Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms
Unmanned surface vehicles (USVs) are receiving increasing attention in recent years from both academia and industry. To make a high-level autonomy for USVs, the environment situational awareness is a key capability. However, due to the richness of the features in marine environments, as well as the...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/9/12/1329 |
_version_ | 1797503350046982144 |
---|---|
author | Haolin Xue Xiang Chen Ruo Zhang Peng Wu Xudong Li Yuanchang Liu |
author_facet | Haolin Xue Xiang Chen Ruo Zhang Peng Wu Xudong Li Yuanchang Liu |
author_sort | Haolin Xue |
collection | DOAJ |
description | Unmanned surface vehicles (USVs) are receiving increasing attention in recent years from both academia and industry. To make a high-level autonomy for USVs, the environment situational awareness is a key capability. However, due to the richness of the features in marine environments, as well as the complexity of the environment influenced by sun glare and sea fog, the development of a reliable situational awareness system remains a challenging problem that requires further studies. This paper, therefore, proposes a new deep semantic segmentation model together with a Simple Linear Iterative Clustering (SLIC) algorithm, for an accurate perception for various maritime environments. More specifically, powered by the SLIC algorithm, the new segmentation model can achieve refined results around obstacle edges and improved accuracy for water surface obstacle segmentation. The overall structure of the new model employs an encoder–decoder layout, and a superpixel refinement is embedded before final outputs. Three publicly available maritime image datasets are used in this paper to train and validate the segmentation model. The final output demonstrates that the proposed model can provide accurate results for obstacle segmentation. |
first_indexed | 2024-03-10T03:49:21Z |
format | Article |
id | doaj.art-fb08e39f78a647f5a17bc74fe4bddb8a |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-10T03:49:21Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-fb08e39f78a647f5a17bc74fe4bddb8a2023-11-23T09:02:09ZengMDPI AGJournal of Marine Science and Engineering2077-13122021-11-01912132910.3390/jmse9121329Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel AlgorithmsHaolin Xue0Xiang Chen1Ruo Zhang2Peng Wu3Xudong Li4Yuanchang Liu5Department of Mechanical Engineering, University College London, Torrington Place, London WC1E 7JE, UKDepartment of Civil, Environmental and Geomatic Engineering, University College London, Chadwick Building, London WC1E 6BT, UKShenzhen Research Institute, The Chinese University of Hong Kong, Shenzhen 518057, ChinaDepartment of Mechanical Engineering, University College London, Torrington Place, London WC1E 7JE, UKSchool of Mechanical Engineering, Dalian University of Technology, Dalian 116024, ChinaDepartment of Mechanical Engineering, University College London, Torrington Place, London WC1E 7JE, UKUnmanned surface vehicles (USVs) are receiving increasing attention in recent years from both academia and industry. To make a high-level autonomy for USVs, the environment situational awareness is a key capability. However, due to the richness of the features in marine environments, as well as the complexity of the environment influenced by sun glare and sea fog, the development of a reliable situational awareness system remains a challenging problem that requires further studies. This paper, therefore, proposes a new deep semantic segmentation model together with a Simple Linear Iterative Clustering (SLIC) algorithm, for an accurate perception for various maritime environments. More specifically, powered by the SLIC algorithm, the new segmentation model can achieve refined results around obstacle edges and improved accuracy for water surface obstacle segmentation. The overall structure of the new model employs an encoder–decoder layout, and a superpixel refinement is embedded before final outputs. Three publicly available maritime image datasets are used in this paper to train and validate the segmentation model. The final output demonstrates that the proposed model can provide accurate results for obstacle segmentation.https://www.mdpi.com/2077-1312/9/12/1329unmanned surface vehiclesimage segmentationdeep convolutional neural networksuperpixel algorithmmaritime image data |
spellingShingle | Haolin Xue Xiang Chen Ruo Zhang Peng Wu Xudong Li Yuanchang Liu Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms Journal of Marine Science and Engineering unmanned surface vehicles image segmentation deep convolutional neural network superpixel algorithm maritime image data |
title | Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms |
title_full | Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms |
title_fullStr | Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms |
title_full_unstemmed | Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms |
title_short | Deep Learning-Based Maritime Environment Segmentation for Unmanned Surface Vehicles Using Superpixel Algorithms |
title_sort | deep learning based maritime environment segmentation for unmanned surface vehicles using superpixel algorithms |
topic | unmanned surface vehicles image segmentation deep convolutional neural network superpixel algorithm maritime image data |
url | https://www.mdpi.com/2077-1312/9/12/1329 |
work_keys_str_mv | AT haolinxue deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms AT xiangchen deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms AT ruozhang deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms AT pengwu deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms AT xudongli deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms AT yuanchangliu deeplearningbasedmaritimeenvironmentsegmentationforunmannedsurfacevehiclesusingsuperpixelalgorithms |