Früher|Nächster

Image segmentation models of remote sensing using full residual connection and multiscale feature fusion

  • role： First author第一作者
  • Affiliation：

    School of Computer Science, Shaanxi Normal University, Xi’an 710119, China

  • Email：15502932507@163.com
  • Introduction：张小娟,1993年生,女,硕士研究生, 研究方向为机器学习、图像处理。E-mail: 15502932507@163.com
ZHANG Xiaojuan1,  
  • role： Corresponding author通信作者
  • Affiliation：

    School of Computer Science, Shaanxi Normal University, Xi’an 710119, China

  • Email：wangxili@snnu.edu.cn
  • Introduction：汪西莉,1969年生，女，教授，研究方向为智能信息处理、模式识别、图像处理。E-mail: wangxili@snnu.edu.cn
WANG Xili1*

Resümee

Many characteristics of remote sensing images, such as large scale, complex illumination and occlusion, dense, multiple scales, various posture targets, and the lack of a large number of labeled images for training depth networks, pose great challenges to the integrity and accuracy of remote sensing image segmentation. In deep convolutional networks for segmentation, resolution is significantly reduced by multiple pooling, thereby reducing the prediction accuracy of pixel class.On the basis of the deep convolutional coding-decoding network, an end-to-end remote sensing image segmentation model with full residual connection and multiscale feature fusion is proposed in this paper. First, the features in the encoder are merged into the corresponding layers of the decoder, and the residual unit is added to the corresponding convolution layer. The full residual connection constructed by the operation enables the model as a whole to effectively enhance feature fusion and be easier to train. Second, the feature pyramid module, which aggregates multiscale context information, is used on the high-level feature map of the fifth stage of the encoder before feature fusion, thus enabling the model to effectively deal with multiscale changes of the target and improve the segmentation performance.Experiments were conducted on the ISPRS Vaihingen and Road Detection datasets. The proposed model was evaluated from the two aspects of average IOU and average F1-score. A comparison between the current advanced models and the results in the literature shows that the proposed model is better than the comparison models. The average IOU on the two datasets is 85% and 84%, and the average F1 value is 92% and 93%, respectively.An end-to-end remote sensing image segmentation model with full residual connection and multiscale feature fusion is proposed in this paper. The proposed model achieves better results than the current advanced image semantic segmentation model on the two datasets. The segmentation targets are more complete, continuous, and have fewer misclassifications and leakages. The proposed model also achieves better results than the comparative model in road segmentation of remote sensing images from different sources, thereby further verifying the robustness of the model.

Schlüsselwort

remote sensing image segmentation;deep convolutional neural network

References

  1. 1.
    Audebert N, Le Saux B and Lefèvrey S. 2017. Fusion of heterogeneous data in convolutional networks for urban semantic labeling//Proceedings of 2017 Joint Urban Remote Sensing Event. Dubai, United Arab Emirates: IEEE: 1-4
  2. 2.
    Badrinarayanan V, Kendall, A and Cipolla R. 2017. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495. DOI: .
  3. 3.
    Chen L C, Papandreou G, Kokkinos I, Murphy K and Yuille A L. 2018. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4): 834-848
  4. 4.
    Chen L C, Papandreou G, Schroff F and Adam H. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587
  5. 5.
    Cheng G L, Wang Y, Xu S B, Wang H Z, Xiang S M and Pan C H. 2017. Automatic road detection and centerline extraction via cascaded end-to-end convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing, 55(6): 3322-3337
  6. 6.
    He K M, Zhang X Y, Ren S Q and Sun J. 2015. Delving deep into rectifiers: surpassing human-level performance on imageNet classification//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 1026-1034
  7. 7.
    He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE: 770-778
  8. 8.
    ISPRS Vaihingen dataset. 2018.
  9. 9.
    Lin G S, Milan A, Shen C H and Reid I. 2017. RefineNet: multi-path refinement networks for high-resolution semantic segmentation//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE: 5168-5177
  10. 10.
    Long J, Shelhamer E and Darrell T. 2015. Fully convolutional networks for semantic segmentation//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE: 3431-3440
  11. 11.
    Maggiori E, Tarabalka Y, Charpiat G and Alliez P. 2017. High-resolution aerial image labeling with convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 55(12): 7092-7103
  12. 12.
    Noh H, Hong S and Han B. 2015. Learning deconvolution network for semantic segmentation//Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 1520-1528
  13. 13.
    Paisitkriangkrai S, Sherrah J, Janney P and Van-Den Hengel A. 2015. Effective semantic pixel labelling with convolutional networks and conditional random fields//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, MA, USA: IEEE: 36-43
  14. 14.
    Panboonyuen T, Jitkajornwanich K, Lawawirojwong S, Srestasathiern P and Vateekul P. 2017. Road segmentation of remotely-sensed images using deep convolutional neural networks with landscape metrics and conditional random fields. Remote Sensing, 9(7): 680
  15. 15.
    Ronneberger O, Fischer P and Brox T. 2015. U-Net: convolutional networks for biomedical image segmentation//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany: Springer: 234-241
  16. 16.
    Sherrah J. 2016. Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery. arXiv preprint arXiv:1606.02585.
  17. 17.
    Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations. 1-14.
  18. 18.
    Volpi M and Tuia D. 2017. Dense semantic labeling of subdecimeter resolution images with convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 55(2): 881-893
  19. 19.
    Wang P Q, Chen P F, Yuan Y, Liu D, Huang Z H, Hou X D and Cottrell G. 2018. Understanding convolution for semantic segmentation//Proceedings of 2018 IEEE Winter Conference on Applications of Computer Vision. Lake Tahoe, NV, USA: IEEE: 1451-1460
  20. 20.
    Wu Y Q, Ji Y, Shen Y and Zhang Y F. 2012. Marine spill oil SAR image segmentation based on Tsallis entropy and improved Chan Vese model. Journal of Remote Sensing, 16(4): 678-690
  21. 21.
    Yang X Z, Liu C J, Wu K W and Lang W H. 2014. SAR sea ice image segmentation using SRRG-MRF. Journal of Remote Sensing, 18(6): 1247-1257
  22. 22.
    Yu B, Meng J M, Zhang X and Ji Y G. 2013. Segmentation method for agglomerative hierarchical-based sea ice types using polarimetric SAR data. Journal of Remote Sensing, 17(4): 887-904
  23. 23.
    Yu F and Koltun V. 2016. Multi-scale context aggregation by dilated convolutions. International Conference on Learning Representations. 1-13.
  24. 24.
    Zeiler M D and Fergus R. 2014. Visualizing and understanding convolutional networks//Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer: 818-833
  25. 25.
    Zhang Z X, Liu Q J and Wang Y H. 2018. Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753
  26. 26.
    Zhao H S, Shi J P, Qi X J, Wang X G and Jia J Y. 2017. Pyramid scene parsing network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE: 6230-6239
  27. 27.
    Zheng W, Kang G W, Chen W F and Li X W. 2008. Unsupervised segmentation of remote sensing images based on fuzzy Markov random field. Journal of Remote Sensing, 12(2): 246-252
  28. 28.
    Zhong Z Y, Jin L W and Xie Z C. 2015. High performance offline handwritten Chinese character recognition using GoogLeNet and directional feature maps//Proceedings of 2015 13th International Conference on Document Analysis and Recognition. Tunis, Tunisia: IEEE: 846-850
  29. 29.
    Zhou M F and Wang X L. 2018. Object detection models of remote sensing images using deep neural networks with weakly supervised training method. Scientia Sinica Informationis, 48(8): 1022-1034

Lesen Sie die ganze Passage

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website