Share Email Print

Proceedings Paper • new

An underwater binocular vision positioning method based on back-propagation neural networks
Author(s): Lei Feng; Jian Gao; Zuocheng Tang; Chen Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In view of the existing underwater sensors cannot obtain a relative positional relationship between the target and the underwater vehicle, as well as, target positioning based on binocular vision method which has systematic errors needs more accurate calibration result. An approach for vision of a recognized underwater target is proposed in this paper. The first step is to process the original image with image enhancement and filtering, identify the target image based on HSV threshold. In the next step for target positioning, a three dimensional (3D) re-construction method based on block matching after binocular vision calibration and a 3D re-construction method with learning neural network are studied. Aiming at the problems of slow convergence rate and local optimum of traditional BP networks, several improvements of traditional BP networks are proposed. Finally, the experiment proves that the method can obtain high precision result and good real-time performance under sufficient stylebook data.

Paper Details

Date Published: 12 December 2018
PDF: 7 pages
Proc. SPIE 10850, Ocean Optics and Information Technology, 108500N (12 December 2018); doi: 10.1117/12.2505517
Show Author Affiliations
Lei Feng, Northwestern Polytechnical Univ. (China)
Jian Gao, Northwestern Polytechnical Univ. (China)
Zuocheng Tang, Northwestern Polytechnical Univ. (China)
Chen Li, Northwestern Polytechnical Univ. (China)

Published in SPIE Proceedings Vol. 10850:
Ocean Optics and Information Technology
Xuelong Li; Lixin Wu; Jianquan Yao; Hao Yin; Renhe Zhang; Zhongliang Zhu, Editor(s)

© SPIE. Terms of Use
Back to Top