Non-linear Convolutional Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery
Detection of mines on the seafloor is most accurately performed by a human operator. However, it is a difficult task for machine vision methods. In addition, mine detection calls for high accuracy detection because of the high-risk nature of the problem. The advancements in the capabilities of sonar imaging and autonomous underwater vehicles has led to research using machine learning techniques and well known computer vision features (Barngrover et al., IEEE J. Ocean Eng. (2015), ). Non-linear classifiers such as Haar-like feature classifiers have shown good potential in extracting complex spatial and temporal patterns from noisy multidirectional series of sonar imagery, however this approach is dependent on specific sonar illumination methods and does not account for amount of lighting or soil type variation in training and test images. In this paper, we report on the preliminary methods and results of applying a non-linear classification method, convolutional neural networks (CNN) to mine detection in noisy sonar imagery. The advantage of this method is that it can learn more abstract and complex features in the input space, leading to a lower false-positive and higher true positive rates. CNNs routinely outperform other methods in similar machine vision tasks (Deng and Yu, Found. Trends Signal Process. 7, 197–387 (2013), ). We used a simple CNN architecture trained to distinguish mine-like objects from background clutter with up to 99% accuracy.
KeywordsNon-linear classifier Convolution neural network (CNN) Sonar Feature selection Machine vision Object detection
- 1.C. Barngrover, A. Althoff, P. DeGuzman, R. Kastner, A Brain–Computer Interface (BCI) for the detection of mine-like objects in sidescan sonar imagery. IEEE J. Ocean Eng. (2015)Google Scholar
- 2.L. Deng, D. Yu, Deep learning methods and applications. Found. Trends Signal Process. 7, 197–387 (2013)Google Scholar
- 3.P. Cervenka, C. De Moustier, P.F. Lonsdale, Geometric corrections on sidescan sonar images based on Bathvmetrv. Application with SeaMARC II and Sea Beam Data. Mar. Geophys. Res. 16(5) (1994)Google Scholar
- 4.D. Gerhart, K. Parikh, I. Dzieciuch, Convolutional Neural Network on Embedded Linux System-On Chip: A Methodology and Performance Benchmark, Technical report at SPAWAR (2014)Google Scholar
- 5.D.R. Wilson, T.R. Martinez, The general inefficiency of batch training for gradient descent learning. Neural Netw. 16(10), 1429–1451 (2003)Google Scholar