Object recognition in forward-looking sonar images with Convolutional Neural Networks
- 1 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Forward-looking sonars can provide high resolution images that can be used for different tasks in an underwater environment. However, image interpretation is still an open problem due to multiple issues inherent in acoustic imaging. In this work, we use Convolutional Neural Networks (CNN) for object recognition in forward-looking sonar images. We show that a CNN outperforms the state of the art for such kind of images by achieving an accuracy of 99.2%. While state of the art template matching methods have accuracies between 92.4% and 97.6%. We also compare the number of learnable parameters of CNNs and template matching that are required to achieve high performance. Our results show that CNNs require less parameters to provide better recognition capabilities that generalize well to unseen data.Keywords
This publication has 8 references indexed in Scilit:
- CNN Features Off-the-Shelf: An Astounding Baseline for Recognition2014
- Fast Target Detection in Synthetic Aperture Sonar Imagery: A New Algorithm and Large-Scale Performance AnalysisIEEE Journal of Oceanic Engineering, 2014
- Unified Design of a Feature-Based ADAC System for Mine Hunting Using Synthetic Aperture SonarIEEE Transactions on Geoscience and Remote Sensing, 2013
- Automatic detection of underwater chain links using a forward-looking sonar2013
- Improving deep neural networks for LVCSR using rectified linear units and dropout2013
- A Template Matching Procedure for Automatic Target Recognition in Synthetic Aperture Sonar ImageryIEEE Signal Processing Letters, 2010
- ImageNet: A large-scale hierarchical image database2009
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998