Sonar Image Translation Using Generative Adversarial Network for Underwater Object Recognition
- Title
- Sonar Image Translation Using Generative Adversarial Network for Underwater Object Recognition
- Authors
- Sung, M.; CHO, HYEONWOO; JASON, KIM; Yu, S.-C.
- Date Issued
- 2019-04-19
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Abstract
- Sonar sensor is widely used for underwater object recognition. However, acquiring reference sonar images for each target object is high-cost and time-consuming. Sonar image simulators can generate reference sonar images with small computation, but the simulated images are different with actual sonar images captured in the field. This paper proposes a method to translate actual sonar images to simulated-like images using a generative adversarial network. We trained the network with images captured by the indoor water tank test. The trained neural network can generate simulator-like images from given actual sonar images. Further, we can recognize the target object using template matching between the translated image and the reference images simulating the target object. © 2019 IEEE.
- URI
- https://oasis.postech.ac.kr/handle/2014.oak/112999
- ISSN
- 0000-0000
- Article Type
- Conference
- Citation
- 2019 IEEE International Underwater Technology Symposium, UT 2019, page. 1 - 6, 2019-04-19
- 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.