摘要
煤岩图像语义分割技术是煤岩界面识别的重要研究方向,现有的语义分割模型通常依赖于大样本数据集进行训练,然而目前已标注的煤岩图像数据样本难以获取,并且缺乏公开数据集。针对以上问题,提出了一种基于改进U-net模型的样本煤岩界面图像分割模型。将裁剪后具有更强特征提取能力且结构上更为简单的VGG16替换U-net的原始骨干特征提取网络,提升对图像信息的特征提取能力并获得更快的训练速度,在U-net网络的跳跃连接和解码器上采样部分引入注意力机制模块,对提取的特征层进行处理,提升模型对煤岩界面图像关键特征的提取能力,提高分割精度。使用迁移学习方法对改进的模型进行预训练,提高模型泛化能力同时避免过拟合,使模型更适用于小样本数据集训练。通过使用自制的煤岩界面数据集对所改进的网络模型性能进行验证,并将该模型与经典Unet、DeepLabv3+、PspNet、HrNet网络模型进行了对比。试验结果表明:在同样使用由125幅煤岩界面图片构建的小样本数据集进行训练的情况下,所提改进模型相较于经典U-net模型在分割精确度和检测效率方面都有显著提升,模型精确度提高了1.84%,平均交并比提高了5.34%,类别平均像素准确率提高了0.48%,检测速度增幅为5.3%。同时,与其他网络模型相比,所提改进模型在小样本煤岩界面图像的语义分割中优势显著,表明所提改进思路的有效性。
In recent years,image semantic segmentation methods have been widely applied in coal rock interface recogni-tion research.However,currently labeled coal rock image data samples are difficult to obtain,and there is a lack of public data-sets.Moreover,existing semantic segmentation models usually rely on large sample datasets for training.In response to the a-bove issues,this article proposes a small sample coal rock interface image segmentation model based on an improved U-net model.Firstly,the VGG16,which has stronger feature extraction capability and simpler structure,is used as the backbone net-work,which can enhance image feature extraction efficiency and achieve faster training speed.Secondly,during the training of the improved network model,the transfer learning method is adopted to improve the model accuracy and avoid overfitting,mak-ing the model more suitable for training with small sample datasets.Additionally,the attention mechanism module is introduced in the skip connections and upsampling section of the U-net network,which helps the model capture key features,enhances the model′s feature extraction capability,and improves the accuracy of coal-rock interface image segmentation.The performance of the improved network model in this study is verified using a homemade coal-rock interface dataset.By comparing this model with the classical U-net,DeepLabv3+,PSPnet,and HRNet network models,experiment results show that under the same train-ing conditions using a small sample dataset constructed from 125 coal-rock interface images,the improved model in this study has a significant improvement in segmentation accuracy and detection speed compared to the original U-net model.The model′s accuracy has improved by 1.84%,the mean intersection over union has increased by 5.34%,the average pixel accura-cy of the class has increased by 0.48%,and the detection speed has increased by 5.3%.At the same time,compared with oth-er network models,the proposed improved model has a significant advantage in the semantic segmen
作者
卢才武
宋义良
江松
章赛
王懋
纪凡
LU Caiwu;SONG Yiliang;JIANG Song;ZHANG Sai;WANG Mao;JI Fan(School of Resource Engineering,Xi′an University of Architecture and Technology,Xi′an 710055,China;Xi′an Key Laboratory for Intelligent Industrial Perception,Calculation and Decision,Xi′an 710055,China;Xi′an Youmai Intelligent Mining Research Institute Co.,Ltd.,Xi′an 710055,China;School of Big Data and Artificial Intelligence,Shaanxi Technical College of Finance&Econnomics,Xianyang 712000,China)
出处
《金属矿山》
CAS
北大核心
2024年第1期149-157,共9页
Metal Mine
基金
陕西省自然科学联合基金项目(编号:2019JLP-16)
陕西省自然科学基金青年项目(编号:2023-JC-QN-0513)
陕西省教育厅服务地方专项重点培育项目(编号:21JC024)。
关键词
煤岩识别
语义分割
少样本学习
U-net
深度学习
机器视觉技术
coal-rock recognition
semantic segmentation
few-shot learning
U-net
deep learning
machine vision tech-nique
