Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

4 Downloads (Pure)

Resumé

In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms have been developed that artificially remove rain streaks from images or video. In order to deploy such rain removal algorithms in a surveillance setting, one must detect if rain is present in the scene. In this paper, we design a system for the detection of rainfall by the use of surveillance cameras. We reimplement the former state-of-the-art method for rain detection and compare it against a modern CNN-based method by utilizing 3D convolutions. The two methods are evaluated on our new AAU Visual Rain Dataset (VIRADA) that consists of 215 hours of general-purpose surveillance video from two traffic crossings. The results show that the proposed 3D CNN outperforms the previous state-of-the-art method by a large margin on all metrics, for both of the traffic crossings. Finally, it is shown that the choice of region-of-interest has a large influence on performance when trying to generalize the investigated methods. The AAU VIRADA dataset and our implementation of the two rain detection algorithms are publicly available at https://bitbucket.org/aauvap/aau-virada
OriginalsprogEngelsk
TitelIEEE Conference on Computer Vision and Pattern Recognition Workshops
Publikationsdatojun. 2019
StatusAccepteret/In press - jun. 2019

Fingerprint

Rain
Cameras
Convolution

Citer dette

Haurum, J. B., Bahnsen, C. H., & Moeslund, T. B. (Accepteret/In press). Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras. I IEEE Conference on Computer Vision and Pattern Recognition Workshops
@inproceedings{1eadb5daaf85416a8b40875d3e9d660e,
title = "Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras",
abstract = "In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms have been developed that artificially remove rain streaks from images or video. In order to deploy such rain removal algorithms in a surveillance setting, one must detect if rain is present in the scene. In this paper, we design a system for the detection of rainfall by the use of surveillance cameras. We reimplement the former state-of-the-art method for rain detection and compare it against a modern CNN-based method by utilizing 3D convolutions. The two methods are evaluated on our new AAU Visual Rain Dataset (VIRADA) that consists of 215 hours of general-purpose surveillance video from two traffic crossings. The results show that the proposed 3D CNN outperforms the previous state-of-the-art method by a large margin on all metrics, for both of the traffic crossings. Finally, it is shown that the choice of region-of-interest has a large influence on performance when trying to generalize the investigated methods. The AAU VIRADA dataset and our implementation of the two rain detection algorithms are publicly available at https://bitbucket.org/aauvap/aau-virada",
author = "Haurum, {Joakim Bruslund} and Bahnsen, {Chris Holmberg} and Moeslund, {Thomas B.}",
year = "2019",
month = "6",
language = "English",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition Workshops",

}

Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras. / Haurum, Joakim Bruslund; Bahnsen, Chris Holmberg; Moeslund, Thomas B.

IEEE Conference on Computer Vision and Pattern Recognition Workshops. 2019.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Is it Raining Outside? Detection of Rainfall using General-Purpose Surveillance Cameras

AU - Haurum, Joakim Bruslund

AU - Bahnsen, Chris Holmberg

AU - Moeslund, Thomas B.

PY - 2019/6

Y1 - 2019/6

N2 - In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms have been developed that artificially remove rain streaks from images or video. In order to deploy such rain removal algorithms in a surveillance setting, one must detect if rain is present in the scene. In this paper, we design a system for the detection of rainfall by the use of surveillance cameras. We reimplement the former state-of-the-art method for rain detection and compare it against a modern CNN-based method by utilizing 3D convolutions. The two methods are evaluated on our new AAU Visual Rain Dataset (VIRADA) that consists of 215 hours of general-purpose surveillance video from two traffic crossings. The results show that the proposed 3D CNN outperforms the previous state-of-the-art method by a large margin on all metrics, for both of the traffic crossings. Finally, it is shown that the choice of region-of-interest has a large influence on performance when trying to generalize the investigated methods. The AAU VIRADA dataset and our implementation of the two rain detection algorithms are publicly available at https://bitbucket.org/aauvap/aau-virada

AB - In integrated surveillance systems based on visual cameras, the mitigation of adverse weather conditions is an active research topic. Within this field, rain removal algorithms have been developed that artificially remove rain streaks from images or video. In order to deploy such rain removal algorithms in a surveillance setting, one must detect if rain is present in the scene. In this paper, we design a system for the detection of rainfall by the use of surveillance cameras. We reimplement the former state-of-the-art method for rain detection and compare it against a modern CNN-based method by utilizing 3D convolutions. The two methods are evaluated on our new AAU Visual Rain Dataset (VIRADA) that consists of 215 hours of general-purpose surveillance video from two traffic crossings. The results show that the proposed 3D CNN outperforms the previous state-of-the-art method by a large margin on all metrics, for both of the traffic crossings. Finally, it is shown that the choice of region-of-interest has a large influence on performance when trying to generalize the investigated methods. The AAU VIRADA dataset and our implementation of the two rain detection algorithms are publicly available at https://bitbucket.org/aauvap/aau-virada

M3 - Article in proceeding

BT - IEEE Conference on Computer Vision and Pattern Recognition Workshops

ER -