Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications
This research addresses visibility challenges in surveillance systems under foggy conditions through a novel synthetic fog generation method leveraging the GridNet dehazing architecture. Our approach uniquely reverses GridNet, originally developed for fog removal, to synthesize realistic foggy image...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/12/6503 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849433432230199296 |
|---|---|
| author | Heekwon Lee Byeongseon Park Yong-Kab Kim Sungkwan Youm |
| author_facet | Heekwon Lee Byeongseon Park Yong-Kab Kim Sungkwan Youm |
| author_sort | Heekwon Lee |
| collection | DOAJ |
| description | This research addresses visibility challenges in surveillance systems under foggy conditions through a novel synthetic fog generation method leveraging the GridNet dehazing architecture. Our approach uniquely reverses GridNet, originally developed for fog removal, to synthesize realistic foggy images. The proposed Fog Generator Model incorporates perceptual and dark channel consistency losses to enhance fog realism and structural consistency. Comparative experiments on the O-HAZY dataset demonstrate that dehazing models trained on our synthetic fog outperform those trained on conventional methods, achieving superior Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores. These findings confirm that integrating high-performance dehazing networks into fog synthesis improves the realism and effectiveness of fog removal solutions, offering significant benefits for real-world surveillance applications. |
| format | Article |
| id | doaj-art-6f6efa15ad50479b947bd943c8390dd5 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-6f6efa15ad50479b947bd943c8390dd52025-08-20T03:27:02ZengMDPI AGApplied Sciences2076-34172025-06-011512650310.3390/app15126503Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance ApplicationsHeekwon Lee0Byeongseon Park1Yong-Kab Kim2Sungkwan Youm3Department of Information & Communication Engineering Department, Wonkwang University, Iksan 54538, Republic of KoreaDepartment of Information & Communication Engineering Department, Wonkwang University, Iksan 54538, Republic of KoreaDepartment of Information & Communication Engineering Department, Wonkwang University, Iksan 54538, Republic of KoreaDepartment of Information & Communication Engineering Department, Wonkwang University, Iksan 54538, Republic of KoreaThis research addresses visibility challenges in surveillance systems under foggy conditions through a novel synthetic fog generation method leveraging the GridNet dehazing architecture. Our approach uniquely reverses GridNet, originally developed for fog removal, to synthesize realistic foggy images. The proposed Fog Generator Model incorporates perceptual and dark channel consistency losses to enhance fog realism and structural consistency. Comparative experiments on the O-HAZY dataset demonstrate that dehazing models trained on our synthetic fog outperform those trained on conventional methods, achieving superior Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores. These findings confirm that integrating high-performance dehazing networks into fog synthesis improves the realism and effectiveness of fog removal solutions, offering significant benefits for real-world surveillance applications.https://www.mdpi.com/2076-3417/15/12/6503synthetic fog generationimage dehazingsurveillance systemsGridNetdeep learningfog removal |
| spellingShingle | Heekwon Lee Byeongseon Park Yong-Kab Kim Sungkwan Youm Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications Applied Sciences synthetic fog generation image dehazing surveillance systems GridNet deep learning fog removal |
| title | Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications |
| title_full | Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications |
| title_fullStr | Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications |
| title_full_unstemmed | Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications |
| title_short | Synthetic Fog Generation Using High-Performance Dehazing Networks for Surveillance Applications |
| title_sort | synthetic fog generation using high performance dehazing networks for surveillance applications |
| topic | synthetic fog generation image dehazing surveillance systems GridNet deep learning fog removal |
| url | https://www.mdpi.com/2076-3417/15/12/6503 |
| work_keys_str_mv | AT heekwonlee syntheticfoggenerationusinghighperformancedehazingnetworksforsurveillanceapplications AT byeongseonpark syntheticfoggenerationusinghighperformancedehazingnetworksforsurveillanceapplications AT yongkabkim syntheticfoggenerationusinghighperformancedehazingnetworksforsurveillanceapplications AT sungkwanyoum syntheticfoggenerationusinghighperformancedehazingnetworksforsurveillanceapplications |