|
|
基于弱监督与光谱指数的哨兵2号图像裸土提取
|
Abstract:
利用哨兵2号图像进行裸土区动态制图对环境管理和生态恢复具有重要意义。深度学习技术已经彻底改变了土地利用与土地覆盖分类的方法，包括裸露土地区域的映射。然而，目前的深度学习方法存在两个主要问题，即标记成本高和模型性能较差的问题。在本文中，我们开发了一种新的深度语义分割网络O-Net来解决当前的问题。O-Net具有典型的编码器–解码器结构，其中编码器和解码器都可以实例化为一个特定的全卷积网络，其中编码器用于预测裸土面积的提取，解码器用于重建输入图像斑块的裸土指数。我们基于弱监督(如不完全或不准确的标签)来训练网络参数。在我们的注释浙江数据集上的实验表明，所提出的方法可以实现较先进的性能。
Dynamic mapping of bare soil areas using sentinel-2 images is important for environmental management and ecological restoration. Deep learning technology has revolutionized the approaches of Land Use and Land Cover classification including the mapping of bare soil areas. However, there are two main problems with current deep learning methods, namely the high cost of labeling and poor model performance. In this paper, we develop a new deep semantic segmentation network called O-Net for tackling the current problems. The O-Net has a typical encoder-decoder structure, among which both the en-coder and the decoder can be instantiated as a specific fully convolutional network, where the en-coder is used to predict the extraction of bare soil areas and the decoder is used to reconstruct the bare soil indices of the input image patches. We train the network parameters based on weak supervision such as incomplete or inaccurate annotations. Experiments over our annotated Zhejiang Dataset demonstrate that the proposed method can achieve more advanced performance.
| [1] | Xu, H. (2013) Dynamics of Bare Soil in a Typical Reddish Soil Loss Region of Southern China: Changting County, Fu-jian Province. Scientia Geographica Sinica, 33, 489-496. |
| [2] | Chen, W., Liu, L., Zhang, C., et al. (2004) Monitoring the Seasonal Bare Soil Areas in Beijing Using Multitemporal TM Images. 2004 IEEE International Geoscience and Remote Sensing Symposium, Vol. 5, 3379-3382. |
| [3] | Nguyen, C.T., Chidthaisong, A., Kieu Diem, P., et al. (2021) A Modified Bare Soil Index to Identify Bare Land Features during Agricultural Fallow-Period in Southeast Asia Using Landsat 8. Land, 10, Article No. 231.
https://doi.org/10.3390/land10030231 |
| [4] | Rasul, A., Balzter, H., Ibrahim, G.R.F., et al. (2018) Applying Built-Up and Bare-Soil Indices from Landsat 8 to Cities in Dry Climates. Land, 7, Article No. 81. https://doi.org/10.3390/land7030081 |
| [5] | Zhu, H. and Basir, O. (2005) An Adaptive Fuzzy Evidential Nearest Neighbor Formulation for Classifying Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing, 43, 1874-1889.
https://doi.org/10.1109/TGRS.2005.848706 |
| [6] | Kavzoglu, T. and Mather, P.M. (2003) The Use of Backpropa-gating Artificial Neural Networks in Land Cover Classification. International Journal of Remote Sensing, 24, 4907-4938. https://doi.org/10.1080/0143116031000114851 |
| [7] | Friedl, M.A. and Brodley, C.E. (1997) Decision Tree Classi-fication of Land Cover from Remotely Sensed Data. Remote Sensing of Environment, 61, 399-409. https://doi.org/10.1016/S0034-4257(97)00049-7 |
| [8] | Gualtieri, J.A. and Cromp, R.F. (1999) Support Vector Ma-chines for Hyperspectral Remote Sensing Classification. 27th AIPR Workshop: Advances in Computer-Assisted Recogni-tion, Vol. 3584, 221-232.
https://doi.org/10.1117/12.339824 |
| [9] | Chen, T., He, T., Benesty, M., et al. (2015) Xgboost: Extreme Gradient Boosting. R Package Version 0.4-2, 1-4. |
| [10] | LeCun, Y., Bottou, L., Bengio, Y., et al. (1998) Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86, 2278-2324. https://doi.org/10.1109/5.726791 |
| [11] | Krizhevsky, A., Sutskever, I. and Hinton, G.E. (2012) Imagenet Classifica-tion with Deep Convolutional Neural Networks. Communications of the ACM, 60, 84-90. |
| [12] | Simonyan, K. and Zis-serman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. |
| [13] | He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vi-sion and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778.
https://doi.org/10.1109/CVPR.2016.90 |
| [14] | 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, 7-12 June 2015, 3431-3440.
https://doi.org/10.1109/CVPR.2015.7298965 |
| [15] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Con-volutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Interven-tion—MICCAI 2015: 18th International Conference, Munich, 5-9 October 2015, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [16] | Chen, L.C., Zhu, Y., Papandreou, G., et al. (2018) Encod-er-Decoder with Atrous Separable Convolution for Semantic Image Segmentation. Proceedings of the European Confer-ence on Computer Vision (ECCV), Munich, 8-14 September 2018, 801-818. https://doi.org/10.1007/978-3-030-01234-2_49 |
| [17] | Liu, J., Zhang, Y., Liu, C., et al. (2023) Monitoring Impervi-ous Surface Area Dynamics in Urban Areas Using Sentinel-2 Data and Improved Deeplabv3+ Model: A Case Study of Jinan City, China. Remote Sensing, 15, Article No. 1976. https://doi.org/10.3390/rs15081976 |
| [18] | Yao, J. and Jin, S. (2022) Multi-Category Segmentation of Sentinel-2 Images Based on the Swin UNet Method. Remote Sensing, 14, Ar-ticle No. 3382. https://doi.org/10.3390/rs14143382 |
| [19] | Cao, H., Wang, Y., Chen, J., et al. (2022) Swin-unet: Unet-Like Pure Transformer for Medical Image Segmentation. European Conference on Computer Vision, Tel Aviv, 23-27 October 2022, 205-218.
https://doi.org/10.1007/978-3-031-25066-8_9 |
| [20] | Zhou, Z.H. (2018) A Brief Introduction to Weakly Supervised Learning. National Science Review, 5, 44-53.
https://doi.org/10.1093/nsr/nwx106 |
| [21] | Schmitt, M., Hughes, L.H., Qiu, C., et al. (2019) SEN12MS—A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion. https://doi.org/10.5194/isprs-annals-IV-2-W7-153-2019 |
| [22] | Nivaggioli, A. and Randrianarivo, H. (2019) Weakly Supervised Semantic Segmentation of Satellite Images. 2019 Joint Urban Remote Sensing Event (JURSE) IEEE, Vannes, 22-24 May 2019, 1-4.
https://doi.org/10.1109/JURSE.2019.8809060 |
| [23] | Qiao, W., Shen, L., Wang, J., et al. (2023) A Weakly Super-vised Semantic Segmentation Approach for Damaged Building Extraction from Post-Earthquake High-Resolution Re-mote-Sensing Images. IEEE Geoscience and Remote Sensing Letters, 20, 1-5. https://doi.org/10.1109/LGRS.2023.3243575 |
| [24] | Wang, J., Shao, Z., Huang, X., et al. (2022) From Artifact Re-moval to Super-Resolution. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-15. https://doi.org/10.1109/TGRS.2022.3196709 |
| [25] | Zhang, B., Xiao, J., Wei, Y., et al. (2022) End-to-End Weakly Supervised Semantic Segmentation with Reliable Region Mining. Pattern Recognition, 128, Article ID: 108663. https://doi.org/10.1016/j.patcog.2022.108663 |
| [26] | Rong, S., Tu, B., Wang, Z., et al. (2023) Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation. Proceedings of the IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition, Vancouver, 17-24 June 2023, 19574-19584. https://doi.org/10.1109/CVPR52729.2023.01875 |
| [27] | Zhou, T., Zhang, M., Zhao, F., et al. (2022) Regional Se-mantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation. Proceedings of the IEEE/CVF Confer-ence on Computer Vision and Pattern Recognition, New Orleans, 18-24 June 2022, 4299-4309. https://doi.org/10.1109/CVPR52688.2022.00426 |
| [28] | Du, Y., Fu, Z., Liu, Q., et al. (2022) Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, 18-24 June 2022, 4320-4329. https://doi.org/10.1109/CVPR52688.2022.00428 |
| [29] | Zhu, H., Geng, T., Wang, J., et al. (2023) Improved Sub-Category Exploration and Attention Hybrid Network for Weakly Supervised Semantic Segmentation. Neural Com-puting and Applications, 35, 10573-10587.
https://doi.org/10.1007/s00521-023-08250-4 |
