91"}],"container-title":["International Journal of Digital Multimedia Broadcasting"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijdmb\/2021\/5519508.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijdmb\/2021\/5519508.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/ijdmb\/2021\/5519508.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T22:05:26Z","timestamp":1626905126000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/ijdmb\/2021\/5519508\/"}},"subtitle":[],"editor":[{"given":"Quoc-Tuan","family":"Vien","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":40,"alternative-id":["5519508","5519508"],"URL":"https:\/\/doi.org\/10.1155\/2021\/5519508","relation":{},"ISSN":["1687-7586","1687-7578"],"issn-type":[{"type":"electronic","value":"1687-7586"},{"type":"print","value":"1687-7578"}],"subject":[],"published":{"date-parts":[[2021,7,21]]}}}