Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection
Camera-based blind-spot detection systems improve the shortcomings of radar-based systems for accurately detecting the position of a vehicle. However, as with many camera-based applications, the detection performance is insufficient in a low-illumination environment such as at night. This problem ca...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9027878/ |
id |
doaj-1dedf73d84db4ad4a51937c131afa0a6 |
---|---|
record_format |
Article |
spelling |
doaj-1dedf73d84db4ad4a51937c131afa0a62021-03-30T01:27:40ZengIEEEIEEE Access2169-35362020-01-018480494805910.1109/ACCESS.2020.29792399027878Nighttime Data Augmentation Using GAN for Improving Blind-Spot DetectionHongjun Lee0https://orcid.org/0000-0003-4431-5090Moonsoo Ra1https://orcid.org/0000-0003-4587-1136Whoi-Yul Kim2https://orcid.org/0000-0003-0320-1409Department of Electronics and Computer Engineering, Hanyang University, Seoul, South KoreaLightVision Inc., Seoul, South KoreaDepartment of Electronics and Computer Engineering, Hanyang University, Seoul, South KoreaCamera-based blind-spot detection systems improve the shortcomings of radar-based systems for accurately detecting the position of a vehicle. However, as with many camera-based applications, the detection performance is insufficient in a low-illumination environment such as at night. This problem can be solved with augmented nighttime images in the training data but acquiring them and annotating the additional images are cumbersome tasks. Therefore, we propose a framework that converts daytime images into synthetic nighttime images using a generative adversarial network and that augments the synthetic images for the training process of the vehicle detector. A public dataset comprising different viewpoints of target images was used to easily obtain the images required for training the generative adversarial network. Experiments on a real nighttime dataset demonstrate that the proposed framework improved the detection performance considerably in comparison with using daytime images only.https://ieeexplore.ieee.org/document/9027878/Data augmentationdomain adaptationgenerative adversarial networksblind-spot detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hongjun Lee Moonsoo Ra Whoi-Yul Kim |
spellingShingle |
Hongjun Lee Moonsoo Ra Whoi-Yul Kim Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection IEEE Access Data augmentation domain adaptation generative adversarial networks blind-spot detection |
author_facet |
Hongjun Lee Moonsoo Ra Whoi-Yul Kim |
author_sort |
Hongjun Lee |
title |
Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection |
title_short |
Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection |
title_full |
Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection |
title_fullStr |
Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection |
title_full_unstemmed |
Nighttime Data Augmentation Using GAN for Improving Blind-Spot Detection |
title_sort |
nighttime data augmentation using gan for improving blind-spot detection |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Camera-based blind-spot detection systems improve the shortcomings of radar-based systems for accurately detecting the position of a vehicle. However, as with many camera-based applications, the detection performance is insufficient in a low-illumination environment such as at night. This problem can be solved with augmented nighttime images in the training data but acquiring them and annotating the additional images are cumbersome tasks. Therefore, we propose a framework that converts daytime images into synthetic nighttime images using a generative adversarial network and that augments the synthetic images for the training process of the vehicle detector. A public dataset comprising different viewpoints of target images was used to easily obtain the images required for training the generative adversarial network. Experiments on a real nighttime dataset demonstrate that the proposed framework improved the detection performance considerably in comparison with using daytime images only. |
topic |
Data augmentation domain adaptation generative adversarial networks blind-spot detection |
url |
https://ieeexplore.ieee.org/document/9027878/ |
work_keys_str_mv |
AT hongjunlee nighttimedataaugmentationusingganforimprovingblindspotdetection AT moonsoora nighttimedataaugmentationusingganforimprovingblindspotdetection AT whoiyulkim nighttimedataaugmentationusingganforimprovingblindspotdetection |
_version_ |
1724186990644035584 |