For the purpose of improving the accuracy of underwater acoustic target recognition with only a small number of labeled data, we proposed a novel recognition method, including 4 steps: pre-processing, pre-training, fine-tuning and recognition. The 4 steps can be explained as follows: (1) Pre-processing with Resonance-based Sparsity Signal Decomposition (RSSD): RSSD was firstly utilized to extract high-resonance components from ship-radiated noise. The high-resonance components contain the major information for target recognition. (2) Pre-training with unsupervised feature-extraction: we proposed a one-dimensional convolution autoencoder-decoder model and then we pre-trained the model to extract features from the high-resonance components. (3) Fine-tuning with supervised feature-separation: a supervised feature-separation algorithm was proposed to fine-tune the model and separate the extracted features. (4) Recognition: classifiers were trained to recognize the separated features and complete the recognition mission. The unsupervised pre-training autoencoder-decoder can make good use of a large number of unlabeled data, so that only a small number of labeled data are required in the following supervised fine-tuning and recognition, which is quite effective when it is difficult to collect enough labeled data. The recognition experiments were all conducted on ship-radiated noise data recorded using a sensory hydrophone. By combining the 4 steps above, the proposed recognition method can achieve recognition accuracy of 93.28%, which sufficiently surpasses other traditional state-of-art feature-extraction methods.

Water pollution has seriously threatened our life, so an effective water quality monitoring mechanism is the most important part of water quality management. Most studies use biological monitoring methods to monitor water pollutants such as pesticides, heavy metals and organic pollutants. However, there are still many difficulties at present. Few methods consider the influence of illumination and complex background in the monitoring environment, and the characteristics parameters extracted in the systems are single. In addition, the results of using shallow neural networks for water quality classification are often not ideal. In order to solve the above problems, we design a water quality monitoring system combined with computer image processing technology, and use computer vision to analyze the fish behavior in real-time for monitoring the existence or not of water pollution. For the illumination problem, we use the no-reference quality assessment algorithm based on Natural Scene Statistics for contrast distortion images (GWH-GLBH) to evaluate the video and configure the lighting conditions of the monitoring environment. White balance preprocessing is also performed to provide a great basis for moving target detection. Besides, we use background modeling to eliminate the influence of complex background on the moving target detection and the foreground is extracted using the saliency detection algorithm (Seg). In order to comprehensively analyze the influence of water quality on the fish behavior from the extracted foreground targets, multidimensional feature parameters are used to quantify the indicators including movement velocity, rotation angle, spatial standard deviation and body color which characterize the behavior changes of the fish. Finally, the classification model based on LSTM (Long Short-Term Memory) neural network is used to classify the feature parameters data of the fish behavior in different water quality environments. In this paper, red zebra fish is used as the indicator organism and copper sulfate solution is used as the toxic pollutant to simulate the water pollution. Experiment results show that the classification accuracy rate of water quality using the proposed system can reach 100% at level 2 classification (93.33% at level 3 and 91% at level 4). Our system can achieve more accurate multi-level classification than shallow neural network such as RNN, and it is faster for real-time monitoring with a high reference for the water environment emergencies.

Ship recognition based on ship-radiated noise is one of the most important and challenging subjects in underwater acoustic signal processing. The recognition methods for ship-radiated noise recognition include traditional methods and deep learning (DL) methods. Developing from the DL methods and inspired by audio–video speech recognition (AVSR), the paper further introduces multimodal deep learning (multimodal-DL) methods for the recognition of ship-radiated noise. In this paper, ship-radiated noise (acoustics modality) and visual observation of the ships (visual modality) are two different modalities that the multimodal-DL methods model on. The paper specially designs a multimodal-DL framework, the multimodal convolutional neural networks (multimodal-CNNs) for the recognition of ship-radiated noise. Then the paper proposes a strategy based on canonical correlation analysis (CCA-based strategy) to build a joint representation and recognition on the two different single-modality (acoustics modality and visual modality). The multimodal-CNNs and the CCA-based strategy are tested on real ship-radiated noise data recorded. Experimental results show that, using the CCA-based strategy, strong-discriminative information can be built from weak-discriminative information provided from a single-modality. Experimental results also show that as long as any one of the single-modalities can provide information for the recognition, the multimodal-DL methods can have a much better multiclass recognition performance than the DL methods. The paper also discusses the advantages and superiorities of the multimodal-Dl methods over the traditional methods for ship-radiated noise recognition.

As acoustic waves are affected by the channel characteristics, such as scattering and reverberation when propagating in water, sonar images often exhibit speckle noise which will cause visual quality of the image to decrease. Therefore, denoising is a crucial preprocessing technique in sonar image applications. However, speckle noise is mainly caused by the sediment echo signals which are related to the background of seafloor sediment and can be obtained by prior modeling. Although deep learning-based denoising algorithms represent a research hotspot now, they are not suitable for such applications due to the high calculation amount and the large requirement of original images considering that sonar is carried by Autonomous Underwater Vehicles (AUVs) for collecting sonar images and performing calculation. In contrast, dictionary learning-based denoising method is more suitable and easier to be modeled. Compared with deep learning, it can greatly reduce the calculation amount and is more easily integrated into AUV systems. In addition, dictionary learning method based on image sparse representation can effectively achieve image denoising similarly. In order to solve the above problems, we propose a new adaptive dictionary learning method based on multi-resolution characteristics, which combines K-SVD dictionary learning with wavelet transform. Our method has the characteristics of dictionary learning and inherits the features of wavelet analysis as well. Compared with several classical methods, the proposed method is better at speckle noise reduction and edge detail preservation. At the same time, the calculation time is greatly reduced and the efficiency is significantly improved.

In turbid water, the attenuation and scattering of light caused by scatterers make underwater optical images degraded, blurred, and contrast reduced, limiting the extraction and analysis of information from images. To address such problems, a turbid underwater image enhancement method based on parameter-tuned stochastic resonance (SR) is proposed in this article. First, an SR algorithm framework for underwater image enhancement is constructed, including the dimensionality reduction and normalization of input images, the solution and parameter optimization of the SR system, the dimensionality upgrading of output images, etc. This framework can apply the SR's ability to enhance weak signals to the enhancement of turbid underwater images. Second, to measure the performance of the system, a synthetic turbid underwater image data set (UWCHIC) is constructed using the underwater imaging model and an image set with simulated scatterers. Based on this data set, the relationship between various image quality evaluation metrics and system parameters is analyzed, and then the suitable no-reference (NR) metrics for system performance evaluation are selected and an adaptive parameter tuning strategy of the SR system is proposed to guide the image enhancement. Lastly, the proposed method is evaluated on the UWCHIC, a dataset to evaluate underwater image restoration methods (TURBID), marine underwater environment database (MUED), and underwater image enhancement benchmark (UIEB) data sets and the turbid underwater images captured from natural waters. Different experimental evaluations demonstrated that the proposed method not only effectively enhances the visual quality of turbid underwater images but also improves the performance of downstream vision tasks.