检索结果-内蒙古大学图书馆

image semantic segmentation method based on improved ERFNet model

JOURNAL OF ENGINEERING-JOE 2022年第2期2022卷 180-190页

作者： Ye, Dexue Han, Rubing Lanzhou Univ Finance & Econ Longqiao Coll Dept Informat Engn 68 Weile Ave Lanzhou 730101 Gansu Peoples R China

In order to solve the problems in the existing image semantic segmentation methods, such as the poor segmentation accuracy of small target object and the difficulty in segmentation of small target area, an image semantic segmentation method based on improved ERFNet model is proposed. Firstly, combining the asymmetric residual module and the weak bottleneck module, the ERFNet network model is improved to improve the running speed and reduce the loss of precision. Then, global pooling is used to fuse the feature channels after pyramid pooling to preserve more important feature information. Finally, the network model is implemented based on PyTorch deep learning framework, and the proposed method is demonstrated by experiments, in which the model retraining method is adopted to learn and train it. The experimental results show that the proposed method improves the segmentation ability of small-scale objects and reduces the possibility of misclassification. The average pixel accuracy (MPA) and average intersection merge ratio (MIOU) of the proposed method are higher than those of other contrast methods.

关键词： poor segmentation accuracy model retraining method convolutional neural nets image segmentation deep learning (artificial intelligence) asymmetric residual module object detection existing image semantic segmentation methods weak bottleneck module target object improved ERFNet model learning (artificial intelligence) segmentation ability image semantic segmentation method ERFNet network model contrast methods feature extraction

来源：评论

学校读者我要写书评

暂无评论

image semantic segmentation method based on GAN network and ERFNet model

引用

JOURNAL OF ENGINEERING-JOE 2021年第4期2021卷 189-200页

作者： Dong, Chaoxian Sanmenxia Polytech Coll Informat Media Sanmenxia Henan Peoples R China

This article addresses the problems of traditional methods in image semantic segmentation, such as insufficient segmentation of small-scale targets and weak anti-noise ability. A method of image semantic segmentation using a generative adversarial network (GAN) combined with ERFNet model is proposed. First, the asymmetric residual module (ARM) and weak bottleneck module are used to improve the ERFNet network model. Moreover, dilated convolution is used to reduce information loss and improve the performance of small target image semantic segmentation. Then, a U-shaped network is used to improve the generator of GAN to avoid low-level information sharing. In addition, the residual module is introduced into convolution layer to realise the dynamic adjustment of generator weight. Finally, the improved ERFNet model is used as the input of the generator to output the segmented image. It is input to the discriminator together with the label for judgment, which further improves the performance of image semantic segmentation. The proposed method is demonstrated experimentally based on the PyTorch platform. The results show that mean pixel accuracy and mean intersection over the union of the proposed method on the CamVid and Cityscapes datasets are higher than those of other comparisons. In addition, the execution time is short, and the overall image semantic segmentation performance is relatively ideal.

关键词： image semantic segmentation method Computer vision and image processing techniques ARM image segmentation Cityscapes datasets Optical, image and video signal processing CamVid datasets asymmetric residual module U neural nets ERFNet network model weak bottleneck module generative adversarial network image classification insufficient segmentation U-shaped network GAN network PyTorch platform Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

image semantic segmentation method based on GAN network and ENet model

引用

JOURNAL OF ENGINEERING-JOE 2021年第10期2021卷 594-604页

作者： Li, Huiyi Hunan Mass Media Vocat & Tech Coll Changsha Hunan Peoples R China

Currently, image semantic segmentation has problems such as low accuracy and long running time. This paper proposes an image semantic segmentation method based on generative adversarial network and ENet model combined with deep neural network. This method first improves the network model of generative adversarial network. Ensure the high resolution of the generated image and achieve high similarity with the real image. While ensuring the high accuracy of image semantic segmentation, it effectively improves the real-time performance of network processing. The proposed method is verified based on public data sets. The experimental results show that the segmentation accuracy of this method can reach more than 93%, and the simulation running time is less than 0.171 s, which shows good high accuracy and high real-time performance. A feasible strategy is proposed for the further productization of semantic segmentation.

关键词： image semantic segmentation method Computer vision and image processing techniques deep neural network GAN network deep learning (artificial intelligence) Optical, image and video signal processing generative adversarial network network processing network model image segmentation real-time performance ENet model

来源：评论

学校读者我要写书评

暂无评论

image semantic segmentation method based on GAN network and FCN model

引用

JOURNAL OF ENGINEERING-JOE 2022年第1期2022卷 1-9页

作者： Zhao, Lixin Sanmenxia Polytech Deans Off 42 Xiaoshan West Rd Sanmenxia 472000 Henan Peoples R China

In order to improve the accuracy of image semantic segmentation, an image semantic segmentation method based on generative adversarial network (GAN) and fully convolutional network (FCN) model is proposed. First of all, the network structure of the generator is improved. Introducing the residual module in the convolutional layer for difference learning makes the network structure sensitive to changes in the output, so as to better adjust the weight of the generator. Second in order to reduce the number of parameters and calculations, a small convolution kernel is used to halve the number of channels of the input feature map before using the large convolution kernel. Finally, the output of the convolutional layer and the output of the deconvolutional layer are connected by using the idea of a U-shaped network to avoid low-level information sharing. The proposed method was experimentally demonstrated on the PASCAL VOC 2012 and CamVid datasets. Experimental results show that the proposed method effectively improves the accuracy of image segmentation, and avoids inaccurate detection caused by insufficient image pixel information and noise interference. Its mean pixel accuracy (MPA) and mean intersection over union (MIOU) are higher than other comparison methods.

关键词： U-shaped network small convolution kernel GAN network mean pixel accuracy convolutional neural nets difference learning convolutional layer residual module network structure improvement learning (artificial intelligence) image semantic segmentation method feature extraction image segmentation input feature map generator weight MPA deconvolutional layer MIOU generative adversarial network FCN model fully convolutional network model mean intersection over union

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：