Format

Send to

Choose Destination
Sensors (Basel). 2017 Aug 3;17(8). pii: E1784. doi: 10.3390/s17081784.

Monocular Vision-Based Underwater Object Detection.

Author information

1
College of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, China. chenzhe@hhu.edu.cn.
2
Key Laboratory of Trusted Cloud Computing and Big Data Analysis, Nanjing Xiaozhuang University, Nanjing 211100, Jiangsu, China. chenzhe@hhu.edu.cn.
3
College of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, China. zz_hhuc@hhu.edu.cn.
4
Laboratory of Information Optics and Opto-Electronic Technology, Shanghai Institute of Optics and Fine Mechanics, Shanghai 201800, China. fzdai@siom.ac.cn.
5
Laboratory of Information Optics and Opto-Electronic Technology, Shanghai Institute of Optics and Fine Mechanics, Shanghai 201800, China. buyang@siom.ac.cn.
6
College of Computer and Information, Hohai University, Nanjing 211100, Jiangsu, China. hbwang@hhu.edu.cn.

Abstract

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.

KEYWORDS:

monocular vision; region of interest; transmission estimation; underwater object detection

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center