Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network
With the development of convolutional neural network, video super-resolution algorithm has achieved remarkable success. Because the dependence between frames is complex, traditional methods lack the ability to model the complex dependence, and it is difficult to estimate and compensate the motion ac...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9543650/ |
| _version_ | 1818742698049273856 |
|---|---|
| author | Fang Wan Xiaorong Zhang |
| author_facet | Fang Wan Xiaorong Zhang |
| author_sort | Fang Wan |
| collection | DOAJ |
| description | With the development of convolutional neural network, video super-resolution algorithm has achieved remarkable success. Because the dependence between frames is complex, traditional methods lack the ability to model the complex dependence, and it is difficult to estimate and compensate the motion accurately in the process of video super-resolution reconstruction. Therefore, a reconstruction network based on optical flow residuals is proposed. In low resolution space, the dense residual network is used to obtain the complementary information of adjacent video frames, and then the optical flow of high-resolution video frames is predicted through the pyramid structure, and then the low resolution video frames are transformed into high-resolution video frames through the sub-pixel convolution layer, The high-resolution video frame is compensated with the predicted high-resolution optical flow. Finally, it is input into the super-resolution fusion network to get better effect. A new loss function training network is proposed to better constrain the network. Experimental results on public data sets show that the reconstruction effect is improved in PSNR, structural similarity and subjective visual effect. |
| first_indexed | 2024-12-18T02:16:39Z |
| format | Article |
| id | doaj.art-efa666a18dc94b8aa4f545312c73642c |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T02:16:39Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-efa666a18dc94b8aa4f545312c73642c2022-12-21T21:24:22ZengIEEEIEEE Access2169-35362021-01-01914037214038210.1109/ACCESS.2021.31144379543650Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural NetworkFang Wan0Xiaorong Zhang1https://orcid.org/0000-0002-9008-1857College of Information Engineering, Hainan Vocational University of Science and Technology, Hainan, ChinaSchool of Electronic Engineering, Beihai University, Haidian, Beijing, ChinaWith the development of convolutional neural network, video super-resolution algorithm has achieved remarkable success. Because the dependence between frames is complex, traditional methods lack the ability to model the complex dependence, and it is difficult to estimate and compensate the motion accurately in the process of video super-resolution reconstruction. Therefore, a reconstruction network based on optical flow residuals is proposed. In low resolution space, the dense residual network is used to obtain the complementary information of adjacent video frames, and then the optical flow of high-resolution video frames is predicted through the pyramid structure, and then the low resolution video frames are transformed into high-resolution video frames through the sub-pixel convolution layer, The high-resolution video frame is compensated with the predicted high-resolution optical flow. Finally, it is input into the super-resolution fusion network to get better effect. A new loss function training network is proposed to better constrain the network. Experimental results on public data sets show that the reconstruction effect is improved in PSNR, structural similarity and subjective visual effect.https://ieeexplore.ieee.org/document/9543650/Super resolutionoptical flow estimationdense residual block |
| spellingShingle | Fang Wan Xiaorong Zhang Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network IEEE Access Super resolution optical flow estimation dense residual block |
| title | Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network |
| title_full | Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network |
| title_fullStr | Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network |
| title_full_unstemmed | Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network |
| title_short | Super Resolution Reconstruction Algorithm of UAV Image Based on Residual Neural Network |
| title_sort | super resolution reconstruction algorithm of uav image based on residual neural network |
| topic | Super resolution optical flow estimation dense residual block |
| url | https://ieeexplore.ieee.org/document/9543650/ |
| work_keys_str_mv | AT fangwan superresolutionreconstructionalgorithmofuavimagebasedonresidualneuralnetwork AT xiaorongzhang superresolutionreconstructionalgorithmofuavimagebasedonresidualneuralnetwork |