Asymmetric Parallel Semantic Segmentation Model Based on Full Convolutional Neural Network

LI Bao-qi; HE Yu-yao; HE Ling-jiao; QIANG Wei

doi:10.3969/j.issn.0372-2112.2019.05.012

您当前的位置：

首页 >

文章列表页 >

Asymmetric Parallel Semantic Segmentation Model Based on Full Convolutional Neural Network

更新时间：2025-07-16

- Asymmetric Parallel Semantic Segmentation Model Based on Full Convolutional Neural Network
- Acta Electronica Sinica Vol. 47, Issue 5, Pages: 1058-1064(2019)
- 作者机构：
  
  西北工业大学航海学院,陕西,西安,710072
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61271143)
- DOI：10.3969/j.issn.0372-2112.2019.05.012
  CLC： TP183
- Published Online：25 May 2019，
  
  Published：2019
- 稿件说明：
移动端阅览
LI Bao-qi, HE Yu-yao, HE Ling-jiao, et al. Asymmetric Parallel Semantic Segmentation Model Based on Full Convolutional Neural Network[J]. Acta Electronica Sinica, 2019, 47(5): 1058-1064.
DOI：

LI Bao-qi, HE Yu-yao, HE Ling-jiao, et al. Asymmetric Parallel Semantic Segmentation Model Based on Full Convolutional Neural Network[J]. Acta Electronica Sinica, 2019, 47(5): 1058-1064. DOI： 10.3969/j.issn.0372-2112.2019.05.012.

摘要

针对RGB图像具有丰富的色彩细节特征，红外图像对目标轮廓、尺寸、边界等外形特征有较高敏感度的特点，提出了一种非对称并行语义分割模型APFCN（Asymmetric Parallelism Fully Convolutional Networks）.APFCN上路设计了一个卷积核尺寸非统一的五层空洞卷积网络来提取红外图像目标高层轮廓特征；下路沿用卷积加池化网络提取RGB图像三个尺度上的细节特征；后端将红外图像高层特征与RGB图像三个尺度的细节特征进行融合，并将4倍上采样后的融合特征作为语义分割输出.结果表明，APFCN在像素精度和交并比等方面均优于FCN（输入为RGB图像或红外图像），适用于背景一致下地面目标的语义分割任务.

Abstract

Aiming at that RGB image is rich in color details of scene and infrared image is sensitive to outline、size and boundary of target

a novel semantic segmentation model APFCN (Asymmetric Parallelism Fully Convolutional Networks) is proposed.In the upper part of APFCN

a five layer dilation convolution network

where the five kernel sizes are not uniform

is designed used to extract the high-level targets contour features of infrared image.In the lower part of APFCN

a classical CNN network is used to extract three scale features of RGB images.At the back of APFCN

the high level features of the infrared image are fused with the three scale features of the RGB image

and the fused features after 4 times upper sampling is used as the semantic segmentation output of APFCN.The results show that APFCN is better than FCN (input RGB image or infrared image) in PA (Pixel Accuracy) and MIoU (Mean Intersection over Union).APFCN is suitable for the semantic segmentation task of ground targets with consistent background colors.

关键词

Keywords

references

Views

497

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

DFRNet: A Semantic Segmentation Method Inspired with Physical Mechanism of Diffusion-Focus

A Semantic Segmentation Method of Embryo Image Based on Curriculum Learning

Remote Sensing Image Segmentation of Around Plateau Lakes Based on Multi-Attention Fusion

Semantic Segmentation Network Based on Semantic and Morphological Feature Fusion

Related Author

FANG Xiao-ping

ZENG Wei-hao

LIANG Xin

ZHANG Ya-sha

GUAN Ya-fei

JIANG Lin

HUANG Yi-sha

TANG Hong-zhong

Related Institution

School of Mathematics and Statistics, Hunan University of Technology and Business

School of AI and Advanced Computing, Hunan University of Technology and Business

School of Intelligent Engineering and Manufacturing, Hunan University of Technology and Business

Xiangjiang Laboratory

College of Automation and Electronic Information， Xiangtan University

⁰