Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering
Outdoor vision sensing systems often struggle with poor weather conditions, such as snow and rain, which poses a great challenge to existing video desnowing and deraining methods. In this paper, we propose a novel video desnowing and deraining model that utilizes the salience information of moving o...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7610 |
| _version_ | 1827675390776180736 |
|---|---|
| author | Yongji Li Rui Wu Zhenhong Jia Jie Yang Nikola Kasabov |
| author_facet | Yongji Li Rui Wu Zhenhong Jia Jie Yang Nikola Kasabov |
| author_sort | Yongji Li |
| collection | DOAJ |
| description | Outdoor vision sensing systems often struggle with poor weather conditions, such as snow and rain, which poses a great challenge to existing video desnowing and deraining methods. In this paper, we propose a novel video desnowing and deraining model that utilizes the salience information of moving objects to address this problem. First, we remove the snow and rain from the video by low-rank tensor decomposition, which makes full use of the spatial location information and the correlation between the three channels of the color video. Second, because existing algorithms often regard sparse snowflakes and rain streaks as moving objects, this paper injects salience information into moving object detection, which reduces the false alarms and missed alarms of moving objects. At the same time, feature point matching is used to mine the redundant information of moving objects in continuous frames, and a dual adaptive minimum filtering algorithm in the spatiotemporal domain is proposed by us to remove snow and rain in front of moving objects. Both qualitative and quantitative experimental results show that the proposed algorithm is more competitive than other state-of-the-art snow and rain removal methods. |
| first_indexed | 2024-03-10T05:05:19Z |
| format | Article |
| id | doaj.art-bb63851914f24511a274e56c719da2b8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:05:19Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bb63851914f24511a274e56c719da2b82023-11-23T01:26:46ZengMDPI AGSensors1424-82202021-11-012122761010.3390/s21227610Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal FilteringYongji Li0Rui Wu1Zhenhong Jia2Jie Yang3Nikola Kasabov4College of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaInstitute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai 200400, ChinaKnowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1020, New ZealandOutdoor vision sensing systems often struggle with poor weather conditions, such as snow and rain, which poses a great challenge to existing video desnowing and deraining methods. In this paper, we propose a novel video desnowing and deraining model that utilizes the salience information of moving objects to address this problem. First, we remove the snow and rain from the video by low-rank tensor decomposition, which makes full use of the spatial location information and the correlation between the three channels of the color video. Second, because existing algorithms often regard sparse snowflakes and rain streaks as moving objects, this paper injects salience information into moving object detection, which reduces the false alarms and missed alarms of moving objects. At the same time, feature point matching is used to mine the redundant information of moving objects in continuous frames, and a dual adaptive minimum filtering algorithm in the spatiotemporal domain is proposed by us to remove snow and rain in front of moving objects. Both qualitative and quantitative experimental results show that the proposed algorithm is more competitive than other state-of-the-art snow and rain removal methods.https://www.mdpi.com/1424-8220/21/22/7610video desnowing and derainingsaliencyadaptive filteringoutdoor vision sensing |
| spellingShingle | Yongji Li Rui Wu Zhenhong Jia Jie Yang Nikola Kasabov Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering Sensors video desnowing and deraining saliency adaptive filtering outdoor vision sensing |
| title | Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering |
| title_full | Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering |
| title_fullStr | Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering |
| title_full_unstemmed | Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering |
| title_short | Video Desnowing and Deraining via Saliency and Dual Adaptive Spatiotemporal Filtering |
| title_sort | video desnowing and deraining via saliency and dual adaptive spatiotemporal filtering |
| topic | video desnowing and deraining saliency adaptive filtering outdoor vision sensing |
| url | https://www.mdpi.com/1424-8220/21/22/7610 |
| work_keys_str_mv | AT yongjili videodesnowingandderainingviasaliencyanddualadaptivespatiotemporalfiltering AT ruiwu videodesnowingandderainingviasaliencyanddualadaptivespatiotemporalfiltering AT zhenhongjia videodesnowingandderainingviasaliencyanddualadaptivespatiotemporalfiltering AT jieyang videodesnowingandderainingviasaliencyanddualadaptivespatiotemporalfiltering AT nikolakasabov videodesnowingandderainingviasaliencyanddualadaptivespatiotemporalfiltering |