Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm

Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm

Image-based sensing of jellyfish is important as they can cause great damage to the fisheries and seaside facilities and need to be properly controlled. In this paper, we present a deep-learning-based technique to generate a synthetic image of the jellyfish easily with autoencoder-combined generativ...

Full description

Bibliographic Details
Main Authors: Kyukwang Kim, Hyun Myung
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Autoencoder
generative adversarial networks
jellyfish swarm
fully convolutional network
regression
Online Access:https://ieeexplore.ieee.org/document/8471171/
id doaj-1735d32a7bbc46eb8860d715a1568c1c
record_format Article
spelling doaj-1735d32a7bbc46eb8860d715a1568c1c2021-03-29T21:14:58ZengIEEEIEEE Access2169-35362018-01-016542075421410.1109/ACCESS.2018.28720258471171Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish SwarmKyukwang Kim0Hyun Myung1https://orcid.org/0000-0002-5799-2026Urban Robotics Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaUrban Robotics Laboratory, Korea Advanced Institute of Science and Technology, Daejeon, South KoreaImage-based sensing of jellyfish is important as they can cause great damage to the fisheries and seaside facilities and need to be properly controlled. In this paper, we present a deep-learning-based technique to generate a synthetic image of the jellyfish easily with autoencoder-combined generative adversarial networks. The proposed system can easily generate simple images with a smaller number of data sets compared with other generative networks. The generated output showed high similarity with the real-image data set. The application using a fully convolutional network and regression network to estimate the size of the jellyfish swarm was also demonstrated, and showed high accuracy during the estimation test.https://ieeexplore.ieee.org/document/8471171/Autoencodergenerative adversarial networksjellyfish swarmfully convolutional networkregression
collection DOAJ
language English
format Article
sources DOAJ
author Kyukwang Kim
Hyun Myung
spellingShingle Kyukwang Kim
Hyun Myung
Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
IEEE Access
Autoencoder
generative adversarial networks
jellyfish swarm
fully convolutional network
regression
author_facet Kyukwang Kim
Hyun Myung
author_sort Kyukwang Kim
title Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
title_short Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
title_full Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
title_fullStr Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
title_full_unstemmed Autoencoder-Combined Generative Adversarial Networks for Synthetic Image Data Generation and Detection of Jellyfish Swarm
title_sort autoencoder-combined generative adversarial networks for synthetic image data generation and detection of jellyfish swarm
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2018-01-01
description Image-based sensing of jellyfish is important as they can cause great damage to the fisheries and seaside facilities and need to be properly controlled. In this paper, we present a deep-learning-based technique to generate a synthetic image of the jellyfish easily with autoencoder-combined generative adversarial networks. The proposed system can easily generate simple images with a smaller number of data sets compared with other generative networks. The generated output showed high similarity with the real-image data set. The application using a fully convolutional network and regression network to estimate the size of the jellyfish swarm was also demonstrated, and showed high accuracy during the estimation test.
topic Autoencoder
generative adversarial networks
jellyfish swarm
fully convolutional network
regression
url https://ieeexplore.ieee.org/document/8471171/
work_keys_str_mv AT kyukwangkim autoencodercombinedgenerativeadversarialnetworksforsyntheticimagedatagenerationanddetectionofjellyfishswarm
AT hyunmyung autoencodercombinedgenerativeadversarialnetworksforsyntheticimagedatagenerationanddetectionofjellyfishswarm
_version_ 1724193274993836032

Similar Items