钻井过程中掉块的监测与识别对于及时发现和减缓井壁不稳定和卡钻等井下复杂至关重要。当前,掉块监测主要依赖人工监测,但该方法易受主观影响且耗时较长,存在滞后性。为此,提出一种基于3D视觉的钻井掉块自动识别与特征判断方法。该方法...钻井过程中掉块的监测与识别对于及时发现和减缓井壁不稳定和卡钻等井下复杂至关重要。当前,掉块监测主要依赖人工监测,但该方法易受主观影响且耗时较长,存在滞后性。为此,提出一种基于3D视觉的钻井掉块自动识别与特征判断方法。该方法利用3D成像技术来获取振动筛上返出掉块的三维深度信息,以构建掉块图像样本库,并以You Only Look Once v8s(YOLOv8s)为基础目标检测模型,结合引入的卷积块注意力模块(CBAM),建立了CBAM-YOLOv8s掉块目标检测模型。通过将3D相机实时获取的三维深度信息集成到模型中,不仅实现了对掉块的实时监测和准确识别,还能够在识别的基础上判断其形状特征,从而实现井壁失稳性分析和井眼状况的实时评估。实验结果表明:CBAM模块的引入增强了模型对掉块关键特征的关注;集成实时获取三维深度信息的CBAM-YOLOv8s模型对掉块识别精确率和召回率分别达到96.01%和93.40%;扩展模型在掉块形状特征预测中的误差均小于10%。结论认为,基于3D视觉技术的实时掉块可视化监测方法具有良好的可行性和有效性,能够准确识别出掉块及其形状特征,这一方法将为井壁稳定性早期预警和井下复杂提供支持。展开更多
Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling cap...Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling capability of the model through the self-attention mechanism,better segmentation performance can be achieve.Moreover,the high computational cost of Transformer has motivated researchers to explore more efficient models,such as the Mamba model based on state-space modeling(SSM),and for the field of medical segmentation,reducing the number of model parameters is also necessary.In this study,a novel asymmetric model called LA-UMamba was proposed,which integrates visual Mamba module to efficiently capture complex visual features and remote dependencies.The classical design of U-Net was adopted in the upsampling phase to help reduce the number of references and recover more details.To mitigate the information loss problem,an auxiliary U-Net downsampling layer was designed to focus on sizing without extracting features,thus enhancing the protection of input information while maintaining the efficiency of the model.The experiments were conducted on the ACDC MRI cardiac segmentation dataset,and the results showed that the proposed LA-UMamba achieves proved performance compared to the baseline model in several evaluation metrics,such as IoU,Accuracy,Precision,HD and ASD,which improved that the model is successful in optimizing the detail processing and reducing the complexity of the model,providing a new perspective for further optimization of medical image segmentation techniques.展开更多
Ship detection via spaceborne synthetic aperture radar(SAR)has become a research hotspot.However,existing small ship detection methods based on the radar signal domain and SAR image features cannot obtain highly accur...Ship detection via spaceborne synthetic aperture radar(SAR)has become a research hotspot.However,existing small ship detection methods based on the radar signal domain and SAR image features cannot obtain highly accurate results because of the obvious coherent speckle noise at sea and strong reflection interference from near‑shore objects.To resolve the above problems,this study proposes a dual‑domain joint dense multiple small ship target detection method for spaceborne SAR image that simultaneously detects objects in the image and frequency domains.This method uses an attention mechanism module and algorithm structure adjustments to improve the small ship target feature mining ability.In the frequency‑based image generation,extreme signal strength values are detected in the azimuth and range directions,with the results of the two complementing each other to realize dual‑domain joint small ship target detection.The comprehensive qualitative and quantitative evaluation results show that the proposed method can attain a final precision rate of 92.25%and achieve accurate results for SAR ship detection in open‑sea,coastal,and port area ships.The test results for the self‑built SAR small‑ship dataset demonstrate the effectiveness and universality of the method.展开更多
文摘钻井过程中掉块的监测与识别对于及时发现和减缓井壁不稳定和卡钻等井下复杂至关重要。当前,掉块监测主要依赖人工监测,但该方法易受主观影响且耗时较长,存在滞后性。为此,提出一种基于3D视觉的钻井掉块自动识别与特征判断方法。该方法利用3D成像技术来获取振动筛上返出掉块的三维深度信息,以构建掉块图像样本库,并以You Only Look Once v8s(YOLOv8s)为基础目标检测模型,结合引入的卷积块注意力模块(CBAM),建立了CBAM-YOLOv8s掉块目标检测模型。通过将3D相机实时获取的三维深度信息集成到模型中,不仅实现了对掉块的实时监测和准确识别,还能够在识别的基础上判断其形状特征,从而实现井壁失稳性分析和井眼状况的实时评估。实验结果表明:CBAM模块的引入增强了模型对掉块关键特征的关注;集成实时获取三维深度信息的CBAM-YOLOv8s模型对掉块识别精确率和召回率分别达到96.01%和93.40%;扩展模型在掉块形状特征预测中的误差均小于10%。结论认为,基于3D视觉技术的实时掉块可视化监测方法具有良好的可行性和有效性,能够准确识别出掉块及其形状特征,这一方法将为井壁稳定性早期预警和井下复杂提供支持。
文摘Deep learning techniques are revolutionizing the developmentof medical image segmentation.With the advancement of Transformer models,especially ViT and Swin-Transformer,which enhances the remote-dependent modeling capability of the model through the self-attention mechanism,better segmentation performance can be achieve.Moreover,the high computational cost of Transformer has motivated researchers to explore more efficient models,such as the Mamba model based on state-space modeling(SSM),and for the field of medical segmentation,reducing the number of model parameters is also necessary.In this study,a novel asymmetric model called LA-UMamba was proposed,which integrates visual Mamba module to efficiently capture complex visual features and remote dependencies.The classical design of U-Net was adopted in the upsampling phase to help reduce the number of references and recover more details.To mitigate the information loss problem,an auxiliary U-Net downsampling layer was designed to focus on sizing without extracting features,thus enhancing the protection of input information while maintaining the efficiency of the model.The experiments were conducted on the ACDC MRI cardiac segmentation dataset,and the results showed that the proposed LA-UMamba achieves proved performance compared to the baseline model in several evaluation metrics,such as IoU,Accuracy,Precision,HD and ASD,which improved that the model is successful in optimizing the detail processing and reducing the complexity of the model,providing a new perspective for further optimization of medical image segmentation techniques.
基金supported by the Foundation Strengthening Fund Project(No.2021-JCJQ-JJ0251)in part by the National Natural Science Foundation of China(Nos.42301384 and 42271448)。
文摘Ship detection via spaceborne synthetic aperture radar(SAR)has become a research hotspot.However,existing small ship detection methods based on the radar signal domain and SAR image features cannot obtain highly accurate results because of the obvious coherent speckle noise at sea and strong reflection interference from near‑shore objects.To resolve the above problems,this study proposes a dual‑domain joint dense multiple small ship target detection method for spaceborne SAR image that simultaneously detects objects in the image and frequency domains.This method uses an attention mechanism module and algorithm structure adjustments to improve the small ship target feature mining ability.In the frequency‑based image generation,extreme signal strength values are detected in the azimuth and range directions,with the results of the two complementing each other to realize dual‑domain joint small ship target detection.The comprehensive qualitative and quantitative evaluation results show that the proposed method can attain a final precision rate of 92.25%and achieve accurate results for SAR ship detection in open‑sea,coastal,and port area ships.The test results for the self‑built SAR small‑ship dataset demonstrate the effectiveness and universality of the method.
