Crosstalk Noise Detection and Removal in Multi-beam Sonar Images Using Convolutional Neural Network
- Title
- Crosstalk Noise Detection and Removal in Multi-beam Sonar Images Using Convolutional Neural Network
- Authors
- Sung, M.; Cho, H.; Joe, H.; Kim, B.; Yu, S.-C.
- Date Issued
- 2018-10-24
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- With its long operating range and ability to be used in a turbid environment, sonar sensor is mainly used to explore underwater environment. As a result, many algorithms based on the sonar have been developed. However, in the case of a multi-beam sonar, its mechanism causes crosstalk noise around the underwater object, which degrades the accuracy of these algorithms. In this paper, we propose a method to remove crosstalk noise from a sonar image by detecting the region where the crosstalk noise occurred using a convolutional neural network and filling the detected region with adjacent pixel values. The proposed method could accurately and effectively detect and remove crosstalk noise in a given sonar image. Therefore, the accuracy of the sonar-based algorithms such as a 3-D reconstruction of underwater terrain can be improved. © 2018 IEEE.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/113005
- ISSN
- 0000-0000
- Article Type
- Conference
- Citation
- OCEANS 2018 MTS/IEEE Charleston, OCEANS 2018, page. 1 - 6, 2018-10-24
- Files in This Item:
- There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.