典型文献
Optimal CNN-based semantic segmentation model of cutting slope images
文献摘要：
This paper utilizes three popular semantic segmentation networks,specifically DeepLab v3+,fully convolutional network(FCN),and U-Net to qualitively analyze and identify the key components of cutting slope images in complex scenes and achieve rapid image-based slope detection.The elements of cutting slope images are divided into 7 categories.In order to determine the best algorithm for pixel level classification of cutting slope images,the networks are compared from three aspects:a)different neural networks,b)different feature extractors,and c)2 different optimization algorithms.It is found that DeepLab v3+with Resnet18 and Sgdm performs best,FCN 32s with Sgdm takes the second,and U-Net with Adam ranks third.This paper also analyzes the segmentation strategies of the three networks in terms of feature map visualization.Results show that the contour generated by DeepLab v3+(combined with Resnetl8 and Sgdm)is closest to the ground truth,while the resulting contour of U-Net(combined with Adam)is closest to the input images.
文献关键词：
中图分类号：
作者姓名：
Mansheng LIN;Shuai TENG;Gongfa CHEN;Jianbing LV;Zhongyu HAO
作者机构：
School of Civil and Transportation Engineering,Guangdong University of Technology,Guangzhou 510006,China;JSTI Group Guangdong Inspection and Certification Co.Ltd,Nanjing 210000,China
文献出处：
引用格式：
[1]Mansheng LIN;Shuai TENG;Gongfa CHEN;Jianbing LV;Zhongyu HAO-.Optimal CNN-based semantic segmentation model of cutting slope images)[J].结构与土木工程前沿,2022(04):414-433
A类：
qualitively,v3+with,Sgdm,Resnetl8
B类：
Optimal,semantic,segmentation,model,cutting,slope,images,This,paper,utilizes,three,popular,networks,specifically,DeepLab,fully,convolutional,FCN,Net,identify,key,components,complex,scenes,achieve,rapid,detection,elements,divided,into,categories,In,order,determine,best,pixel,level,classification,compared,from,aspects,different,neural,feature,extractors,optimization,algorithms,It,found,that,Resnet18,performs,32s,takes,second,Adam,ranks,third,also,analyzes,strategies,terms,map,visualization,Results,show,contour,generated,by,combined,closest,ground,truth,while,resulting,input
AB值：
0.498502
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
