基于改进SEGNET模型的图像语义分割

doi:10.19678/j.issn.1000-3428.0058015

计算机工程 ›› 2021, Vol. 47 ›› Issue (4): 256-261. doi: 10.19678/j.issn.1000-3428.0058015

基于改进SEGNET模型的图像语义分割

罗嗣卿, 张志超, 岳琪

东北林业大学信息与计算机工程学院, 哈尔滨 150040

收稿日期:2020-04-09 修回日期:2020-05-21 发布日期:2020-05-28
作者简介:罗嗣卿(1964-),男,副教授、硕士,主研方向为图像处理、信息系统集成;张志超、硕士研究生;岳琪(通信作者),教授、博士。
基金资助:
国家自然科学基金青年项目“基于用户标签和主体兴趣的社会媒体信息推荐研究”（61806049）。

Semantic Image Segmentation Based on Improved SEGNET Model

LUO Siqing, ZHANG Zhichao, YUE Qi

School of Information and Computer Engineering, Northeast Forestry University, Harbin 150040, China

Received:2020-04-09 Revised:2020-05-21 Published:2020-05-28

摘要/Abstract

摘要： 使用原始SEGNET模型对图像进行语义分割时，未对图像中相邻像素点间的关系进行考虑，导致同一目标中像素点类别预测结果不一致。通过在SEGNET结构中加入一条自上而下的通道，使得SEGNET包含的多尺度语义信息更加丰富，从而提升对每个像素点的类别预测精度，在模型中加入生成对抗网络以充分考虑空间中相邻像素点间关系。实验结果表明，该模型的语义分割效果相比原始SEGNET模型显著提升，且可有效解决SEGNET测试中出现的分类错误问题。

关键词: SEGNET模型, 生成对抗网络, 多尺度语义信息, 相邻像素类别关系, 特征融合

Abstract: When applied to semantic image segmentation,the original SEGNET model does not account for the relationship between adjacent pixels in the image,resulting in inconsistent prediction results of pixel categories in the same target.By adding a top-down channel in the SEGNET structure,the multi-scale semantic information of the SEGNET model is enriched,and the accuracy of category prediction for each pixel is improved.The generative adversarial network is added to the model to ensure that the model can consider the relationship between adjacent pixels in space.The experimental results show that the semantic segmentation effect of the improved SEGNET model is significantly improved compared with the original SEGNET model.It can effectively avoid the classification errors in the SEGNET test.

Key words: SEGNET model, Generative Adversarial Network (GAN), multi-scale semantic information, adjacent pixel category relationship, feature fusion

中图分类号:

TP391.4

罗嗣卿, 张志超, 岳琪. 基于改进SEGNET模型的图像语义分割[J]. 计算机工程, 2021, 47(4): 256-261.

LUO Siqing, ZHANG Zhichao, YUE Qi. Semantic Image Segmentation Based on Improved SEGNET Model[J]. Computer Engineering, 2021, 47(4): 256-261.

https://www.ecice06.com/CN/Y2021/V47/I4/256

图/表 9

20210425171536

20210425171539

20210425171542

20210425171546

20210425171549

20210425171551

20210425171554

20210425171557

20210425171600

参考文献

[1] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:3431-3440.
[2] YANG Shuo,CHEN Lifang,SHI Yu,et al.Semantic segmentation of blue-green algae based on deep generative adversary net[J].Computer Applications,2018,38(6):1554-1561.(in Chinese)杨朔,陈丽芳,石瑀,等.基于深度生成式对抗网络的蓝藻语义分割[J].计算机应用,2018,38(6):1554-1561.
[3] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:a deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[4] RONNEBERGER O,FISCHER P,BROX T.U-Net:convolutional networks for biomedical image segmenta-tion[C]//Proceedings of International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin,Germany:Springer,2015:234-241.
[5] JIANG Yun,TAN Ning,ZHANG Hai,et al.Bitewing radiography image segmentation based on conditional generative adversarial network[J].Computer Engineering,2019,45(4):223-227.(in Chinese)蒋芸,谭宁,张海,等.基于条件生成对抗网络的咬翼片图像分割[J].计算机工程,2019,45(4):223-227.
[6] LI Zhi,ZAHNG Juan,FANG Zhijun,et al.Road scene semantic segmentation with cycle-consistent adversarial networks[J].Journal of Wuhan University (Natural Science Edition),2019,65(3):303-308.(in Chinese)李智,张娟,方志军,等.基于循环生成对抗网络的道路场景语义分割[J].武汉大学学报(理学版),2019,65(3):303-308.
[7] CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation[EB/OL].[2020-03-05].https://arxiv.org/pdf/1706.05587.pdf.
[8] GOODFELLOW I,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems.New York,USA:ACM Press,2014:2672-2680.
[9] CHEN Kai,PANG Jiangmiao,WANG Jiaqi,et al.Hybrid task cascade for instance segmentation[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2019:4974-4983.
[10] KIRILLOV A,GIRSHICK R,HE K,et al.Panoptic feature pyramid networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recogni-tion.Washington D.C.,USA:IEEE Press,2019:6399-6408.
[11] KENDALL A,BADRINARAYANAN V,CIPOLLA R.Bayesian segnet:model uncertainty in deep convolu-tional encoder-decoder architectures for scene under-standing[EB/OL].[2020-03-05].https://arxiv.org/pdf/1511.02680.pdf.
[12] ZHAO Hengshuang,SHI Jianping,QI Xiaojuan,et al.Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2881-2890.
[13] LIN T Y,DOLLAR P,GIRSHICK R,et al.Feature pyramid networks for object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2117-2125.
[14] MIRZA M,OSINDERO S.Conditional generative adversarial nets[EB/OL].[2020-03-05].http://de.arxiv.org/pdf/1411.1784.
[15] CAI Z,VASCONCELOS N.Cascade R-CNN:Delving into high quality object detection[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:6154-6162.
[16] ZHANG Wenkai,SUN Hao,SUN Xian,et al.Image set visual summarization based on MFF-GAN[J].Computer Engineering,2019,45(2):202-206.(in Chinese)张文凯,孙皓,孙显,等.基于MFF-GAN的图像集视觉总结[J].计算机工程,2019,45(2):202-206.
[17] LIU Qikai,JIANG Daihong,LI Wenji.Generative adversarial network based on piecewise loss[J].Computer Engineering,2019,45(5):155-160,168.(in Chinese)刘其开,姜代红,李文吉.基于分段损失的生成对抗网络[J].计算机工程,2019,45(5):155-160,168.
[18] DENG J,DONG W,SOCHER R,et al.Imagenet:a large-scale hierarchical image database[C]//Proceedings of 2009 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:248-255.
[19] GLOROT X,BENGIO Y.Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of International Conference on Artificial Intelligence and Statistics.Washington D.C.,USA:IEEE Press,2010:249-256.
[20] BROSTOW G J,FAUQUEUR J,CIPOLLA R.Semantic object classes in video:a high-definition ground truth database[J].Pattern Recognition Letters,2009,30(2):88-97.
[21] 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 and Machine Intelligence,2017,40(4):834-848.

选择文件类型/文献管理软件名称

选择包含的内容

基于改进SEGNET模型的图像语义分割

Semantic Image Segmentation Based on Improved SEGNET Model

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李俊仪, 李向阳, 龙朝勋, 李海燕, 李红松, 余鹏飞. 基于多级区域选择与跨层特征融合的野生菌分类[J]. 计算机工程, 2024, 50(9): 179-188.
[2]	张华青, 夏张涛, 陆晓庆, 童基均. 基于字形特征的血管外科命名实体识别[J]. 计算机工程, 2024, 50(8): 13-21.
[3]	李华昱, 张智康, 闫阳, 岳阳. 基于知识图谱增强的领域多模态实体识别[J]. 计算机工程, 2024, 50(8): 31-39.
[4]	刘锁兰, 王炎, 王洪元, 朱生升. 基于多流语义图卷积网络的人体行为识别[J]. 计算机工程, 2024, 50(8): 64-74.
[5]	赵婉秋, 张俊虎, 李海涛. 用于建筑物分割的平行结构特征融合网络[J]. 计算机工程, 2024, 50(8): 239-248.
[6]	赵宏, 王枭. 基于Swin-Transformer的黑色素瘤图像病灶分割研究[J]. 计算机工程, 2024, 50(8): 249-258.
[7]	王富平, 刘鸿玮, 张锲石, 段冠庄. 基于深度特征抑制的遮挡人脸识别网络[J]. 计算机工程, 2024, 50(8): 259-269.
[8]	闵莉, 董冰洁, 安冬. 基于多注意力机制与跨特征融合的语义分割算法[J]. 计算机工程, 2024, 50(8): 282-289.
[9]	王夙喆, 张雪英, 陈晓玉, 李凤莲, 吴泽林. 基于有效注意力和GAN结合的脑卒中EEG增强算法[J]. 计算机工程, 2024, 50(8): 336-344.
[10]	陈宇航, 杨勇, 先木斯亚·买买提明, 帕力旦·吐尔逊, 樊小超, 任鸽, 刁宇峰. 基于主题感知和语义增强的作文自动评分方法[J]. 计算机工程, 2024, 50(8): 363-371.
[11]	谭巨全, 王然. 特征融合下田径录像3D人体动作DTW捕捉算法[J]. 计算机工程, 2024, 50(7): 71-78.
[12]	张溢文, 蔡满春, 陈咏豪, 朱懿, 姚利峰. 融合空间特征的多尺度深度伪造检测方法[J]. 计算机工程, 2024, 50(7): 240-250.
[13]	王晋涛, 秦昂, 张元, 陈一飞, 王廷凤, 谢承霖, 邹刚. 基于注意力增强与特征融合的中文医学实体识别[J]. 计算机工程, 2024, 50(7): 324-332.
[14]	李亚康, 陈刚. 小角中子散射物理模型自动化筛选[J]. 计算机工程, 2024, 50(6): 56-64.
[15]	胡庆. 多尺度融合与双输出U-Net网络的行人重识别[J]. 计算机工程, 2024, 50(6): 102-109.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于改进SEGNET模型的图像语义分割

Semantic Image Segmentation Based on Improved SEGNET Model

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价