Recent advancements in remote sensing technology have made it easier to detect surface faults.Deep learning,especially convolutional models,offers new potential for automatic fault detection from remote sensing imager...Recent advancements in remote sensing technology have made it easier to detect surface faults.Deep learning,especially convolutional models,offers new potential for automatic fault detection from remote sensing imagery.However,these models often struggle with segmentation accuracy due to their limitations in handling spatial hierarchies and short-range dependencies.They process data in local contexts,which is insufficient for tasks requiring an understanding of global structures,like fault detection.This leads to inaccurate boundary divisions and incomplete fault trace detections.To address these issues,the Convolution Holographic Reduced Representations-Based Unet(CHRRA-Unet)is introduced.This U-shaped network combines convolution and a novel attention-based transformer for remote sensing image segmentation.By extracting both local and global features,the CHRRA-Unet significantly improves the detection of geological faults in remote sensing images.By incorporating a convolutional module(CM)and holographic reduced representation attention(HRRA),local and global feature extraction is improved.To minimize computational complexity,the traditional Multi-Layer Per-ceptron(MLP)is replaced with the Local Perception Module(LPM).The Multi-Feature Conversion Module(MFCM)ensures an effective combination of feature maps during encoding and decoding,enhancing the net-work’s ability to accurately detect fault traces.Extensive experiments show that CHRRA-Unet achieves a high accuracy rate of 97.20%in remote sensing image segmentation,outperforming existing models and providing superior fault detection capabilities over current methods.展开更多
针对背景复杂、尺度变化较大、被遮挡情况下机械外破隐患目标检测精度不高,容易出现错检、漏检的问题,文中提出了一种改进YOLOv7(you only look once version 7)的机械外破隐患目标检测算法。文章在检测头网络中添加Swin Transformer注...针对背景复杂、尺度变化较大、被遮挡情况下机械外破隐患目标检测精度不高,容易出现错检、漏检的问题,文中提出了一种改进YOLOv7(you only look once version 7)的机械外破隐患目标检测算法。文章在检测头网络中添加Swin Transformer注意力机制提高对多尺度特征的提取能力,然后在主干网络中将部分卷积模块替换为深度可分离卷积,降低模型运算成本,采用Focal-EIOU(Focal and enhanced intersection over union)损失函数优化预测框,最后引入Mish激活函数增强网络的泛化能力,提高模型在复杂背景、目标部分被遮挡情况下的检测性能。实验结果表明,改进后的算法较原YOLOv7在准确率、召回率和平均精度均值上分别提高了5.2%、10.6%和5.2%,较其他主流算法在检测精度和模型体积上有着明显的优势,验证了改进方法的有效性,为复杂场景下机械外破隐患目标的边缘识别提供算法支持。展开更多
基金funded by Comprehensive Remote Sensing for Refined Investigation and Risk Assessment of Geological Hazards in Yunnan Province,grant number YCZH[2020]-68 and The APC was funded by Construction of Yunnan Geological Hazard Identification Center,YCZH[2021]-23 and Fine investigation and risk assessment of geological hazards in key regions of Yunnan Province,YNGH[2021]-168F.Also support was provided by the Chinese Academy of Geological Sciences Basal Research Fund(No.JKYDM2025110)the Open Project Program of Hebei Province Collaborative Innovation Center for Strategic Critical Mineral Research,Hebei GEO University(No.HGUXT-2024-1)+1 种基金the Geological Survey Project of the China Geological Survey(DD20230366)the Open Project of the Technology Innovation Center for Deep Gold Resources Exploration and Mining,Ministry of Natural Resources(No.LDKF-2023BZX-20).
文摘Recent advancements in remote sensing technology have made it easier to detect surface faults.Deep learning,especially convolutional models,offers new potential for automatic fault detection from remote sensing imagery.However,these models often struggle with segmentation accuracy due to their limitations in handling spatial hierarchies and short-range dependencies.They process data in local contexts,which is insufficient for tasks requiring an understanding of global structures,like fault detection.This leads to inaccurate boundary divisions and incomplete fault trace detections.To address these issues,the Convolution Holographic Reduced Representations-Based Unet(CHRRA-Unet)is introduced.This U-shaped network combines convolution and a novel attention-based transformer for remote sensing image segmentation.By extracting both local and global features,the CHRRA-Unet significantly improves the detection of geological faults in remote sensing images.By incorporating a convolutional module(CM)and holographic reduced representation attention(HRRA),local and global feature extraction is improved.To minimize computational complexity,the traditional Multi-Layer Per-ceptron(MLP)is replaced with the Local Perception Module(LPM).The Multi-Feature Conversion Module(MFCM)ensures an effective combination of feature maps during encoding and decoding,enhancing the net-work’s ability to accurately detect fault traces.Extensive experiments show that CHRRA-Unet achieves a high accuracy rate of 97.20%in remote sensing image segmentation,outperforming existing models and providing superior fault detection capabilities over current methods.
文摘针对背景复杂、尺度变化较大、被遮挡情况下机械外破隐患目标检测精度不高,容易出现错检、漏检的问题,文中提出了一种改进YOLOv7(you only look once version 7)的机械外破隐患目标检测算法。文章在检测头网络中添加Swin Transformer注意力机制提高对多尺度特征的提取能力,然后在主干网络中将部分卷积模块替换为深度可分离卷积,降低模型运算成本,采用Focal-EIOU(Focal and enhanced intersection over union)损失函数优化预测框,最后引入Mish激活函数增强网络的泛化能力,提高模型在复杂背景、目标部分被遮挡情况下的检测性能。实验结果表明,改进后的算法较原YOLOv7在准确率、召回率和平均精度均值上分别提高了5.2%、10.6%和5.2%,较其他主流算法在检测精度和模型体积上有着明显的优势,验证了改进方法的有效性,为复杂场景下机械外破隐患目标的边缘识别提供算法支持。
