Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing
In recent decades, haze has become an environmental issue due to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to ins...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/13/6725 |
| _version_ | 1797480798748672000 |
|---|---|
| author | Cheng-Ying Tsai Chieh-Li Chen |
| author_facet | Cheng-Ying Tsai Chieh-Li Chen |
| author_sort | Cheng-Ying Tsai |
| collection | DOAJ |
| description | In recent decades, haze has become an environmental issue due to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to instantly remove the haze effect on an image. The purpose of this study is to leverage useful modules to achieve a lightweight and real-time image-dehazing model. Based on the U-Net architecture, this study integrates four modules, including an image pre-processing block, inception-like blocks, spatial pyramid pooling blocks, and attention gates. The original attention gate was revised to fit the field of image dehazing and consider different color spaces to retain the advantages of each color space. Furthermore, using an ablation study and a quantitative evaluation, the advantages of using these modules were illustrated. Through existing indoor and outdoor test datasets, the proposed method shows outstanding dehazing quality and an efficient execution time compared to other state-of-the-art methods. This study demonstrates that the proposed model can improve dehazing quality, keep the model lightweight, and obtain pleasing dehazing results. A comparison to existing methods using the RESIDE SOTS dataset revealed that the proposed model improves the <i>SSIM</i> and <i>PSNR</i> metrics by at least 5–10%. |
| first_indexed | 2024-03-09T22:05:19Z |
| format | Article |
| id | doaj.art-30e8459b4813467db9632669818478f3 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T22:05:19Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-30e8459b4813467db9632669818478f32023-11-23T19:41:40ZengMDPI AGApplied Sciences2076-34172022-07-011213672510.3390/app12136725Attention-Gate-Based Model with Inception-like Block for Single-Image DehazingCheng-Ying Tsai0Chieh-Li Chen1Department of Aeronautics and Astronautics, National Cheng Kung University, Tainan 70101, TaiwanDepartment of Aeronautics and Astronautics, National Cheng Kung University, Tainan 70101, TaiwanIn recent decades, haze has become an environmental issue due to its effects on human health. It also reduces visibility and degrades the performance of computer vision algorithms in autonomous driving applications, which may jeopardize car driving safety. Therefore, it is extremely important to instantly remove the haze effect on an image. The purpose of this study is to leverage useful modules to achieve a lightweight and real-time image-dehazing model. Based on the U-Net architecture, this study integrates four modules, including an image pre-processing block, inception-like blocks, spatial pyramid pooling blocks, and attention gates. The original attention gate was revised to fit the field of image dehazing and consider different color spaces to retain the advantages of each color space. Furthermore, using an ablation study and a quantitative evaluation, the advantages of using these modules were illustrated. Through existing indoor and outdoor test datasets, the proposed method shows outstanding dehazing quality and an efficient execution time compared to other state-of-the-art methods. This study demonstrates that the proposed model can improve dehazing quality, keep the model lightweight, and obtain pleasing dehazing results. A comparison to existing methods using the RESIDE SOTS dataset revealed that the proposed model improves the <i>SSIM</i> and <i>PSNR</i> metrics by at least 5–10%.https://www.mdpi.com/2076-3417/12/13/6725single-image dehazingdeep learningattention gatelightweightreal-time |
| spellingShingle | Cheng-Ying Tsai Chieh-Li Chen Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing Applied Sciences single-image dehazing deep learning attention gate lightweight real-time |
| title | Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing |
| title_full | Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing |
| title_fullStr | Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing |
| title_full_unstemmed | Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing |
| title_short | Attention-Gate-Based Model with Inception-like Block for Single-Image Dehazing |
| title_sort | attention gate based model with inception like block for single image dehazing |
| topic | single-image dehazing deep learning attention gate lightweight real-time |
| url | https://www.mdpi.com/2076-3417/12/13/6725 |
| work_keys_str_mv | AT chengyingtsai attentiongatebasedmodelwithinceptionlikeblockforsingleimagedehazing AT chiehlichen attentiongatebasedmodelwithinceptionlikeblockforsingleimagedehazing |