Monocular Vision-Based Underwater Object Detection
In this paper, we propose an underwater object detection method using monocular vision sensors. In addition to commonly used visual features such as color and intensity, we investigate the potential of underwater object detection using light transmission information. The global contrast of various f...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2017-08-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/17/8/1784 |
id |
doaj-b44d297e5bbd4949b6c23e9bc5af4d8b |
---|---|
record_format |
Article |
spelling |
doaj-b44d297e5bbd4949b6c23e9bc5af4d8b2020-11-24T23:19:45ZengMDPI AGSensors1424-82202017-08-01178178410.3390/s17081784s17081784Monocular Vision-Based Underwater Object DetectionZhe Chen0Zhen Zhang1Fengzhao Dai2Yang Bu3Huibin Wang4College of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, ChinaCollege of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, ChinaLaboratory of Information Optics and Opto-Electronic Technology, Shanghai Institute of Optics and Fine Mechanics, Shanghai 201800, ChinaLaboratory of Information Optics and Opto-Electronic Technology, Shanghai Institute of Optics and Fine Mechanics, Shanghai 201800, ChinaCollege of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, ChinaIn this paper, we propose an underwater object detection method using monocular vision sensors. In addition to commonly used visual features such as color and intensity, we investigate the potential of underwater object detection using light transmission information. The global contrast of various features is used to initially identify the region of interest (ROI), which is then filtered by the image segmentation method, producing the final underwater object detection results. We test the performance of our method with diverse underwater datasets. Samples of the datasets are acquired by a monocular camera with different qualities (such as resolution and focal length) and setups (viewing distance, viewing angle, and optical environment). It is demonstrated that our ROI detection method is necessary and can largely remove the background noise and significantly increase the accuracy of our underwater object detection method.https://www.mdpi.com/1424-8220/17/8/1784underwater object detectionmonocular visionregion of interesttransmission estimation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhe Chen Zhen Zhang Fengzhao Dai Yang Bu Huibin Wang |
spellingShingle |
Zhe Chen Zhen Zhang Fengzhao Dai Yang Bu Huibin Wang Monocular Vision-Based Underwater Object Detection Sensors underwater object detection monocular vision region of interest transmission estimation |
author_facet |
Zhe Chen Zhen Zhang Fengzhao Dai Yang Bu Huibin Wang |
author_sort |
Zhe Chen |
title |
Monocular Vision-Based Underwater Object Detection |
title_short |
Monocular Vision-Based Underwater Object Detection |
title_full |
Monocular Vision-Based Underwater Object Detection |
title_fullStr |
Monocular Vision-Based Underwater Object Detection |
title_full_unstemmed |
Monocular Vision-Based Underwater Object Detection |
title_sort |
monocular vision-based underwater object detection |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2017-08-01 |
description |
In this paper, we propose an underwater object detection method using monocular vision sensors. In addition to commonly used visual features such as color and intensity, we investigate the potential of underwater object detection using light transmission information. The global contrast of various features is used to initially identify the region of interest (ROI), which is then filtered by the image segmentation method, producing the final underwater object detection results. We test the performance of our method with diverse underwater datasets. Samples of the datasets are acquired by a monocular camera with different qualities (such as resolution and focal length) and setups (viewing distance, viewing angle, and optical environment). It is demonstrated that our ROI detection method is necessary and can largely remove the background noise and significantly increase the accuracy of our underwater object detection method. |
topic |
underwater object detection monocular vision region of interest transmission estimation |
url |
https://www.mdpi.com/1424-8220/17/8/1784 |
work_keys_str_mv |
AT zhechen monocularvisionbasedunderwaterobjectdetection AT zhenzhang monocularvisionbasedunderwaterobjectdetection AT fengzhaodai monocularvisionbasedunderwaterobjectdetection AT yangbu monocularvisionbasedunderwaterobjectdetection AT huibinwang monocularvisionbasedunderwaterobjectdetection |
_version_ |
1725577119727091712 |