广东工业大学学报 ›› 2022, Vol. 39 ›› Issue (01): 63-70.doi: 10.12052/gdutxb.210014

• 综合研究 • 上一篇    下一篇

一种双路网络语义分割模型

杨运龙, 梁路, 滕少华   

  1. 广东工业大学 计算机学院，广东 广州 510006
  • 收稿日期:2021-01-25 发布日期:2022-01-20
  • 通信作者: 梁路(1980-),女,副教授,博士,主要研究方向为人工智能、协同计算,E-mail:ll475730489@163.com
  • 作者简介:杨运龙(1996-),男,硕士研究生,主要研究方向为图像处理、深度学习
  • 基金资助:
    国家自然科学基金资助项目(61972102，61603100)

A Two-way Network Model for Semantic Segmentation

Yang Yun-long, Liang Lu, Teng Shao-hua   

  1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2021-01-25 Published:2022-01-20

HTML

PDF (PC)

3017

摘要： 深度卷积神经网络对高分辨率遥感影像进行语义分割时, 对图像的下采样会造成物体边缘模糊, 使分割结果在边缘附近划分不清晰, 误分类较多。通过在网络中增加边缘信息可以提升模型对遥感图像的分割能力。因此, 提出了一个用于语义分割的双路网络模型, 增加一路边缘网络学习目标的边缘特征, 并利用边缘特征对分割特征进行细化。同时, 作为一个多任务学习模型, 分割网络和边缘网络可以同时进行训练。本文在ISPRS Potsdam和ISPRS Vaihingen数据集上证明了双路网络模型的有效性, 对比多种语义分割模型, 均取得了领先的效果。

关键词: 双路网络, 边缘检测, 高分辨率遥感图像, 语义分割

Abstract: When deep convolutional neural networks perform semantic segmentation of high-resolution remote sensing images, the downsampling of images can cause blurring of object edges, making the segmentation results unclearly delineated near the edges and more misclassified. The segmentation ability of the model for remote sensing images can be improved by adding edge information in the network. Therefore, a two-way network model is proposed for semantic segmentation, adding one-way edge network to learn the edge features of the target and refining the segmentation features using the edge features. Meanwhile, the segmentation network and the edge network can be trained simultaneously as a multi-task learning model. In this paper, the effectiveness of the two-way network model is demonstrated on the ISPRS Potsdam and ISPRS Vaihingen dataset datasets, and leading results are achieved when comparing multiple semantic segmentation models.

Key words: two-way network, edge detection, high-resolution remote sensing images, semantic segmentation

中图分类号: 

  • TP391
[1] YAO XW, HAN J W, CHENG G, et al. Semantic annotation of high-resolution satellite images via weakly supervised learning [J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(6): 3660-3671.
[2] MARTHA T R, KERLE N, WESTEN C J, et al. Segment optimization and data-driven thresholding for knowledge-based landslide detection by object-based image analysis [J]. IEEE Transactions on Geoence & Remote Sensing, 2011, 49(12): 4928-4943.
[3] YIN H, PFLUGMACHER D, LI A, et al. Land use and land cover change in Inner Mongolia-understanding the effects of China's re-vegetation programs [J]. Remote Sensing of Environment, 2018, 204: 918-930.
[4] AHMAD K, POGORELOV K, RIEGLER M, et al. Automatic detection of passable roads after floods in remote sensed and social media data [J]. Signal Processing: Image Communication, 2019, 74: 110-118.
[5] 陈旭, 张军, 陈文伟, 等. 卷积网络深度学习算法与实例[J]. 广东工业大学学报, 2017, 34(6): 20-26.
CHEN X, ZHANG J, CHEN W W, et al. Convolutional neural network algorithm and case [J]. Journal of Guangdong University of Technology, 2017, 34(6): 20-26.
[6] LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640-651.
[7] YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[J]. arXiv preprint arXiv: 1511.07122, 2015.
[8] ZHAO H S, SHI J P, QI X, et al. Pyramid scene parsing network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 2881-2890.
[9] GADDE R, JAMPANI V, KIEFEL M, et al. Superpixel convolutional networks using bilateral inceptions[C]//European Conference on Computer Vision. Cham: Springer, 2016: 597-613.
[10] HUANG G, LIU Z, MAATEN L, et al. Densely connected convolutional networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 4700-4708.
[11] GHIASI G, FOWLKES C. Laplacian pyramid reconstruction and refinement for semantic segmentation[C]// European Conference on Computer Vision. Cham: Springer, 2016: 519-534.
[12] LIN G, MILAN A, SHEN C, et al. Refinenet: multi-path refinement networks for high-resolution semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 1925-1934.
[13] PENG C, ZHANG X, YU G, et al. Large kernel matters-improve semantic segmentation by global convolutional network[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 4353-4361.
[14] 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.
[15] SHERRAH J. Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery[J]. arXiv preprint arXiv: 1606.02585, 2016.
[16] RONNEBERGER O, FISCHER P, BROX T. U-net: convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234-241.
[17] YU Z, FENG C, LIU M Y, et al. Casenet: deep category-aware semantic edge detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2017: 5964-5973.
[18] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C] //Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[19] HARIHARAN B, ARBELÁEZ P, GIRSHICK R, et al. Simultaneous detection and segmentation[C] //European Conference on Computer Vision. Zurich: Springer, 2014: 297-312.
[20] NOH H, HONG S, HAN B. Learning deconvolution network for semantic segmentation[C] //Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1520-1528.
[21] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//European Conference on Computer Vision. Zurich: Springer, 2014: 818-833.
[22] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[J]. arXiv preprint arXiv: 1706.05587, 2017.
[23] ZHENG S, JAYASUMANA S, ROMERAPAREDES B, et al. Conditional random fields as recurrent neural networks[C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1529-1537.
[24] LIN G, SHEN C, VAN DEN HENGEL A, et al. Efficient piecewise training of deep structured models for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 3194-3203.
[25] JAMPANI V, KIEFEL M, GEHLER P V. Learning sparse high dimensional filters: image filtering, dense CRFs and bilateral neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 4452-4461.
[26] POHLEN T, HERMANS A, MATHIAS M, et al. Full-resolution residual networks for semantic segmentation in street scenes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE, 2017: 4151-4160.
[27] PRASAD M, ZISSERMAN A, FITZGIBBON A W, et al. Learning class-specific edges for object detection and segmentation [J]. Lecture Notes in Computer Science, 2006, 4338: 94-10 5.
[28] BERTASIUS G, SHI J, TORRESANI L. High-for-low and low-for-high: efficient boundary detection from deep object features and its applications to high-level vision[C]// Proceedings of the IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 504-512.
[29] BERTASIUS G, SHI J, TORRESANI L. Semantic segmentation with boundary neural fields[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 3602-3610.
[30] XIE S, TU Z. Holistically-nested edge detection [J]. International Journal of Computer Vision, 2015, 125(1-3): 3-18.
[31] KENDALL A, GAL Y, CIPOLLA R. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7482-7491.
[32] MISRA I, SHRIVASTAVA A, GUPTA A, et al. Cross-stitch networks for multi-task learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016: 3994-4003.
[33] 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.
[34] CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//Proceedings of the European Conference on Computer Vision (ECCV). Glasgow: Springer, 2018: 801-818.
[35] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv: 1409.1556, 2014.
[36] 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. Las Vegas: IEEE, 2016: 770-778.
[37] ACUNA D, KAR A, FIDLER S. Devil is in the edges: learning semantic boundaries from noisy annotations[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 11075-11083.
[38] YU Z, LIU W, ZOU Y, et al. Simultaneous edge alignment and learning[C]//Proceedings of the European Conference on Computer Vision (ECCV). Glasgow: Springer, 2018: 388-404.
[39] TAKIKAWA T, ACUNA D, JAMPANI V, et al. Gated-SCNN: gated shape CNNs for semantic segmentation[C]//Proceedings of the IEEE International Conference on Computer Vision. Seoul: IEEE, 2019: 5229-5238.
[1] 谢岩, 刘广聪. 基于编解码器模型的车道识别与车辆检测算法[J]. 广东工业大学学报, 2019, 36(04): 36-41.
[2] 何春，冯桑，陆晓，陈小龙. 形态学在交通标志边缘检测中的应用研究[J]. 广东工业大学学报, 2013, 30(3): 101-104.
[3] 刘立程；. 改进的基于形态学梯度法的车辆图像边缘检测方法[J]. 广东工业大学学报, 2007, 24(2): 84-86.
[4] 曹晓均； 潘保昌； 郑胜林； 甘艳芬； . 基于特征图像方法的运动物体检测[J]. 广东工业大学学报, 2007, 24(2): 87-89.
[5] 刘立程； . 图像聚类分析法用于汽车图像边缘的检测[J]. 广东工业大学学报, 2006, 23(2): 69-73.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发