MAPDNet:一种检测XCO2图像中羽流的方法
作者单位:

南京信息工程大学

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


MAPDNet - a method for detecting plumes in XCO2 images
Author:
Affiliation:

Nanjing University of Information Science and Technology

Fund Project:

The National Natural Science Foundation of China (General Program, Key Program, Major Research Plan)

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    检测温室气体羽流是碳排放监测的关键任务,目前相关算法中,对羽流边缘细节的分割精度还有提升空间。为此,本文提出一种基于多尺度注意力机制的羽流检测网络(MAPDNet)。首先,本文提出了多尺度池化条带卷积模块(MPSCM),补偿编码器降采样操作中稀释的高级语义信息,增强主要的羽流轮廓信息,减少细节信息的丢失。然后,关系注意力模块(RAM)建立了特征之间的全局信息与局部信息交互,增强有用特征,降低特征图中冗余信息的比例,提高模型的分割精度。此外,本文还提出了上下文特征融合模块(CFFM)以便网络更好地理解上下文特征的信息,在恢复图像分辨率的同时,较好地将特征对齐,恢复空间位置信息。最后,边界增强模块(BEM)实现端到端训练,增强输出分割边界的细节,进一步提高分割精度。实验结果表明,MAPDNet模型能够从XCO2羽流图像中检测碳羽流,并在模拟羽流数据集上具有良好的分割性能,其分割精度优于现有方法。

    Abstract:

    The detection of greenhouse gas plumes is a key task of carbon emission monitoring. In the current relevant algorithms, the segmentation accuracy of plume edge details still has room for improvement. In this paper, a multi-scale attention mechanism based plume detection network (MAPDNet) is proposed. Firstly, a multi-scale pooled strip Convolution module (MPSCM) is proposed to compensate the high-level semantic information diluted in the downsampling operation of the encoder, enhance the main plume profile information, and reduce the loss of detail information. Then, the relational attention module (RAM) establishes the global and local information interaction between features, enhances the useful features, reduces the proportion of redundant information in the feature map, and improves the segmentation accuracy of the model. In addition, a context feature fusion module (CFFM) is proposed in this paper so that the network can understand the context feature information better, align the features better, and recover the spatial position information while recovering the image resolution. Finally, the edge enhancement module (BEM) implements end-to-end training, enhances the details of the output segmentation boundary, and further improves the segmentation accuracy. The experimental results show that MAPDNet model can detect carbon plumes from XCO2 plume images, and has good segmentation performance on simulated plume data sets, and its segmentation accuracy is better than the existing methods.

    参考文献
    1. 许志杰 和 孙浩捷, 全球甲烷浓度不断升高. 生态经济, 2022. 38(06): p. 5-8. Xu Zhijie and Sun Haojie, Global methane concentrations are increasing. Ecological Economy, 2022. 38(06): p. 5-8.
    2. Pan, G., Y. Xu, and J. Ma, The potential of CO2 satellite monitoring for climate governance: A review. Journal of Environmental Management, 2021. 277: p. 111423.
    3. Crisp, D., et al., The on-orbit performance of the Orbiting Carbon Observatory-2 (OCO-2) instrument and its radiometrically calibrated products. Atmospheric Measurement Techniques, 2017. 10(1): p. 59-81.
    4. Yang, D., et al., A new TanSat XCO 2 global product towards climate studies. Advances in Atmospheric Sciences, 2021. 38: p. 8-11.
    5. Benveniste, J., et al., Earth observations for coastal hazards monitoring and international services: a European perspective. Surveys in Geophysics, 2020. 41: p. 1185-1208.
    6. Janssens-Maenhout, G., et al., Toward an operational anthropogenic CO2 emissions monitoring and verification support capacity. Bulletin of the American Meteorological Society, 2020. 101(8): p. E1439-E1451.
    7. Green, R.O., et al., Imaging spectroscopy and the airborne visible/infrared imaging spectrometer (AVIRIS). Remote sensing of environment, 1998. 65(3): p. 227-248.
    8. Dennison, P.E., et al., High spatial resolution mapping of elevated atmospheric carbon dioxide using airborne imaging spectroscopy: Radiative transfer modeling and power plant plume detection. Remote sensing of environment, 2013. 139: p. 116-129.
    9. Lauvaux, T., et al., Global assessment of oil and gas methane ultra-emitters. Science,, 2022. 375(6580): p. 557-561.
    10. Buades, A., B. Coll, and J.-M. Morel, A review of image denoising algorithms, with a new one. Multiscale Modeling Simulation, 2005. 4(2): p. 490-530.
    11. Adnan, M.M., et al., Automatic image annotation based on deep learning models: a systematic review and future challenges. IEEE Access, 2021. 9: p. 50253-50264.
    12. Long, J., E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
    13. Zhao, H., et al. Pyramid scene parsing network. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.
    14. Chen, L.-C., et al., Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv., 2014.
    15. Chen, L.-C., et al., Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis machine intelligence. 2017. 40(4): p. 834-848.
    16. Chen, L.-C., et al., Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:.05587, 2017.
    17. Chen, L.-C., et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. in Proceedings of the European conference on computer vision (ECCV). 2018.
    18. Lu, C., M. Xia, and H. Lin, Multi-scale strip pooling feature aggregation network for cloud and cloud shadow segmentation. Neural Computing Applications, 2022. 34(8): p. 6149-6162.
    19. Lu, C., et al., Dual-branch network for cloud and cloud shadow segmentation. IEEE Transactions on Geoscience Remote Sensing, 2022. 60: p. 1-12.
    20. Larsen, A., et al., A deep learning approach to identify smoke plumes in satellite imagery in near-real time for health risk communication. Journal of exposure science environmental epidemiology, 2021. 31(1): p. 170-176.
    21. Ronneberger, O., P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. in Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. 2015. Springer.
    22. Mommert, M., et al., Characterization of industrial smoke plumes from remote sensing data. arXiv preprint arXiv:.11344, 2020.
    23. He, K., et al. Deep residual learning for image recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
    24. Dumont Le Brazidec, J., et al., Segmentation of XCO 2 images with deep learning: application to synthetic plumes from cities and power plants. Geoscientific Model Development Discussions, 2022. 2022: p. 1-29.
    25. Tan, M. and Q. Le. Efficientnet: Rethinking model scaling for convolutional neural networks. in International conference on machine learning. 2019. PMLR.
    26. Hu, K., D. Zhang, and M. Xia, CDUNet: Cloud detection UNet for remote sensing imagery. Remote Sensing, 2021. 13(22): p. 4533.
    27. Chen, K., et al., Multi-scale attention feature aggregation network for cloud and cloud shadow segmentation. IEEE Transactions on Geoscience Remote Sensing, 2023. 61: p. 1-16.
    28. Song, L., et al., Axial cross attention meets CNN: Bibranch fusion network for change detection. IEEE Journal of Selected Topics in Applied Earth Observations Remote Sensing, 2022. 16: p. 21-32.
    29. Huang, H., et al. Unet 3+: A full-scale connected unet for medical image segmentation. in ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). 2020. IEEE.
    30. Li, R., C. Duan, and S. Zheng, Macu-net semantic segmentation from high-resolution remote sensing images. arXiv preprint arXiv:.13083, 2020.
    31. Krizhevsky, A., I. Sutskever, and G.E. Hinton, ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017. 60(6): p. 84-90.
    32. Wang, H., et al. Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. in Proceedings of the AAAI conference on artificial intelligence. 2022.
    33. Yu, C., et al., Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation. International Journal of Computer Vision, 2021. 129: p. 3051-3068.
    34. Li, X., et al. Semantic flow for fast and accurate scene parsing. in Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part I 16. 2020. Springer.
    35. Xu, J., Z. Xiong, and S.P. Bhattacharyya. PIDNet: A real-time semantic segmentation network inspired by PID controllers. in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2023.
    36. Pei, Z., et al., A method for estimating the background column concentration of CO 2 using the lagrangian approach. IEEE Transactions on Geoscience Remote Sensing, 2022. 60: p. 1-12.
    37. Brazidec, J.D.L., et al., Simulated XCO2 images and hotspot plumes formatted for deep learning methods and segmentation models weights. [dataset], 2022.
    38. Kuhlmann, G., et al., Synthetic XCO2, CO and NO2 observations for the CO2M and Sentinel-5 satellites. Zenodo [data set].
    39. J?hn, M., et al., An online emission module for atmospheric chemistry transport models: implementation in COSMO-GHG v5. 6a and COSMO-ART v5. 1-3.1. Geoscientific Model Development, 2020. 13(5): p. 2379-2392.
    40. Grell, G.A., et al., Fully coupled “online” chemistry within the WRF model. Atmospheric Environment, 2005. 39(37): p. 6957-6975.
    41. Paszke, A., et al., Automatic differentiation in pytorch. 2017.
    相似文献
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

邵鹏飞,胡凯,刘滋然,冯新龑,马科宇,章琪,姜闪闪,夏旻,叶小岭. MAPDNet:一种检测XCO2图像中羽流的方法[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:30
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2024-06-28
  • 最后修改日期:2024-09-27
  • 录用日期:2024-09-28

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司