Rain density classification guides the expansion network for rain removal from a single images
Since the rain line stripes in the image have different shapes and sizes and are unevenly distributed, the rain density of the single neural network learning uneven distribution is weak, and the rain removal effect is not significant. This paper proposes a rain density sensing guide expansion networ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
National Computer System Engineering Research Institute of China
2019-02-01
|
| Series: | Dianzi Jishu Yingyong |
| Subjects: | |
| Online Access: | http://www.chinaaet.com/article/3000097262 |
| _version_ | 1818041241579814912 |
|---|---|
| author | An Henan Zhang Changlin Tu Zhiwei Zhao Guangjun Liu Jia Li Wei |
| author_facet | An Henan Zhang Changlin Tu Zhiwei Zhao Guangjun Liu Jia Li Wei |
| author_sort | An Henan |
| collection | DOAJ |
| description | Since the rain line stripes in the image have different shapes and sizes and are unevenly distributed, the rain density of the single neural network learning uneven distribution is weak, and the rain removal effect is not significant. This paper proposes a rain density sensing guide expansion network to remove rain from a single images. The network is divided into two parts. The first part is the rain density perception network classifying the images of different density rains(Heavy rain, Medium rain, Light rain). The second part is the expansion network guided by the joint rain density perception classification information learning different rain density characteristics details for detecting rain lines and removing rain. Experiments show the effectiveness of the method in the de-rain on synthetic and real data sets. |
| first_indexed | 2024-12-10T08:27:18Z |
| format | Article |
| id | doaj.art-9141de86a04a420fa7f33b4a8a9e9d3f |
| institution | Directory Open Access Journal |
| issn | 0258-7998 |
| language | zho |
| last_indexed | 2024-12-10T08:27:18Z |
| publishDate | 2019-02-01 |
| publisher | National Computer System Engineering Research Institute of China |
| record_format | Article |
| series | Dianzi Jishu Yingyong |
| spelling | doaj.art-9141de86a04a420fa7f33b4a8a9e9d3f2022-12-22T01:56:12ZzhoNational Computer System Engineering Research Institute of ChinaDianzi Jishu Yingyong0258-79982019-02-014521410.16157/j.issn.0258-7998.1833133000097262Rain density classification guides the expansion network for rain removal from a single imagesAn Henan0Zhang Changlin1Tu Zhiwei2Zhao Guangjun3Liu Jia4Li Wei5School of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSchool of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSchool of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSchool of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSchool of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSchool of Electronic Science and Technology，Shenzhen University，Shenzhen 518061，ChinaSince the rain line stripes in the image have different shapes and sizes and are unevenly distributed, the rain density of the single neural network learning uneven distribution is weak, and the rain removal effect is not significant. This paper proposes a rain density sensing guide expansion network to remove rain from a single images. The network is divided into two parts. The first part is the rain density perception network classifying the images of different density rains(Heavy rain, Medium rain, Light rain). The second part is the expansion network guided by the joint rain density perception classification information learning different rain density characteristics details for detecting rain lines and removing rain. Experiments show the effectiveness of the method in the de-rain on synthetic and real data sets.http://www.chinaaet.com/article/3000097262single imagesrain density classification networkexpansion networkde-rain |
| spellingShingle | An Henan Zhang Changlin Tu Zhiwei Zhao Guangjun Liu Jia Li Wei Rain density classification guides the expansion network for rain removal from a single images Dianzi Jishu Yingyong single images rain density classification network expansion network de-rain |
| title | Rain density classification guides the expansion network for rain removal from a single images |
| title_full | Rain density classification guides the expansion network for rain removal from a single images |
| title_fullStr | Rain density classification guides the expansion network for rain removal from a single images |
| title_full_unstemmed | Rain density classification guides the expansion network for rain removal from a single images |
| title_short | Rain density classification guides the expansion network for rain removal from a single images |
| title_sort | rain density classification guides the expansion network for rain removal from a single images |
| topic | single images rain density classification network expansion network de-rain |
| url | http://www.chinaaet.com/article/3000097262 |
| work_keys_str_mv | AT anhenan raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages AT zhangchanglin raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages AT tuzhiwei raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages AT zhaoguangjun raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages AT liujia raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages AT liwei raindensityclassificationguidestheexpansionnetworkforrainremovalfromasingleimages |