Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks
Rapid developments in urbanization and smart city environments have accelerated the need to deliver safe, sustainable, and effective resource utilization and service provision and have thereby enhanced the need for intelligent, real-time video surveillance. Recent advances in machine learning and de...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/5/2214 |
| _version_ | 1797415477291515904 |
|---|---|
| author | Prasad Hettiarachchi Rashmika Nawaratne Damminda Alahakoon Daswin De Silva Naveen Chilamkurti |
| author_facet | Prasad Hettiarachchi Rashmika Nawaratne Damminda Alahakoon Daswin De Silva Naveen Chilamkurti |
| author_sort | Prasad Hettiarachchi |
| collection | DOAJ |
| description | Rapid developments in urbanization and smart city environments have accelerated the need to deliver safe, sustainable, and effective resource utilization and service provision and have thereby enhanced the need for intelligent, real-time video surveillance. Recent advances in machine learning and deep learning have the capability to detect and localize salient objects in surveillance video streams; however, several practical issues remain unaddressed, such as diverse weather conditions, recording conditions, and motion blur. In this context, image de-raining is an important issue that has been investigated extensively in recent years to provide accurate and quality surveillance in the smart city domain. Existing deep convolutional neural networks have obtained great success in image translation and other computer vision tasks; however, image de-raining is ill posed and has not been addressed in real-time, intelligent video surveillance systems. In this work, we propose to utilize the generative capabilities of recently introduced conditional generative adversarial networks (cGANs) as an image de-raining approach. We utilize the adversarial loss in GANs that provides an additional component to the loss function, which in turn regulates the final output and helps to yield better results. Experiments on both real and synthetic data show that the proposed method outperforms most of the existing state-of-the-art models in terms of quantitative evaluations and visual appearance. |
| first_indexed | 2024-03-09T05:49:11Z |
| format | Article |
| id | doaj.art-769c4f21074140609bc25b5c0e291335 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T05:49:11Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-769c4f21074140609bc25b5c0e2913352023-12-03T12:18:26ZengMDPI AGApplied Sciences2076-34172021-03-01115221410.3390/app11052214Rain Streak Removal for Single Images Using Conditional Generative Adversarial NetworksPrasad Hettiarachchi0Rashmika Nawaratne1Damminda Alahakoon2Daswin De Silva3Naveen Chilamkurti4Research Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, AustraliaResearch Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, AustraliaResearch Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, AustraliaResearch Centre for Data Analytics and Cognition, La Trobe University, Melbourne, VIC 3086, AustraliaDepartment of Computer Science and Information Technology, La Trobe University, Melbourne, VIC 3086, AustraliaRapid developments in urbanization and smart city environments have accelerated the need to deliver safe, sustainable, and effective resource utilization and service provision and have thereby enhanced the need for intelligent, real-time video surveillance. Recent advances in machine learning and deep learning have the capability to detect and localize salient objects in surveillance video streams; however, several practical issues remain unaddressed, such as diverse weather conditions, recording conditions, and motion blur. In this context, image de-raining is an important issue that has been investigated extensively in recent years to provide accurate and quality surveillance in the smart city domain. Existing deep convolutional neural networks have obtained great success in image translation and other computer vision tasks; however, image de-raining is ill posed and has not been addressed in real-time, intelligent video surveillance systems. In this work, we propose to utilize the generative capabilities of recently introduced conditional generative adversarial networks (cGANs) as an image de-raining approach. We utilize the adversarial loss in GANs that provides an additional component to the loss function, which in turn regulates the final output and helps to yield better results. Experiments on both real and synthetic data show that the proposed method outperforms most of the existing state-of-the-art models in terms of quantitative evaluations and visual appearance.https://www.mdpi.com/2076-3417/11/5/2214deep learninggenerative adversarial networkstraffic surveillance image processingimage de-raining |
| spellingShingle | Prasad Hettiarachchi Rashmika Nawaratne Damminda Alahakoon Daswin De Silva Naveen Chilamkurti Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks Applied Sciences deep learning generative adversarial networks traffic surveillance image processing image de-raining |
| title | Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks |
| title_full | Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks |
| title_fullStr | Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks |
| title_full_unstemmed | Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks |
| title_short | Rain Streak Removal for Single Images Using Conditional Generative Adversarial Networks |
| title_sort | rain streak removal for single images using conditional generative adversarial networks |
| topic | deep learning generative adversarial networks traffic surveillance image processing image de-raining |
| url | https://www.mdpi.com/2076-3417/11/5/2214 |
| work_keys_str_mv | AT prasadhettiarachchi rainstreakremovalforsingleimagesusingconditionalgenerativeadversarialnetworks AT rashmikanawaratne rainstreakremovalforsingleimagesusingconditionalgenerativeadversarialnetworks AT dammindaalahakoon rainstreakremovalforsingleimagesusingconditionalgenerativeadversarialnetworks AT daswindesilva rainstreakremovalforsingleimagesusingconditionalgenerativeadversarialnetworks AT naveenchilamkurti rainstreakremovalforsingleimagesusingconditionalgenerativeadversarialnetworks |