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 pa...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.展开更多
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,whic...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.展开更多
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 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.展开更多
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 ...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.展开更多
基金supported by the National Natural Science Foundation of China(No.62103072)the Postdoctoral Science Foundation of China(No.2021M690502)。
文摘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.
基金Scientific Research Fund of Liaoning Provincial Education Department(No.JGLX2021030):Research on Vision-Based Intelligent Perception Technology for the Survival of Benthic Organisms.
文摘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.
基金the National Natural Science Foundation of China(Grant number 10074039)
文摘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.
文摘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.