Side-scan sonar(SSS)is essential for acquiring high-resolution seafloor images over large areas,facilitat-ing the identification of subsea objects.However,military security restrictions and the scarcity of subsea targ...Side-scan sonar(SSS)is essential for acquiring high-resolution seafloor images over large areas,facilitat-ing the identification of subsea objects.However,military security restrictions and the scarcity of subsea targets limit the availability of SSS data,posing challenges for Automatic Target Recognition(ATR)research.This paper presents an approach that uses Cycle-Consistent Generative Adversarial Networks(CycleGAN)to augment SSS images of key subsea objects,such as shipwrecks,aircraft,and drowning victims.The process begins by constructing 3D models to generate rendered images with realistic shadows frommultiple angles.To enhance image quality,a shadowextractor and shadow region loss function are introduced to ensure consistent shadowrepresentation.Additionally,amulti-resolution learning structure enables effective training,even with limited data availability.The experimental results show that the generated data improved object detection accuracy when they were used for training and demonstrated the ability to generate clear shadow and background regions with stability.展开更多
Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the...Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the task of object detection in shipwreck side-scan sonar images, due to the complex seabed environment, it is difficult to extract object features, often leading to missed detections of shipwreck images and slow detection speed. To address these issues, this paper proposes an object detection algorithm, CSC-YOLO (Context Guided Block, Shared Conv_Group Normalization Detection, Cross Stage Partial with 2 Partial Convolution-You Only Look Once), based on YOLOv8n for shipwreck side-scan sonar images. Firstly, to tackle the problem of small samples in shipwreck side-scan sonar images, a new dataset was constructed through offline data augmentation to expand data and intuitively enhance sample diversity, with the Mosaic algorithm integrated to strengthen the network’s generalization to the dataset. Subsequently, the Context Guided Block (CGB) module was introduced into the backbone network model to enhance the network’s ability to learn and express image features. Additionally, by employing Group Normalization (GN) techniques and shared convolution operations, we constructed the Shared Conv_GN Detection (SCGD) head, which improves the localization and classification performance of the detection head while significantly reducing the number of parameters and computational load. Finally, the Partial Convolution (PConv) was introduced and the Cross Stage Partial with 2 PConv (C2PC) module was constructed to help the network maintain effective extraction of spatial features while reducing computational complexity. The improved CSC-YOLO model, compared with the YOLOv8n model on the validation set, mean Average Precision (mAP) increases by 3.1%, Recall (R) increases by 6.4%, and the F1-measure (F1) increases by 4.7%. Furthermore, in the improved algorithm, the number of parameters decreases by 20%, the computational complexity decreases by 23.2%, and Frames Per Second (FPS) increases by 17.6%. In addition, compared with the advanced popular model, the superiority of the proposed model is proved. The subsequent experiments on real side-scan sonar images of shipwrecks fully demonstrate that the CSC-YOLO algorithm meets the requirements for actual side-scan sonar detection of underwater shipwrecks.展开更多
Underwater target detection in forward-looking sonar(FLS)images is a challenging but promising endeavor.The existing neural-based methods yield notable progress but there remains room for improvement due to overlookin...Underwater target detection in forward-looking sonar(FLS)images is a challenging but promising endeavor.The existing neural-based methods yield notable progress but there remains room for improvement due to overlooking the unique characteristics of underwater environments.Considering the problems of low imaging resolution,complex background environment,and large changes in target imaging of underwater sonar images,this paper specifically designs a sonar images target detection Network based on Progressive sensitivity capture,named ProNet.It progressively captures the sensitive regions in the current image where potential effective targets may exist.Guided by this basic idea,the primary technical innovation of this paper is the introduction of a foundational module structure for constructing a sonar target detection backbone network.This structure employs a multi-subspace mixed convolution module that initially maps sonar images into different subspaces and extracts local contextual features using varying convolutional receptive fields within these heterogeneous subspaces.Subsequently,a Scale-aware aggregation module effectively aggregates the heterogeneous features extracted from different subspaces.Finally,the multi-scale attention structure further enhances the relational perception of the aggregated features.We evaluated ProNet on three FLS datasets of varying scenes,and experimental results indicate that ProNet outperforms the current state-of-the-art sonar image and general target detectors.展开更多
为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency ide...为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency identification sonar,DIDSON)数据,开发了1种快速、准确的鱼类目标识别与计数方法。实验结果表明,YOLOv8X与ByteTrack联合方法与传统的Echoview软件识别精度接近(偏差率仅为1.36%),但处理时间显著减少(单条测线从约30 min减少至约3 min),表现出较强的实时处理能力和泛化性能。同时,通过重复实验验证了该方法的稳定性,确认其在不同场景中的可靠性。本研究方法与成果为水域鱼类资源的自动化监测提供了可靠的技术支持,可广泛地应用于大范围高频次的渔业资源监测与管理工作中。展开更多
底质声学特性是影响水下声传播的重要边界条件,其会影响声呐的效能,因而不同底质对水下声场及声呐效能的影响规律是研究的热点问题之一。该文通过仿真模拟方法,计算了不同底质类型与不同地声模型条件下水下声传播损失、被动声呐的有效...底质声学特性是影响水下声传播的重要边界条件,其会影响声呐的效能,因而不同底质对水下声场及声呐效能的影响规律是研究的热点问题之一。该文通过仿真模拟方法,计算了不同底质类型与不同地声模型条件下水下声传播损失、被动声呐的有效作用距离、探测概率与搜索效能。结果表明:极细砂质底质类型作用下的声传播损失更小,在传播距离为5 km时,传播损失最大相差65 d B;粒径更大的底质环境下的声传播损失对地声模型更敏感、受海底沉积物分层影响更小;在不同底质环境下不同声速梯度的声传播损失差异均明显;在该文设定中,极细砂质底质条件下探测概率为粉砂质黏土的2.34~3.98倍,搜索效能为10.74~11.65倍。研究表明,地声模型与底质类型对声传播与声呐效能预测有重要影响。展开更多
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00334159)the Korea Institute of Ocean Science and Technology(KIOST)project entitled“Development of Maritime Domain Awareness Technology for Sea Power Enhancement”(PEA0332).
文摘Side-scan sonar(SSS)is essential for acquiring high-resolution seafloor images over large areas,facilitat-ing the identification of subsea objects.However,military security restrictions and the scarcity of subsea targets limit the availability of SSS data,posing challenges for Automatic Target Recognition(ATR)research.This paper presents an approach that uses Cycle-Consistent Generative Adversarial Networks(CycleGAN)to augment SSS images of key subsea objects,such as shipwrecks,aircraft,and drowning victims.The process begins by constructing 3D models to generate rendered images with realistic shadows frommultiple angles.To enhance image quality,a shadowextractor and shadow region loss function are introduced to ensure consistent shadowrepresentation.Additionally,amulti-resolution learning structure enables effective training,even with limited data availability.The experimental results show that the generated data improved object detection accuracy when they were used for training and demonstrated the ability to generate clear shadow and background regions with stability.
基金supported in part by the Hainan Provincial Natural Science Foundation(Grant No.420CXTD439)Sanya Science and Technology Special Fund(Grant No.2022KJCX83)+1 种基金Institute and Local Cooperation Foundation of Sanya in China(Grant No.2019YD08)National Natural Science Foundation of China(Grant No.61661038).
文摘Underwater shipwreck identification technology, as a crucial technique in the field of marine surveying, plays a significant role in areas such as the search and rescue of maritime disaster shipwrecks. When facing the task of object detection in shipwreck side-scan sonar images, due to the complex seabed environment, it is difficult to extract object features, often leading to missed detections of shipwreck images and slow detection speed. To address these issues, this paper proposes an object detection algorithm, CSC-YOLO (Context Guided Block, Shared Conv_Group Normalization Detection, Cross Stage Partial with 2 Partial Convolution-You Only Look Once), based on YOLOv8n for shipwreck side-scan sonar images. Firstly, to tackle the problem of small samples in shipwreck side-scan sonar images, a new dataset was constructed through offline data augmentation to expand data and intuitively enhance sample diversity, with the Mosaic algorithm integrated to strengthen the network’s generalization to the dataset. Subsequently, the Context Guided Block (CGB) module was introduced into the backbone network model to enhance the network’s ability to learn and express image features. Additionally, by employing Group Normalization (GN) techniques and shared convolution operations, we constructed the Shared Conv_GN Detection (SCGD) head, which improves the localization and classification performance of the detection head while significantly reducing the number of parameters and computational load. Finally, the Partial Convolution (PConv) was introduced and the Cross Stage Partial with 2 PConv (C2PC) module was constructed to help the network maintain effective extraction of spatial features while reducing computational complexity. The improved CSC-YOLO model, compared with the YOLOv8n model on the validation set, mean Average Precision (mAP) increases by 3.1%, Recall (R) increases by 6.4%, and the F1-measure (F1) increases by 4.7%. Furthermore, in the improved algorithm, the number of parameters decreases by 20%, the computational complexity decreases by 23.2%, and Frames Per Second (FPS) increases by 17.6%. In addition, compared with the advanced popular model, the superiority of the proposed model is proved. The subsequent experiments on real side-scan sonar images of shipwrecks fully demonstrate that the CSC-YOLO algorithm meets the requirements for actual side-scan sonar detection of underwater shipwrecks.
基金supported in part by Youth Innovation Promotion Association,Chinese Academy of Sciences under Grant 2022022in part by South China Sea Nova project of Hainan Province under Grant NHXXRCXM202340in part by the Scientific Research Foundation Project of Hainan Acoustics Laboratory under grant ZKNZ2024001.
文摘Underwater target detection in forward-looking sonar(FLS)images is a challenging but promising endeavor.The existing neural-based methods yield notable progress but there remains room for improvement due to overlooking the unique characteristics of underwater environments.Considering the problems of low imaging resolution,complex background environment,and large changes in target imaging of underwater sonar images,this paper specifically designs a sonar images target detection Network based on Progressive sensitivity capture,named ProNet.It progressively captures the sensitive regions in the current image where potential effective targets may exist.Guided by this basic idea,the primary technical innovation of this paper is the introduction of a foundational module structure for constructing a sonar target detection backbone network.This structure employs a multi-subspace mixed convolution module that initially maps sonar images into different subspaces and extracts local contextual features using varying convolutional receptive fields within these heterogeneous subspaces.Subsequently,a Scale-aware aggregation module effectively aggregates the heterogeneous features extracted from different subspaces.Finally,the multi-scale attention structure further enhances the relational perception of the aggregated features.We evaluated ProNet on three FLS datasets of varying scenes,and experimental results indicate that ProNet outperforms the current state-of-the-art sonar image and general target detectors.
文摘为提高水域鱼类资源监测的自动化程度和实时分析能力,结合YOLOv8X(You only look once version 8-extra large)目标检测模型、ByteTrack(ByteTrack:a strong baseline for multi-object tracking)算法与双频识别声呐(Dual-frequency identification sonar,DIDSON)数据,开发了1种快速、准确的鱼类目标识别与计数方法。实验结果表明,YOLOv8X与ByteTrack联合方法与传统的Echoview软件识别精度接近(偏差率仅为1.36%),但处理时间显著减少(单条测线从约30 min减少至约3 min),表现出较强的实时处理能力和泛化性能。同时,通过重复实验验证了该方法的稳定性,确认其在不同场景中的可靠性。本研究方法与成果为水域鱼类资源的自动化监测提供了可靠的技术支持,可广泛地应用于大范围高频次的渔业资源监测与管理工作中。
文摘底质声学特性是影响水下声传播的重要边界条件,其会影响声呐的效能,因而不同底质对水下声场及声呐效能的影响规律是研究的热点问题之一。该文通过仿真模拟方法,计算了不同底质类型与不同地声模型条件下水下声传播损失、被动声呐的有效作用距离、探测概率与搜索效能。结果表明:极细砂质底质类型作用下的声传播损失更小,在传播距离为5 km时,传播损失最大相差65 d B;粒径更大的底质环境下的声传播损失对地声模型更敏感、受海底沉积物分层影响更小;在不同底质环境下不同声速梯度的声传播损失差异均明显;在该文设定中,极细砂质底质条件下探测概率为粉砂质黏土的2.34~3.98倍,搜索效能为10.74~11.65倍。研究表明,地声模型与底质类型对声传播与声呐效能预测有重要影响。
