Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi...Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi-category,and multi-scale target segmentation tasks.To address these challenges,this paper proposes Pyramid-MixNet,an intelligent segmentation model for high-speed rail surface damage,leveraging dataset construction and expansion alongside a feature pyramid-based encoder-decoder network with multi-attention mechanisms.The encoding net-work integrates Spatial Reduction Masked Multi-Head Attention(SRMMHA)to enhance global feature extraction while reducing trainable parameters.The decoding network incorporates Mix-Attention(MA),enabling multi-scale structural understanding and cross-scale token group correlation learning.Experimental results demonstrate that the proposed method achieves 62.17%average segmentation accuracy,80.28%Damage Dice Coefficient,and 56.83 FPS,meeting real-time detection requirements.The model’s high accuracy and scene adaptability significantly improve the detection of small-scale and complex multi-scale rail damage,offering practical value for real-time monitoring in high-speed railway maintenance systems.展开更多
针对在自然场景中,由于遮挡、视角限制和操作不当等问题,导致传感器获取的植物或器官点云不完整,提出了一种基于多尺度特征提取模块结合点云金字塔解码器(Multi-scale feature extraction model with point cloud pyramid decoder,MSF-P...针对在自然场景中,由于遮挡、视角限制和操作不当等问题,导致传感器获取的植物或器官点云不完整,提出了一种基于多尺度特征提取模块结合点云金字塔解码器(Multi-scale feature extraction model with point cloud pyramid decoder,MSF-PPD)的叶片形状补全网络。首先,采用多尺度特征提取模块实现不同维度特征信息的全局提取和融合,其次,通过点云金字塔解码器进行叶片点云的多阶段生成补全,最终得到完整的目标叶片形状。使用曲面参数方程构建绿萝叶片仿真模型库,并将其离散成点云作为网络模型训练的训练集和验证集,使用Kinect v2相机获取绿萝叶片点云作为网络模型补全性能评估的测试集。试验结果表明,本文网络结构对叶片点云补全的效果理想,证明本文方法能够对遮挡情况下的绿萝叶片进行高效、完整的补全。展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 6226070954Jiangxi Provincial Key R&D Programme under Grant 20244BBG73002.
文摘Rail surface damage is a critical component of high-speed railway infrastructure,directly affecting train operational stability and safety.Existing methods face limitations in accuracy and speed for small-sample,multi-category,and multi-scale target segmentation tasks.To address these challenges,this paper proposes Pyramid-MixNet,an intelligent segmentation model for high-speed rail surface damage,leveraging dataset construction and expansion alongside a feature pyramid-based encoder-decoder network with multi-attention mechanisms.The encoding net-work integrates Spatial Reduction Masked Multi-Head Attention(SRMMHA)to enhance global feature extraction while reducing trainable parameters.The decoding network incorporates Mix-Attention(MA),enabling multi-scale structural understanding and cross-scale token group correlation learning.Experimental results demonstrate that the proposed method achieves 62.17%average segmentation accuracy,80.28%Damage Dice Coefficient,and 56.83 FPS,meeting real-time detection requirements.The model’s high accuracy and scene adaptability significantly improve the detection of small-scale and complex multi-scale rail damage,offering practical value for real-time monitoring in high-speed railway maintenance systems.
文摘针对在自然场景中,由于遮挡、视角限制和操作不当等问题,导致传感器获取的植物或器官点云不完整,提出了一种基于多尺度特征提取模块结合点云金字塔解码器(Multi-scale feature extraction model with point cloud pyramid decoder,MSF-PPD)的叶片形状补全网络。首先,采用多尺度特征提取模块实现不同维度特征信息的全局提取和融合,其次,通过点云金字塔解码器进行叶片点云的多阶段生成补全,最终得到完整的目标叶片形状。使用曲面参数方程构建绿萝叶片仿真模型库,并将其离散成点云作为网络模型训练的训练集和验证集,使用Kinect v2相机获取绿萝叶片点云作为网络模型补全性能评估的测试集。试验结果表明,本文网络结构对叶片点云补全的效果理想,证明本文方法能够对遮挡情况下的绿萝叶片进行高效、完整的补全。
