Accurate Underwater ATR in Forward-Looking Sonar Imagery Using Deep Convolutional Neural Networks

• Published in: IEEE access Vol. 7; pp. 125522 - 125531
• Main Authors: Jin, Leilei, Liang, Hong, Yang, Changsheng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Automatic target recognition; Automatic target recognition (ATR); Autonomous underwater vehicles; deep convolutional neural networks (DCNNs); Feature extraction; Feature recognition; forward-looking sonar; Image recognition; Imagery; Imaging; Network management systems; Neural networks; Object recognition; Optimization; Preprocessing; Sonar; sonar image processing; Target recognition; Task analysis; Training; transfer learning
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2939005

Underwater automatic target recognition (ATR) is a challenging task for marine robots due to the complex environment. The existing recognition methods basically use hand-crafted features and classifiers to recognize targets, which are difficult to achieve ideal recognition accuracy. In this paper, we proposed a novel method to realize accurate multiclass underwater ATR by using forward-looking sonar-Echoscope and deep convolutional neural networks (DCNNs). A complete recognition process from data preprocessing to network training and image recognition was realized. Firstly, we established a real, measured Echoscope sonar image dataset. Inspired by the human visual attention mechanism, the suspected target region was extracted via the graph-based manifold ranking method in image preprocessing. Secondly, an end-to-end DCNNs model, named EchoNet, was designed for Echoscope sonar image feature extraction and recognition. Finally, a network training method based on transfer learning was developed to solve the problem of insufficient training data, and mini-batch gradient descent was used for network optimization. Experimental results demonstrated that our method can implement efficiently, and the recognition accuracy on a nine-class underwater ATR task reached 97.3%, outperforming traditional feature-based methods. The proposed method is expected to be a potential novel technology for the intelligent perception of autonomous underwater vehicles.