Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images
Dehazing has emerged as a promising technology to recover the clear image from an input hazy image, such that the image quality can be significantly enhanced. However, it is still an open issue to quantitatively evaluate the performance of existing dehazing algorithms. To fill in this gap, we propos...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8329966/ |
| _version_ | 1818331980127797248 |
|---|---|
| author | Keyan Wang Hui Wang Yufei Li Yan Hu Yunsong Li |
| author_facet | Keyan Wang Hui Wang Yufei Li Yan Hu Yunsong Li |
| author_sort | Keyan Wang |
| collection | DOAJ |
| description | Dehazing has emerged as a promising technology to recover the clear image from an input hazy image, such that the image quality can be significantly enhanced. However, it is still an open issue to quantitatively evaluate the performance of existing dehazing algorithms. To fill in this gap, we propose an effective performance evaluation method for image dehazing by exploiting synthetic outdoor hazy images dataset. To be specific, we first synthesize hazes on the original haze-free images to approximate the realworld hazy scenes. A dataset that contains original images, synthetic hazy images, estimated depth maps, and transmission maps of the same scene is then established. Due to the fact that the generation of the synthetic hazy images is based on the physical model which is strongly related to the depth information, an effective depth estimation method that combines the geometry and edge information is proposed. With the estimated depth map, we are able to create a corresponding hazy scene with high fidelity. Numerous experiments are conducted to verify the consistency of subjective and objective evaluation of the proposed method. |
| first_indexed | 2024-12-13T13:28:28Z |
| format | Article |
| id | doaj.art-4d67a6333e694344b087852c21d0eda8 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-13T13:28:28Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-4d67a6333e694344b087852c21d0eda82022-12-21T23:44:13ZengIEEEIEEE Access2169-35362018-01-016204812049610.1109/ACCESS.2018.28227758329966Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy ImagesKeyan Wang0https://orcid.org/0000-0002-9545-718XHui Wang1Yufei Li2Yan Hu3Yunsong Li4State Key Laboratory of Integrated Service Networks, Xidian University, Xi’an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi’an, ChinaNorthwest Electric Power Design Institute, Xi’an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi’an, ChinaState Key Laboratory of Integrated Service Networks, Xidian University, Xi’an, ChinaDehazing has emerged as a promising technology to recover the clear image from an input hazy image, such that the image quality can be significantly enhanced. However, it is still an open issue to quantitatively evaluate the performance of existing dehazing algorithms. To fill in this gap, we propose an effective performance evaluation method for image dehazing by exploiting synthetic outdoor hazy images dataset. To be specific, we first synthesize hazes on the original haze-free images to approximate the realworld hazy scenes. A dataset that contains original images, synthetic hazy images, estimated depth maps, and transmission maps of the same scene is then established. Due to the fact that the generation of the synthetic hazy images is based on the physical model which is strongly related to the depth information, an effective depth estimation method that combines the geometry and edge information is proposed. With the estimated depth map, we are able to create a corresponding hazy scene with high fidelity. Numerous experiments are conducted to verify the consistency of subjective and objective evaluation of the proposed method.https://ieeexplore.ieee.org/document/8329966/Dehazingestimated depth mapsimage quality evaluationsynthetic hazy images |
| spellingShingle | Keyan Wang Hui Wang Yufei Li Yan Hu Yunsong Li Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images IEEE Access Dehazing estimated depth maps image quality evaluation synthetic hazy images |
| title | Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images |
| title_full | Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images |
| title_fullStr | Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images |
| title_full_unstemmed | Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images |
| title_short | Quantitative Performance Evaluation for Dehazing Algorithms on Synthetic Outdoor Hazy Images |
| title_sort | quantitative performance evaluation for dehazing algorithms on synthetic outdoor hazy images |
| topic | Dehazing estimated depth maps image quality evaluation synthetic hazy images |
| url | https://ieeexplore.ieee.org/document/8329966/ |
| work_keys_str_mv | AT keyanwang quantitativeperformanceevaluationfordehazingalgorithmsonsyntheticoutdoorhazyimages AT huiwang quantitativeperformanceevaluationfordehazingalgorithmsonsyntheticoutdoorhazyimages AT yufeili quantitativeperformanceevaluationfordehazingalgorithmsonsyntheticoutdoorhazyimages AT yanhu quantitativeperformanceevaluationfordehazingalgorithmsonsyntheticoutdoorhazyimages AT yunsongli quantitativeperformanceevaluationfordehazingalgorithmsonsyntheticoutdoorhazyimages |