Image semantic segmentation method based on improved ERFNet model

doi:10.1049/tje2.12104

LZUFE-KMS

	Image semantic segmentation method based on improved ERFNet model
	Ye, Dexue; Han, Rubing
	2022-02-01
发表期刊	Journal of Engineering
卷号	2022 期号:2 页码:180-190
摘要	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. © 2021 The Authors. The Journal of Engineering published by John Wiley & Sons Ltd on behalf of The Institution of Engineering and Technology
关键词	Deep learning Image enhancement Image segmentation Semantics Feature information Image semantics Important features Network models Running speed Segmentation accuracy Segmentation methods Semantic segmentation Small targets Target object
DOI	10.1049/tje2.12104
收录类别	EI ; ESCI
ISSN	2051-3305
语种	英语
WOS研究方向	Engineering
WOS类目	Engineering, Multidisciplinary
WOS记录号	WOS:000714858100001
出版者	John Wiley and Sons Inc
EI入藏号	20214511118959
EI主题词	Semantic Segmentation
EI分类号	461.4 Ergonomics and Human Factors Engineering ; 723.4 Artificial Intelligence
原始文献类型	Journal article (JA)
EISSN	2051-3305
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.lzufe.edu.cn/handle/39EH0E1M/31967
专题	兰州财经大学
作者单位	Department of Information Engineering, Longqiao College of Lanzhou University of Finance and Economics, Gansu, Lanzhou, China
第一作者单位	兰州财经大学
推荐引用方式 GB/T 7714	Ye, Dexue,Han, Rubing. Image semantic segmentation method based on improved ERFNet model[J]. Journal of Engineering,2022,2022(2):180-190.
APA	Ye, Dexue,&Han, Rubing.(2022).Image semantic segmentation method based on improved ERFNet model.Journal of Engineering,2022(2),180-190.
MLA	Ye, Dexue,et al."Image semantic segmentation method based on improved ERFNet model".Journal of Engineering 2022.2(2022):180-190.