Abstract
This paper presents a system for the intelligent search of shipwrecks using Autonomous Underwater Vehicles (AUVs). It introduces a machine learning approach to the automatic identification of potential archaeological sites from AUV-obtained side-scan sonar (SSS) data. The site identification pipeline consists of a series of stages that set up for, run, and process the output of a convolutional neural network (CNN). To alleviate the issue of training data scarcity, i.e. the lack of SSS data that includes shipwrecks, and improve the performance at testing time, a data augmentation stage is included in the pipeline. In addition, edge detection and other traditional image processing feature extraction methods are used in parallel with CNN to improve algorithmic performance. Experiments from two multi-deployment shipwreck search expeditions involving actual AUV deployments along the coast of Malta for data collection and processing demonstrate the pipeline’s usefulness. Results from these two field expeditions yielded a precision/recall of 29.34%/97.22% and 32.95%/80.39%, respectively. Despite the poor precision, the pipeline filters out 99.79% of the area in data set A and 99.31% of the area in data set B.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Atallah, L., Shang, C., Bates, R.: Object detection at different resolution in archaeological side-scan sonar images. Eur. Ocean 2005 (2005). https://doi.org/10.1109/OCEANSE.2005.1511727
Barngrover, C., Kastner, R., Belongie, S.: Semisynthetic versus real-world sonar training data for the classification of mine-like objects. J. Ocean Eng. 40, 48–56 (2015)
Bradski, G., Kaehler, A.: Learning Opencv, 1st edn. O’Reilly, Sabostopol, CA (2008)
Chang, R., Wang, Y., Hou, J. et al.: Underwater object detection with efficient shadow-removal for side scan sonar images. OCEANS 2016—Shanghai (2016). https://doi.org/10.1109/OCEANSAP.2016.7485696
Chew, A., Tong, P., Chia, C.: Automatic detection and classification of man-made targets in side scan sonar images. Symposium on Underwater Tech (2007). https://doi.org/10.1109/UT.2007.370841
Daniel, S., Le Léannec, F., Roux, C., et al.: Side-scan sonar image matching. J. Ocean Eng. 23, 245–259 (1998)
Dura, E., Zhang, Y., Liao, X., et al.: Active learning for detection of mine-like objects in side-scan sonar imagery. J. Ocean Eng. 30, 360–371 (2005)
Gambin, T.: Side scan sonar and the management of underwater cultural heritage. In: Formosa, S. (ed.) Future Preparedness: Thematic and Spatial Issues for the Environment and Sustainability. Msida, Malta (2014)
He, K., Zhang, X., Ren, S. et al.: Deep residual learning for image recognition (2016). arXiv:1512.03385
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv:1502.03167
Langner, F., Knauer, C., Jans, W. et al.: Side scan sonar image resolution and automatic object detection, classification and identification. OCEANS 2009-EUROPE (2009). https://doi.org/10.1109/OCEANSE.2009.5278183
Lin, T.Y., Maire, M., Belongie, S. et al.: Microsoft COCO: common objects in context (2014). arXiv:1405.0312
McKay, J., Gerg, I., Monga, V. et al.: What’s mine is yours: pretrained CNNs for limited training sonar ATR (2017). arXiv:1706.09858
Nixon, M., Aguado, A.: Feature Extraction and Image Processing for Computer Vision, 3rd edn. Academic Press (2012)
Perez, L., Wang, J.: The effectiveness of data augmentation in image classification using deep learning (2017). arXiv:1712.04621
Razavian, A.S., Azizpour, H., Sullivan, J. et al.: CNN features off-the-shelf: an astounding baseline for recognition (2014). arXiv:1403.6382
Reed, S., Petillot, Y., Bell, J.: An automatic approach to the detection and extraction of mine features in Sidescan sonar. J. Ocean Eng, 28, 95–105 (2003)
Rublee, E., Rabaud, V., Konolige, K., et al.: ORB: an efficient alternative to SIFT or SURF. Int. Conf. Comput. Vis. (2011). 10.1.1.370.4395
Russakovsky, O., Deng, J., Su, H. et al.: ImageNet large scale visual recognition challenge (2015). arXiv:1409.0575
Rutledge, J., Yuan, W., Wu, J., et al.: Intelligent shipwreck search using autonomous underwater vehicles. Int. Conf. Robot Autom. (2018). https://doi.org/10.1109/ICRA.2018.8460548
Shang, C., Brown, K.: Feature-based texture classification of side-scan sonar images using a neural network approach. Electron. Lett. 28, 2165–2167 (1992)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015). arXiv:1409.1556
Singh, H., Adams, J., Mindell, D., et al.: Imaging underwater for archaeology. J. Field Archaeol. 27, 319–328 (2000)
Srivastava, N., Hinton, G., Krizhevsky, A., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)
Wang, B., Klabjan, D.: Regularization for unsupervised deep neural nets (2017). arXiv:1608.04426
Acknowledgements
We would like to thank Jeffrey Rutledge, Samantha Ting, Russell Bingham, Andrew Pham, Kolton Yager, Bonita Galvan, and Mitchell Keller for helping us deploy the robot. This work was performed in part at Claremont Colleges Robert J. Bernard Biological Field Station. This material is based upon work supported by National Science Foundation under Grant No. 1460153.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nayak, N., Nara, M., Gambin, T., Wood, Z., Clark, C.M. (2021). Machine Learning Techniques for AUV Side-Scan Sonar Data Feature Extraction as Applied to Intelligent Search for Underwater Archaeological Sites. In: Ishigami, G., Yoshida, K. (eds) Field and Service Robotics. Springer Proceedings in Advanced Robotics, vol 16. Springer, Singapore. https://doi.org/10.1007/978-981-15-9460-1_16
Download citation
DOI: https://doi.org/10.1007/978-981-15-9460-1_16
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9459-5
Online ISBN: 978-981-15-9460-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)