Image semantic segmentation method based on improved ERFNet model

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, combin...

Full description

Saved in:

Bibliographic Details
Published in:	Journal of engineering (Stevenage, England) Vol. 2022; no. 2; pp. 180 - 190
Main Authors:	Ye, Dexue, Han, Rubing
Format:	Journal Article
Language:	English
Published:	London John Wiley & Sons, Inc 01-02-2022
Subjects:	Accuracy Algorithms Classification Decision trees Deep learning Geographic information systems Image segmentation Methods Modules Neural networks Performance evaluation Remote sensing Semantic segmentation Semantics Wavelet transforms
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
ISSN:	2051-3305 2051-3305
DOI:	10.1049/tje2.12104