Side scan sonar(SSS)is an important means to detect and locate seafloor targets.Autonomous underwater vehicles(AUVs)carrying SSS stay near the seafloor to obtain high-resolution images and provide the outline of the t...Side scan sonar(SSS)is an important means to detect and locate seafloor targets.Autonomous underwater vehicles(AUVs)carrying SSS stay near the seafloor to obtain high-resolution images and provide the outline of the target for observers.The target feature information of an SSS image is similar to the background information,and a small target has less pixel information;therefore,accu-rately identifying and locating small targets in SSS images is challenging.We collect the SSS images of iron metal balls(with a diameter of 1m)and rocks to solve the problem of target misclassification.Thus,the dataset contains two types of targets,namely,‘ball’and‘rock’.With the aim to enable AUVs to accurately and automatically identify small underwater targets in SSS images,this study designs a multisize parallel convolution module embedded in state-of-the-art Yolo5.An attention mechanism transformer and a convolutional block attention module are also introduced to compare their contributions to small target detection accuracy.The performance of the proposed method is further evaluated by taking the lightweight networks Mobilenet3 and Shufflenet2 as the backbone network of Yolo5.This study focuses on the performance of convolutional neural networks for the detection of small targets in SSS images,while another comparison experiment is carried out using traditional HOG+SVM to highlight the neural network’s ability.This study aims to improve the detection accuracy while ensuring the model efficiency to meet the real-time working requirements of AUV target detection.展开更多
To reduce the computation burden of a large-aperture multiple-input multiple-output（MIMO） sonar imaging system,the phase-shift beamformer（PSBF） is used at the cost of bringing the intensity loss（IL）.The cause of...To reduce the computation burden of a large-aperture multiple-input multiple-output（MIMO） sonar imaging system,the phase-shift beamformer（PSBF） is used at the cost of bringing the intensity loss（IL）.The cause of the IL is analyzed in detail and a variable termed as IL factor is defined to quantify the loss amount.To compensate for the IL,two methods termed as intensity compensation for the PSBF（IC-PSBF） and the hybrid beamforming（HBF）,respectively,are proposed.The IC-PSBF uses previously estimated IL factors to compensate for output intensities of all PSBFs;and the HBF applies the IC-PSBF to the center beam region and the shifted-sideband beamformer（SSBF） to the side beam region,respectively.Numerical simulations demonstrate the effectiveness of the two proposed methods.展开更多
水下目标物的准确识别是保障通航安全的一项重要工作,针对现有算法对水下多类别目标存在识别精度不高的问题,本文在YOLOv5s(You Only Look Once v5s)的基础上提出对其进行改进。首先,为平衡样本间的数量,通过利用几何变化操作模拟现实...水下目标物的准确识别是保障通航安全的一项重要工作,针对现有算法对水下多类别目标存在识别精度不高的问题,本文在YOLOv5s(You Only Look Once v5s)的基础上提出对其进行改进。首先,为平衡样本间的数量,通过利用几何变化操作模拟现实发生的情况对数量较少的样本进行扩充;其次,将YOLOv5s中传统损失函数CIoU惩罚项中的反正切函数改为Sigmoid函数,加快目标识别模型的收敛速度;最后,融合坐标注意力机制(Coordinate Attention,CA),融合后的模型能衡量每个通道信息的重要性,在关注目标位置信息的同时也不增加过多的计算量。试验结果表明:本文所提出的改进的YOLOv5s较改进前在准确率上提升了4.97%,在召回率上提高了6.20%,在类平均精度上提升了4.98%,证明本文改进的方法在工程应用上的价值。展开更多
基金supported by the National Key Research and Development Program of China(No.2016YFC0301400).
文摘Side scan sonar(SSS)is an important means to detect and locate seafloor targets.Autonomous underwater vehicles(AUVs)carrying SSS stay near the seafloor to obtain high-resolution images and provide the outline of the target for observers.The target feature information of an SSS image is similar to the background information,and a small target has less pixel information;therefore,accu-rately identifying and locating small targets in SSS images is challenging.We collect the SSS images of iron metal balls(with a diameter of 1m)and rocks to solve the problem of target misclassification.Thus,the dataset contains two types of targets,namely,‘ball’and‘rock’.With the aim to enable AUVs to accurately and automatically identify small underwater targets in SSS images,this study designs a multisize parallel convolution module embedded in state-of-the-art Yolo5.An attention mechanism transformer and a convolutional block attention module are also introduced to compare their contributions to small target detection accuracy.The performance of the proposed method is further evaluated by taking the lightweight networks Mobilenet3 and Shufflenet2 as the backbone network of Yolo5.This study focuses on the performance of convolutional neural networks for the detection of small targets in SSS images,while another comparison experiment is carried out using traditional HOG+SVM to highlight the neural network’s ability.This study aims to improve the detection accuracy while ensuring the model efficiency to meet the real-time working requirements of AUV target detection.
基金supported by the National Natural Science Foundation of China(51509204)the Opening Project of State Key Laboratory of Acoustics(SKLA201501)the Fundamental Research Funds for the Central Universities(3102015ZY011)
文摘To reduce the computation burden of a large-aperture multiple-input multiple-output（MIMO） sonar imaging system,the phase-shift beamformer（PSBF） is used at the cost of bringing the intensity loss（IL）.The cause of the IL is analyzed in detail and a variable termed as IL factor is defined to quantify the loss amount.To compensate for the IL,two methods termed as intensity compensation for the PSBF（IC-PSBF） and the hybrid beamforming（HBF）,respectively,are proposed.The IC-PSBF uses previously estimated IL factors to compensate for output intensities of all PSBFs;and the HBF applies the IC-PSBF to the center beam region and the shifted-sideband beamformer（SSBF） to the side beam region,respectively.Numerical simulations demonstrate the effectiveness of the two proposed methods.
文摘水下目标物的准确识别是保障通航安全的一项重要工作,针对现有算法对水下多类别目标存在识别精度不高的问题,本文在YOLOv5s(You Only Look Once v5s)的基础上提出对其进行改进。首先,为平衡样本间的数量,通过利用几何变化操作模拟现实发生的情况对数量较少的样本进行扩充;其次,将YOLOv5s中传统损失函数CIoU惩罚项中的反正切函数改为Sigmoid函数,加快目标识别模型的收敛速度;最后,融合坐标注意力机制(Coordinate Attention,CA),融合后的模型能衡量每个通道信息的重要性,在关注目标位置信息的同时也不增加过多的计算量。试验结果表明:本文所提出的改进的YOLOv5s较改进前在准确率上提升了4.97%,在召回率上提高了6.20%,在类平均精度上提升了4.98%,证明本文改进的方法在工程应用上的价值。
