Blind Source Separation based on Time-Frequency Morphological Characteristics for Rigid Acoustic Scattering by Underwater Objects

Separation of the components of rigid acoustic scattering by underwater objects is essential in obtaining the structural characteristics of such objects. To overcome the problem of rigid structures appearing to have the same spectral structure in the time domain, time-frequency Blind Source Separation （BSS） can be used in combination with image morphology to separate the rigid scattering components of different objects. Based on a highlight model, the separation of the rigid scattering structure of objects with time-frequency distribution is deduced. Using a morphological filter, different characteristics in a Wigner-Ville Distribution （WVD） observed for single auto term and cross terms can be simplified to remove any cross-term interference. By selecting time and frequency points of the auto terms signal, the accuracy of BSS can be improved. A simulation experimental has been used to analyze the feasibility of the new method, with changing the pulse width of the transmitted signal, the relative amplitude and the time delay parameter. And simulation results show that the new method can not only separate rigid scattering components, but can also separate the components when elastic scattering and rigid scattering exist at the same time. Experimental results confirm that the new method can be used in separating the rigid scattering structure of underwater objects.

An Underwater Target Detection Algorithm Based on Attention Mechanism and Improved YOLOv7

For underwater robots in the process of performing target detection tasks,the color distortion and the uneven quality of underwater images lead to great difficulties in the feature extraction process of the model,which is prone to issues like error detection,omission detection,and poor accuracy.Therefore,this paper proposed the CER-YOLOv7(CBAM-EIOU-RepVGG-YOLOv7)underwater target detection algorithm.To improve the algorithm’s capability to retain valid features from both spatial and channel perspectives during the feature extraction phase,we have added a Convolutional Block Attention Module(CBAM)to the backbone network.The Reparameterization Visual Geometry Group(RepVGG)module is inserted into the backbone to improve the training and inference capabilities.The Efficient Intersection over Union(EIoU)loss is also used as the localization loss function,which reduces the error detection rate and missed detection rate of the algorithm.The experimental results of the CER-YOLOv7 algorithm on the UPRC(Underwater Robot Prototype Competition)dataset show that the mAP(mean Average Precision)score of the algorithm is 86.1%,which is a 2.2%improvement compared to the YOLOv7.The feasibility and validity of the CER-YOLOv7 are proved through ablation and comparison experiments,and it is more suitable for underwater target detection.

Underwater object detection by fusing features from different representations of sonar data

Modern underwater object detection methods recognize objects from sonar data based on their geometric shapes.However,the distortion of objects during data acquisition and representation is seldom considered.In this paper,we present a detailed summary of representations for sonar data and a concrete analysis of the geometric characteristics of different data representations.Based on this,a feature fusion framework is proposed to fully use the intensity features extracted from the polar image representation and the geometric features learned from the point cloud representation of sonar data.Three feature fusion strategies are presented to investigate the impact of feature fusion on different components of the detection pipeline.In addition,the fusion strategies can be easily integrated into other detectors,such as the You Only Look Once(YOLO)series.The effectiveness of our proposed framework and feature fusion strategies is demonstrated on a public sonar dataset captured in real-world underwater environments.Experimental results show that our method benefits both the region proposal and the object classification modules in the detectors.

Research of Underwater Bottom Object and Reverberation in Feature Space

The critical technical problem of underwater bottom object detection is founding a stable feature space for echo signals classification. The past literatures more focus on the characteristics of object echoes in feature space and reverberation is only treated as interference. In this paper, reverberation is considered as a kind of signal with steady characteristic, and the clustering of reverberation in frequency discrete wavelet transform （FDWT） feature space is studied. In order to extract the identifying information of echo signals, feature compression and cluster analysis are adopted in this paper, and the criterion of separability between object echoes and reverberation is given. The experimental data processing results show that reverberation has steady pattern in FDWT feature space which differs from that of object echoes. It is proven that there is separability between reverberation and object echoes.

Classification of underwater still objects based on multi-field features and SVM

A Support Vector Machine is used as a classifier to the automatic detection and recognition of underwater still objects. Discrimination between the objects can be transferred into different projection spaces by the process of multi-field feature extraction. The multi-field feature vector includes time-domain, spectral, time-frequency distribution and bi-spectral features. Underwater target recognition can be considered as a problem of small sample recognition. SVM algorithm is appropriate to this kind of problems because of its outstanding generalizability. The SVM is contrasted with a Gaussian classifier and a k-nearest classifier in some experiments using real data of lake or sea trial. The experimental results indicate that SVM is better than the others two.

Study on the optical system for the record of the pulsed acoustic field and the scattering of the cylindrical-like objects buried in underwater sand

The response of the two working mode of the optical systems, the schlieren mode and shadowgraph mode, for taking of optical photograph of the pulsed acoustic field in liquid are studied. It shows that, the response of the optical intensity on the screen to the acoustic pressure is linear for shadowgraph mode and nonlinear for the schlieren mode. Because the function of shadowgraph mode has no limit on working frequency, it is suitable for the studies of the acoustic field of laboratory model of the seabed or the buried objects at low ultrasonic range. The ultrasonic pulse scattered by the cylindrical-like objects buried in underwater sand was studied experimentally by the shadowgraph mode at low ultrasonic frequency. There are five kinds of the scattered waves from the half-buried object and three kinds of the waves from the full-buried objects were recorded. The two kinds of creeping waves (the longitudinal wave and the shear wave of the object) appear in both of the two cases.

Analytical review and study on object detection techniques in the image

Object detection is the most fundamental but challenging issues in the field of computer vision.Object detection identifies the presence of various individual objects in an image.Great success is attained for object detection/recognition problems in the controlled environment,but still,the problem remains unsolved in the uncontrolled places,particularly,when the objects are placed in arbitrary poses in an occluded and cluttered environment.In the last few years,a lots of efforts are made by researchers to resolve this issue,because of its wide range of applications in computer vision tasks,like content-enabled image retrieval,event or activity recognition,scene understanding,and so on.This review provides a detailed survey of 50 research papers presenting the object detection techniques,like machine learning-based techniques,gradient-based techniques,Fast Region-based Convolutional Neural Network(Fast R-CNN)detector,and the foreground-based techniques.Here,the machine learning-based approaches are classified into deep learning-based approaches,random forest,Support Vector Machine(SVM),and so on.Moreover,the challenges faced by the existing techniques are explained in the gaps and issues section.The analysis based on the classification,toolset,datasets utilized,published year,and the performance metrics are discussed.The future dimension of the research is based on the gaps and issues identified from the existing research works.