Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

Marija Jegorova; Antti Ilari Karjalainen; Jose Vazquez; Timothy Hospedales

doi:10.1109/ICRA40945.2020.9197353

Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

Marija Jegorova, Antti Ilari Karjalainen, Jose Vazquez, Timothy Hospedales

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple applications, including training of human operators for postmission analysis, as well as tuning and validation of autonomous target recognition (ATR) systems for underwater vehicles. Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle attitude, and a variety of environmental factors. We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). Quantitative assessment results confirm that the quality of the produced data is almost indistinguishable from real. Furthermore, we show that bootstrapping ATR systems with MC-pix2pix data can improve the performance. Synthetic data is generated 18
times faster than real acquisition speed, with full user control over the topography of the generated data.

Original language	English
Title of host publication	2020 IEEE International Conference on Robotics and Automation (ICRA)
Publisher	Institute of Electrical and Electronics Engineers
Pages	3168-3174
Number of pages	7
ISBN (Electronic)	978-1-7281-7395-5
ISBN (Print)	978-1-7281-7396-2
DOIs	https://doi.org/10.1109/ICRA40945.2020.9197353
Publication status	Published - 15 Sept 2020
Event	2020 International Conference on Robotics and Automation - Virtual conference, France Duration: 31 May 2020 → 31 Aug 2020 https://www.icra2020.org/

Publication series

Name
Publisher	IEEE
ISSN (Print)	1050-4729
ISSN (Electronic)	2577-087X

Conference

Conference	2020 International Conference on Robotics and Automation
Abbreviated title	ICRA 2020
Country/Territory	France
City	Virtual conference
Period	31/05/20 → 31/08/20
Internet address	https://www.icra2020.org/

Access to Document

10.1109/ICRA40945.2020.9197353Licence: All Rights Reserved

Full-Scale Continuous_JEGOROVA_DOA27022020_AFVAccepted author manuscript, 9.58 MBLicence: All Rights Reserved

https://ieeexplore.ieee.org/document/9197353Licence: All Rights Reserved

Cite this

@inproceedings{e5bb5af94e354f8998f539e0a87d0b6a,

title = "Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks",

abstract = "Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple applications, including training of human operators for postmission analysis, as well as tuning and validation of autonomous target recognition (ATR) systems for underwater vehicles. Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle attitude, and a variety of environmental factors. We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). Quantitative assessment results confirm that the quality of the produced data is almost indistinguishable from real. Furthermore, we show that bootstrapping ATR systems with MC-pix2pix data can improve the performance. Synthetic data is generated 18times faster than real acquisition speed, with full user control over the topography of the generated data.",

author = "Marija Jegorova and Karjalainen, {Antti Ilari} and Jose Vazquez and Timothy Hospedales",

year = "2020",

month = sep,

day = "15",

doi = "10.1109/ICRA40945.2020.9197353",

language = "English",

isbn = "978-1-7281-7396-2",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "3168--3174",

booktitle = "2020 IEEE International Conference on Robotics and Automation (ICRA)",

address = "United States",

note = "2020 International Conference on Robotics and Automation, ICRA 2020 ; Conference date: 31-05-2020 Through 31-08-2020",

url = "https://www.icra2020.org/",

}

Jegorova, M, Karjalainen, AI, Vazquez, J & Hospedales, T 2020, Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks. in 2020 IEEE International Conference on Robotics and Automation (ICRA). Institute of Electrical and Electronics Engineers, pp. 3168-3174, 2020 International Conference on Robotics and Automation, Virtual conference, France, 31/05/20. https://doi.org/10.1109/ICRA40945.2020.9197353

Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks. / Jegorova, Marija; Karjalainen, Antti Ilari; Vazquez, Jose et al.
2020 IEEE International Conference on Robotics and Automation (ICRA). Institute of Electrical and Electronics Engineers, 2020. p. 3168-3174.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

AU - Jegorova, Marija

AU - Karjalainen, Antti Ilari

AU - Vazquez, Jose

AU - Hospedales, Timothy

PY - 2020/9/15

Y1 - 2020/9/15

N2 - Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple applications, including training of human operators for postmission analysis, as well as tuning and validation of autonomous target recognition (ATR) systems for underwater vehicles. Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle attitude, and a variety of environmental factors. We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). Quantitative assessment results confirm that the quality of the produced data is almost indistinguishable from real. Furthermore, we show that bootstrapping ATR systems with MC-pix2pix data can improve the performance. Synthetic data is generated 18times faster than real acquisition speed, with full user control over the topography of the generated data.

AB - Deployment and operation of autonomous underwater vehicles is expensive and time-consuming. High-quality realistic sonar data simulation could be of benefit to multiple applications, including training of human operators for postmission analysis, as well as tuning and validation of autonomous target recognition (ATR) systems for underwater vehicles. Producing realistic synthetic sonar imagery is a challenging problem as the model has to account for specific artefacts of real acoustic sensors, vehicle attitude, and a variety of environmental factors. We propose a novel method for generating realistic-looking sonar side-scans of full-length missions, called Markov Conditional pix2pix (MC-pix2pix). Quantitative assessment results confirm that the quality of the produced data is almost indistinguishable from real. Furthermore, we show that bootstrapping ATR systems with MC-pix2pix data can improve the performance. Synthetic data is generated 18times faster than real acquisition speed, with full user control over the topography of the generated data.

U2 - 10.1109/ICRA40945.2020.9197353

DO - 10.1109/ICRA40945.2020.9197353

M3 - Conference contribution

SN - 978-1-7281-7396-2

SP - 3168

EP - 3174

BT - 2020 IEEE International Conference on Robotics and Automation (ICRA)

PB - Institute of Electrical and Electronics Engineers

T2 - 2020 International Conference on Robotics and Automation

Y2 - 31 May 2020 through 31 August 2020

ER -

Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this