Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images
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...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | International Journal of Digital Multimedia Broadcasting |
| Online Access: | http://dx.doi.org/10.1155/2021/5519508 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832560567200514048 |
|---|---|
| author | Yuqing Zhao Guangyuan Fu Hongqiao Wang Shaolei Zhang Min Yue |
| author_facet | Yuqing Zhao Guangyuan Fu Hongqiao Wang Shaolei Zhang Min Yue |
| author_sort | Yuqing Zhao |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-f14c08b1acfb450dba6ae787bd97a2e8 |
| institution | Kabale University |
| issn | 1687-7578 1687-7586 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Digital Multimedia Broadcasting |
| spelling | doaj-art-f14c08b1acfb450dba6ae787bd97a2e82025-02-03T01:27:19ZengWileyInternational Journal of Digital Multimedia Broadcasting1687-75781687-75862021-01-01202110.1155/2021/55195085519508Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared ImagesYuqing Zhao0Guangyuan Fu1Hongqiao Wang2Shaolei Zhang3Min Yue4Xi’an Research Institute of High-Tech, Shaanxi 710025, ChinaXi’an Research Institute of High-Tech, Shaanxi 710025, ChinaXi’an Research Institute of High-Tech, Shaanxi 710025, ChinaXi’an Research Institute of High-Tech, Shaanxi 710025, ChinaXi’an Research Institute of High-Tech, Shaanxi 710025, ChinaThe 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.http://dx.doi.org/10.1155/2021/5519508 |
| spellingShingle | Yuqing Zhao Guangyuan Fu Hongqiao Wang Shaolei Zhang Min Yue Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images International Journal of Digital Multimedia Broadcasting |
| title | Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images |
| title_full | Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images |
| title_fullStr | Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images |
| title_full_unstemmed | Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images |
| title_short | Generative Adversarial Network-Based Edge-Preserving Superresolution Reconstruction of Infrared Images |
| title_sort | generative adversarial network based edge preserving superresolution reconstruction of infrared images |
| url | http://dx.doi.org/10.1155/2021/5519508 |
| work_keys_str_mv | AT yuqingzhao generativeadversarialnetworkbasededgepreservingsuperresolutionreconstructionofinfraredimages AT guangyuanfu generativeadversarialnetworkbasededgepreservingsuperresolutionreconstructionofinfraredimages AT hongqiaowang generativeadversarialnetworkbasededgepreservingsuperresolutionreconstructionofinfraredimages AT shaoleizhang generativeadversarialnetworkbasededgepreservingsuperresolutionreconstructionofinfraredimages AT minyue generativeadversarialnetworkbasededgepreservingsuperresolutionreconstructionofinfraredimages |