Underwater acoustic target recognition technology is an important part of underwater acoustic signal processing and an important technical support for underwater acoustic information acquisition and underwater acoustic information countermeasures. Aiming at the problems of large amount of detection data,low automation degree and low recognition efficiency in underwater acoustic target recognition,the application of deep learning in underwater acoustic target recognition was studied. First,the research status and the current challenges of underwater acoustic target recognition technology are introduced. Then,the network structure principle and improved form of deep learning are analyzed,and the application statuses of deep learning in underwater acoustic signal recognition and underwater acoustic image signal recognition are explained respectively. Finally,it is pointed out that due to the constraints of current technical conditions and the complex underwater environment,this method still has shortcomings. This mehod provides a reference for further optimization of deep learning algorithms,expansion of the scope of deep learning technology applications,and improvement of underwater acoustic target recognition efficiency.
[5] RAJAGOPAL R,SANKARANARAYANAN B,RAO P R.Target classification in a passive sonar—an expert system approach[C]//International Conference on Acoustics.US:IEEE,2002.
[6] LOURENS J G.Classification of ships using underwater radiated noise[C]//Conference on Communications & Signal Processing.US:IEEE,1988.
[7] ARNAB D,ARUN K,RAJENDAR B.Feature analyses for marine vessel classification using passive sonar[C]//International Conference on Acoustics.US:IEEE,2005.
[8] MAKSYM J N,BONNER A J,DENT C A,et al.Machine analysis of acoustical signal[J].Pattern Recognition,1983,16(6):615-625.
[9] FARROKHROOZ M,KARIMI M.Ship noise classification using probabilistic neural network and AR model coefficients[C]//Oceans UDT.Europe:IEEE,2005.
[10] TANMAY R,ARUN K,RAJENDAR B.Estimation of a nonlinear coupling feature for underwater target classification[C]//Oceans UDT.Europe:IEEE,2002.
[11] VACCARO R J.The past,present,and the future of underwater acoustic signal processing[J].IEEE Signal Processing Magazine,1998,15(4):21-51.
[12] LENNARTSSON R K,PERSSON L,ROBINSON J W C,et al.Passive underwater signature estimation by bispectral analysis[J].IEEE,2000,20(8):281-285.
[13] LI Q H,WAN J L,WEI W.An application of expert system in recognition of radiated noise of underwater target[C]//Oceans UDT.Europe:IEEE,1995.
[22] HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[23] CHEN H,MURRAY A.A continuous restricted Boltzmann machine with a hardware amenable learning algorithm[C]//Artificial Neural Networks-ICANN 2002.Berlin:Springer,2002.
[24] LEE H,EKANADHAM C,NG A Y.Sparse deep belief net model for visual area V2[C]//Proceedings of the Advances in neural information processing systems.Europe:IEEE,2008.
[25] LUO H,SHEN R,NIU C,et al.Sparse group restricted Boltzmann machines[C]//Proceedings of the AAAI.US:AAAI,2011.
[26] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradientbased learning applied to document recognition[C]//Proceedings of the IEEE.Europe:IEEE,1998.
[27] IMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2015-03-25].http://www.cs.utexas.edu.
[28] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2014.
[29] GIRSHICK R.Fast R-CNN[C]//International Conference on Computer Vision.Piscataway:IEEE,2015.
[30] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[C]//Annual Conference on Neural Information Processing Systems.Cambridge:MIT Press,2015.
[31] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//International Conference on Computer Vision.Piscataway:IEEE,2017.
[33] CHO K,MERNENBOER B,BAHDANAU D,et al.On the properties of neural machine translation:Encoder-decoder approaches[EB/OL].[2014-05-23].http://www.engi-neering.purdue.edu.
[34] PEREZ J,ATTANASIO A C,NECHYPORENKO N,et al.A deep learning approach for underwater image enhancement[C]//International Work-Conference on the Interplay Between Natural and Artificial Computation.Europe:IEEE,2017.
[35] WON K T,YU S C,YUH J K.Neural network-based underwater image classification for autonomous underwater vehicles[C]//Proceedings of the 17th World Congress,International Federation of Automatic Control.US:IFAC,2008.
[36] ORENSTEIN E C,BEIJBOM O,PEACOCK E E,et al.Whoi-plankton-A large scale fine grained visual recognition benchmark dataset for plankton classification[J].Proceedings of the IEEE,2015,8(26):2357-2368.