In this paper, we propose a novel seismic blind deconvolution approach based on the Spearman’s rho in the case of band-limited seismic data with a low dominant frequency and short data records. The Spearman’s rho is...In this paper, we propose a novel seismic blind deconvolution approach based on the Spearman’s rho in the case of band-limited seismic data with a low dominant frequency and short data records. The Spearman’s rho is a measure of the dependence between two continuous random variables without the influence of the marginal distributions, by which a new criterion for blind deconvolution is constructed. The optimization program for new criterion of blind deconvolution is performed by applying Neidell’s wavelet model to the inverse filter. The noise-free and noisy synthetic data, onshore seismic trace in the Ordos Basin, and offshore stacked section in the Bohai Bay Basin examples show good results of the method.展开更多
针对煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂工况环境因素导致煤矸识别存在误检、漏检以及检测精度低的问题,提出一种基于CFS-YOLO算法的煤矸智能识别模型。采用ConvNeXt V2(Convolutional Neural Network with NeXt Units...针对煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂工况环境因素导致煤矸识别存在误检、漏检以及检测精度低的问题,提出一种基于CFS-YOLO算法的煤矸智能识别模型。采用ConvNeXt V2(Convolutional Neural Network with NeXt Units Version 2)特征提取模块替换主干网络末端的2个C3(Cross Stage Partial Bottle Neck Mudule)模块,通过将掩码自动编码器(Masked Autoencoders,MAE)和全局响应归一化(Global Response Normalization,GRN)层添加到ConvNeXt架构中,有效缓解特征崩溃问题以及保持特征在网络传递过程中的多样性;采用Focal-EIOU(Focal and Efficient Intersection Over Union)损失函数替换原CIOU(Computer Intersection Over Union)损失函数,通过其Focal-Loss机制和调整样本权重的方式优化边界框回归任务中的样本不平衡问题,提高模型的收敛速度和定位精度;添加无参注意力机制(Simple Attention Mechanism,SimAM)于主干网络每个C3模块的后端,凭借其注意力权重自适应调整策略,提升模型对尺度变化较大或低分辨率煤矸目标关键特征的提取能力。通过消融试验和对比试验验证所提CFS-YOLO模型的有效性与优越性。试验结果表明:CFS-YOLO模型对于煤矸在煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂环境下的检测效果均得到有效提高,模型的平均精度均值达到90.2%,相较于原YOLOv5s模型的平均精度均值提高了3.7%,平均检测速度达到90.09 FPS,可充分满足煤矸实时检测的需求。同时与YOLOv5s、YOLOv7-tiny与YOLOv8n等6种YOLO系列算法相比,CFS-YOLO模型对煤矿复杂环境的适应性最强且综合检测性能最佳,可为煤矸的智能高效分选提供技术支持。展开更多
文摘In this paper, we propose a novel seismic blind deconvolution approach based on the Spearman’s rho in the case of band-limited seismic data with a low dominant frequency and short data records. The Spearman’s rho is a measure of the dependence between two continuous random variables without the influence of the marginal distributions, by which a new criterion for blind deconvolution is constructed. The optimization program for new criterion of blind deconvolution is performed by applying Neidell’s wavelet model to the inverse filter. The noise-free and noisy synthetic data, onshore seismic trace in the Ordos Basin, and offshore stacked section in the Bohai Bay Basin examples show good results of the method.
文摘针对煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂工况环境因素导致煤矸识别存在误检、漏检以及检测精度低的问题,提出一种基于CFS-YOLO算法的煤矸智能识别模型。采用ConvNeXt V2(Convolutional Neural Network with NeXt Units Version 2)特征提取模块替换主干网络末端的2个C3(Cross Stage Partial Bottle Neck Mudule)模块,通过将掩码自动编码器(Masked Autoencoders,MAE)和全局响应归一化(Global Response Normalization,GRN)层添加到ConvNeXt架构中,有效缓解特征崩溃问题以及保持特征在网络传递过程中的多样性;采用Focal-EIOU(Focal and Efficient Intersection Over Union)损失函数替换原CIOU(Computer Intersection Over Union)损失函数,通过其Focal-Loss机制和调整样本权重的方式优化边界框回归任务中的样本不平衡问题,提高模型的收敛速度和定位精度;添加无参注意力机制(Simple Attention Mechanism,SimAM)于主干网络每个C3模块的后端,凭借其注意力权重自适应调整策略,提升模型对尺度变化较大或低分辨率煤矸目标关键特征的提取能力。通过消融试验和对比试验验证所提CFS-YOLO模型的有效性与优越性。试验结果表明:CFS-YOLO模型对于煤矸在煤矿高噪声、低照度、运动模糊与大批量煤矸混杂等复杂环境下的检测效果均得到有效提高,模型的平均精度均值达到90.2%,相较于原YOLOv5s模型的平均精度均值提高了3.7%,平均检测速度达到90.09 FPS,可充分满足煤矸实时检测的需求。同时与YOLOv5s、YOLOv7-tiny与YOLOv8n等6种YOLO系列算法相比,CFS-YOLO模型对煤矿复杂环境的适应性最强且综合检测性能最佳,可为煤矸的智能高效分选提供技术支持。
