[1]李瀚超,蔡毅,王岭雪.全局特征提取的全卷积网络图像语义分割算法[J].红外技术,2019,41(7):595-599.[doi:10.11846/j.issn.1001_8891.201907001]
 LI Hanchao,CAI Yi,WANG Lingxue.Image Semantic Segmentation Based on Fully Convoluted Network with Global Feature Extraction[J].Infrared Technology,2019,41(7):595-599.[doi:10.11846/j.issn.1001_8891.201907001]
点击复制

全局特征提取的全卷积网络图像语义分割算法
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
41卷
期数:
2019年第7期
页码:
595-599
栏目:
出版日期:
2019-07-20

文章信息/Info

Title:
Image Semantic Segmentation Based on Fully Convoluted Network with Global Feature Extraction

文章编号:
1001-8891(2019)07-0595-05
作者:
李瀚超蔡毅王岭雪
北京理工大学 光电学院纳米光子学与超精密光电系统北京市重点实验室,光电成像技术与系统教育部重点实验室
Author(s):
LI HanchaoCAI YiWANG Lingxue
School of Optics and Photonics, Beijing Institute of Technology, Beijing Key Laboratory of Nanophotonics and Ultrafine Optoelectronic Systems, Key Laboratory of Photoelectronic Imaging Technology and System, Ministry of Education of China
关键词:
全卷积神经网络热图像红外图像带孔卷积全局特征语义分割
Keywords:
fully convoluted networksthermal imagesinfrared imagesdilate convolutionglobal featuresemantic segmentation
分类号:
TP391.4
DOI:
10.11846/j.issn.1001_8891.201907001
文献标志码:
A
摘要:
以全卷积神经网络为基础设计图像语义分割算法框架,设计全局特征提取模块提升高维语义特征的提取能力,引入带孔卷积算子保留图像细节并提升分割结果的分辨率。通过搭建端到端的图像语义分割算法框架进行训练,在可见光数据集上对算法框架进行性能评估,结果表明,本文方法在可见光图像上取得良好的语义分割性能和精度。本文还在不借助红外数据标注训练的情况下对红外图像进行分割,结果证明本文方法在典型红外目标如行人、车辆的分割中也有较好的表现。
Abstract:
We employed a fully convoluted network to perform the image semantic segmentation task. In detail, we introduced a global feature extraction module to enhance the high-level semantic feature extraction ability. Furthermore, we adopted the dilate convolution operation to preserve image details and increase the resolution of prediction results. We evaluated and analyzed our end-to-end semantic segmentation algorithm on visible image datasets. The results demonstrated that our proposed approach achieved a satisfactory accuracy and better visual effect. We also evaluated our framework on infrared images without training of semantic labels. The results have shown that our algorithm can obtain significance visualization on classical objects segmentation such as humans and cars.

参考文献/References:

[1]? Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014, 39(4): 640-651.
[2]? Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]//International Conference on Medical Image Computing & Computer-assisted Intervention, 2015.
[3]? Chen L C , Papandreou G , Kokkinos I , et al. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs[J]. IEEE Transactions on Pattern Analysis &Machine Intelligence, 2016, 40(4): 834-848.
[4]? ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 2881-2890.
[5]? HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[6]? Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014: 1409-1556.
[7]? Premachandran V, Bonev B, Lian X, et al. Pascal boundaries: A semantic boundary dataset with a deep semantic boundary detector[C]//IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2017: 73-81.
[8]? ZHENG S, Jayasumana S, Romera-Paredes B, et al. Conditional random fields as recurrent neural networks[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1529-1537.

相似文献/References:

[1]高军,荆益国.基于全卷积神经网络的卫星遥感图像云检测方法[J].红外技术,2019,41(7):607.[doi:10.11846/j.issn.1001_8891.201907003]
 GAO Jun,JING Yiguo.A Fully Convoluted Neural Network-based Cloud Detection Method for Satellite Remote Sensing Images[J].Infrared Technology,2019,41(7):607.[doi:10.11846/j.issn.1001_8891.201907003]

备注/Memo

备注/Memo:
收稿日期:2019-04-23;修订日期:2019-07-05.
作者简介:李瀚超(1994-),男,硕士生,主要从事图像处理、图像语义分割技术方面的研究。E-mail:lihanchao@bit.edu.cn。
通信作者:王岭雪(1973-),女,副教授,工学博士,主要从事红外成像、图像处理和红外光谱的研究工作。E-mail:neobull@bit.edu.cn。
基金项目:国家自然科学基金(61471044)。

更新日期/Last Update: 2019-07-12