Enhanced densely dehazing network for single image haze removal under railway scenes
Purpose – This paper aims to propose an enhanced densely dehazing network to suit railway scenes’ features and improve the visual quality degraded by haze and fog. Design/methodology/approach – It is an end-to-end network based on DenseNet. The authors design enhanced dense blocks and fuse them in a...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Emerald Publishing
2021-12-01
|
| Series: | Smart and Resilient Transportation |
| Subjects: | |
| Online Access: | https://www.emerald.com/insight/content/doi/10.1108/SRT-12-2020-0029/full/pdf?title=enhanced-densely-dehazing-network-for-single-image-haze-removal-under-railway-scenes |
| _version_ | 1828324487607615488 |
|---|---|
| author | Ruhao Zhao Xiaoping Ma He Zhang Honghui Dong Yong Qin Limin Jia |
| author_facet | Ruhao Zhao Xiaoping Ma He Zhang Honghui Dong Yong Qin Limin Jia |
| author_sort | Ruhao Zhao |
| collection | DOAJ |
| description | Purpose – This paper aims to propose an enhanced densely dehazing network to suit railway scenes’ features and improve the visual quality degraded by haze and fog. Design/methodology/approach – It is an end-to-end network based on DenseNet. The authors design enhanced dense blocks and fuse them in a pyramid pooling module for visual data’s local and global features. Multiple ablation studies have been conducted to show the effects of each module proposed in this paper. Findings – The authors have compared dehazed results on real hazy images and railway hazy images of state-of-the-art dehazing networks with the dehazed results in data quality. Finally, an object-detection test is taken to judge the edge information preservation after haze removal. All results demonstrate that the proposed dehazing network performs better under railway scenes in detail. Originality/value – This study provides a new method for image enhancing in the railway monitoring system. |
| first_indexed | 2024-04-13T19:07:40Z |
| format | Article |
| id | doaj.art-04aaa5ef78b94284b7a2249422bc63ee |
| institution | Directory Open Access Journal |
| issn | 2632-0495 |
| language | English |
| last_indexed | 2024-04-13T19:07:40Z |
| publishDate | 2021-12-01 |
| publisher | Emerald Publishing |
| record_format | Article |
| series | Smart and Resilient Transportation |
| spelling | doaj.art-04aaa5ef78b94284b7a2249422bc63ee2022-12-22T02:33:56ZengEmerald PublishingSmart and Resilient Transportation2632-04952021-12-013321823410.1108/SRT-12-2020-0029673020Enhanced densely dehazing network for single image haze removal under railway scenesRuhao Zhao0Xiaoping Ma1He Zhang2Honghui Dong3Yong Qin4Limin Jia5State Key Laboratory of Rail Traffic Control and Safety, Beijing, ChinaState Key Laboratory of Traffic Control and Safety, School of Traffic and Transportation, Beijing Jiaotong University, Beijing, ChinaRutgers, Piscataway, New Jersey, USAState Key Laboratory of Rail Traffic Control and Safety, Beijing, ChinaBeijing Jiaotong University, Beijing, ChinaBeijing Jiaotong University, Beijing, ChinaPurpose – This paper aims to propose an enhanced densely dehazing network to suit railway scenes’ features and improve the visual quality degraded by haze and fog. Design/methodology/approach – It is an end-to-end network based on DenseNet. The authors design enhanced dense blocks and fuse them in a pyramid pooling module for visual data’s local and global features. Multiple ablation studies have been conducted to show the effects of each module proposed in this paper. Findings – The authors have compared dehazed results on real hazy images and railway hazy images of state-of-the-art dehazing networks with the dehazed results in data quality. Finally, an object-detection test is taken to judge the edge information preservation after haze removal. All results demonstrate that the proposed dehazing network performs better under railway scenes in detail. Originality/value – This study provides a new method for image enhancing in the railway monitoring system.https://www.emerald.com/insight/content/doi/10.1108/SRT-12-2020-0029/full/pdf?title=enhanced-densely-dehazing-network-for-single-image-haze-removal-under-railway-scenesdeep learninghaze removalrailway intelligent transportation systemrailway monitoring system |
| spellingShingle | Ruhao Zhao Xiaoping Ma He Zhang Honghui Dong Yong Qin Limin Jia Enhanced densely dehazing network for single image haze removal under railway scenes Smart and Resilient Transportation deep learning haze removal railway intelligent transportation system railway monitoring system |
| title | Enhanced densely dehazing network for single image haze removal under railway scenes |
| title_full | Enhanced densely dehazing network for single image haze removal under railway scenes |
| title_fullStr | Enhanced densely dehazing network for single image haze removal under railway scenes |
| title_full_unstemmed | Enhanced densely dehazing network for single image haze removal under railway scenes |
| title_short | Enhanced densely dehazing network for single image haze removal under railway scenes |
| title_sort | enhanced densely dehazing network for single image haze removal under railway scenes |
| topic | deep learning haze removal railway intelligent transportation system railway monitoring system |
| url | https://www.emerald.com/insight/content/doi/10.1108/SRT-12-2020-0029/full/pdf?title=enhanced-densely-dehazing-network-for-single-image-haze-removal-under-railway-scenes |
| work_keys_str_mv | AT ruhaozhao enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes AT xiaopingma enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes AT hezhang enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes AT honghuidong enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes AT yongqin enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes AT liminjia enhanceddenselydehazingnetworkforsingleimagehazeremovalunderrailwayscenes |