A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze
This survey article is concerned with the emergence of vision augmentation AI tools for enhancing the situational awareness of first responders (FRs) in rescue operations. More specifically, the article surveys three families of image restoration methods serving the purpose of vision augmentation un...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/13/4707 |
| _version_ | 1797408251061469184 |
|---|---|
| author | Sotiris Karavarsamis Ioanna Gkika Vasileios Gkitsas Konstantinos Konstantoudakis Dimitrios Zarpalas |
| author_facet | Sotiris Karavarsamis Ioanna Gkika Vasileios Gkitsas Konstantinos Konstantoudakis Dimitrios Zarpalas |
| author_sort | Sotiris Karavarsamis |
| collection | DOAJ |
| description | This survey article is concerned with the emergence of vision augmentation AI tools for enhancing the situational awareness of first responders (FRs) in rescue operations. More specifically, the article surveys three families of image restoration methods serving the purpose of vision augmentation under adverse weather conditions. These image restoration methods are: (a) deraining; (b) desnowing; (c) dehazing ones. The contribution of this article is a survey of the recent literature on these three problem families, focusing on the utilization of deep learning (DL) models and meeting the requirements of their application in rescue operations. A faceted taxonomy is introduced in past and recent literature including various DL architectures, loss functions and datasets. Although there are multiple surveys on recovering images degraded by natural phenomena, the literature lacks a comprehensive survey focused explicitly on assisting FRs. This paper aims to fill this gap by presenting existing methods in the literature, assessing their suitability for FR applications, and providing insights for future research directions. |
| first_indexed | 2024-03-09T03:55:41Z |
| format | Article |
| id | doaj.art-89f4faf211b14eaeb21cbb11a3349ad7 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T03:55:41Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-89f4faf211b14eaeb21cbb11a3349ad72023-12-03T14:21:41ZengMDPI AGSensors1424-82202022-06-012213470710.3390/s22134707A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and HazeSotiris Karavarsamis0Ioanna Gkika1Vasileios Gkitsas2Konstantinos Konstantoudakis3Dimitrios Zarpalas4Visual Computing Lab, Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceVisual Computing Lab, Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceVisual Computing Lab, Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceVisual Computing Lab, Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceVisual Computing Lab, Information Technologies Institute, Centre for Research and Technology Hellas (CERTH), 57001 Thessaloniki, GreeceThis survey article is concerned with the emergence of vision augmentation AI tools for enhancing the situational awareness of first responders (FRs) in rescue operations. More specifically, the article surveys three families of image restoration methods serving the purpose of vision augmentation under adverse weather conditions. These image restoration methods are: (a) deraining; (b) desnowing; (c) dehazing ones. The contribution of this article is a survey of the recent literature on these three problem families, focusing on the utilization of deep learning (DL) models and meeting the requirements of their application in rescue operations. A faceted taxonomy is introduced in past and recent literature including various DL architectures, loss functions and datasets. Although there are multiple surveys on recovering images degraded by natural phenomena, the literature lacks a comprehensive survey focused explicitly on assisting FRs. This paper aims to fill this gap by presenting existing methods in the literature, assessing their suitability for FR applications, and providing insights for future research directions.https://www.mdpi.com/1424-8220/22/13/4707derainingdehazingdesnowingdeep learningdeep neural networks |
| spellingShingle | Sotiris Karavarsamis Ioanna Gkika Vasileios Gkitsas Konstantinos Konstantoudakis Dimitrios Zarpalas A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze Sensors deraining dehazing desnowing deep learning deep neural networks |
| title | A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze |
| title_full | A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze |
| title_fullStr | A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze |
| title_full_unstemmed | A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze |
| title_short | A Survey of Deep Learning-Based Image Restoration Methods for Enhancing Situational Awareness at Disaster Sites: The Cases of Rain, Snow and Haze |
| title_sort | survey of deep learning based image restoration methods for enhancing situational awareness at disaster sites the cases of rain snow and haze |
| topic | deraining dehazing desnowing deep learning deep neural networks |
| url | https://www.mdpi.com/1424-8220/22/13/4707 |
| work_keys_str_mv | AT sotiriskaravarsamis asurveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT ioannagkika asurveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT vasileiosgkitsas asurveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT konstantinoskonstantoudakis asurveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT dimitrioszarpalas asurveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT sotiriskaravarsamis surveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT ioannagkika surveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT vasileiosgkitsas surveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT konstantinoskonstantoudakis surveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze AT dimitrioszarpalas surveyofdeeplearningbasedimagerestorationmethodsforenhancingsituationalawarenessatdisastersitesthecasesofrainsnowandhaze |