基于DeepLab v3的西藏地区降雨云团分割方法

doi:10.11772/j.issn.1001-9081.2019122131

计算机应用 ›› 2020, Vol. 40 ›› Issue (9): 2781-2788.DOI: 10.11772/j.issn.1001-9081.2019122131

• 应用前沿、交叉与综合 • 上一篇

基于DeepLab v3的西藏地区降雨云团分割方法

张永宏^1,2, 刘昊², 田伟³, 王剑庚⁴

1. 南京信息工程大学气象灾害预报预警与评估协同创新中心, 南京 210044;
2. 南京信息工程大学自动化学院, 南京 210044;
3. 南京信息工程大学计算机与软件学院, 南京 210044;
4. 南京信息工程大学大气物理学院, 南京 210044

收稿日期:2019-12-19 修回日期:2020-02-27 出版日期:2020-09-10 发布日期:2020-05-13
通讯作者: 刘昊
作者简介:张永宏(1974-),男,山东临沂人,教授,博士,主要研究方向:大气遥感检测、图像处理分析;刘昊(1996-),男,江苏镇江人,硕士研究生,主要研究方向:遥感图像处理、大数据分析;田伟(1980-),男,江苏涟水人,副教授,博士,主要研究方向:计算机软件、人工智能降雨估计、大数据处理;王剑庚(1982-),男,甘肃定西人,副教授,博士,主要研究方向:积雪遥感、"地-气"相互作用。
基金资助:
国家自然科学基金资助项目（41875027）。

Rainfall cloud segmentation method in Tibet based on DeepLab v3

ZHANG Yonghong^1,2, LIU Hao², TIAN Wei³, WANG Jiangeng⁴

1. Collaborative Innovation Center on Forecast and Evaluation of Meteorological Disasters, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China;
2. School of Automation, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China;
3. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China;
4. School of Atmospheric Physics, Nanjing University of Information Science and Technology, Nanjing Jiangsu 210044, China

Received:2019-12-19 Revised:2020-02-27 Online:2020-09-10 Published:2020-05-13
Supported by:
This work is partially supported by the National Natural Science Foundation of China (41875027).

摘要/Abstract

摘要： 针对高原地区数值预测法建模复杂，雷达回波外推法易产生累积误差且模型参数难以设置的问题，提出了一种基于改进DeepLab v3网络模型的西藏地区降雨云团的分割方法。首先，通过编码网络中的卷积层和残差模块进行下采样；然后，利用空洞卷积构建多尺度采样模块，并且加入注意力机制模块提取深层高维特征；最后，通过解码网络利用反卷积恢复特征图分辨率。将所提方法与谷歌语义分割网络DeepLab v3等模型在验证集上进行比较，实验结果表明所提方法具有更好的分割性能与泛化能力，其降雨云团分割结果更为准确，平均交并比（Miou）达到0.95，与原始DeepLab v3相比提高了15.54个百分点。在小目标上和非平衡数据集上，该方法可以更准确地分割出降雨云团，为降雨云团监测预警提供参考。

关键词: 降雨云团分割, 多尺度采样, 注意力机制, DeepLab v3, 遥感图像处理

Abstract: Concerning the problem that the numerical prediction method is complex in modeling, the radar echo extrapolation method is easy to generate cumulative error and the model parameters are difficult to set in plateau area, a method for segmenting rainfall clouds in Tibet was proposed based on the improved DeepLab v3. Firstly, the convolutional layers and residual modules in the coding network were used for down-sampling. Then, the multi-scale sampling module was constructed by using the dilated convolution, and the attention mechanism module was added to extract deep high-dimensional features. Finally, the deonvolutional layers in the decoding network were used to restore the feature map resolution. The proposed method was compared with Google semantic segmentation network DeepLab v3 and other models on the validation set. The experimental results show that the method has better segmentation performance and generalization ability, has the rainfall cloud segmented more accurately, and the Mean intersection over union (Miou) reached 0.95, which is 15.54 percentage points higher than that of the original DeepLab v3. On small targets and unbalanced datasets, rainfall clouds can be segmented more accurately by this method, so that the proposed method can provide a reference for the rain cloud monitoring and early warning.

Key words: rainfall cloud segmentation, multi-scale sampling, attention mechanism, DeepLab v3, remote sensing image processing

中图分类号:

TP183
TP751

张永宏, 刘昊, 田伟, 王剑庚. 基于DeepLab v3的西藏地区降雨云团分割方法[J]. 计算机应用, 2020, 40(9): 2781-2788.

ZHANG Yonghong, LIU Hao, TIAN Wei, WANG Jiangeng. Rainfall cloud segmentation method in Tibet based on DeepLab v3[J]. Journal of Computer Applications, 2020, 40(9): 2781-2788.

参考文献

[1] 陈森发,张文红,张建坤,等. 短期降雨预测的随机微分模型[J]. 系统工程学报, 2004, 19(3):239-243.(CHEN S F, ZHANG W H, ZHANG J K, et al. Short-term rainfall prediction of stochastic differential models[J]. Journal of Systems Engineering, 2004, 19(3):239-243.)
[2] 赵欣,邹良超,倪林. 基于有序聚类的模糊加权马尔可夫模型在降雨预测中的应用[J]. 江西农业学报, 2009, 21(2):110-113. (ZHAO X, ZOU L C, NI L. Application of fuzzy weighted Markov model based on ordered clustering to rainfall prediction[J]. Acta Agriculture Jiangxi, 2009, 21(2):110-113.)
[3] 朱平,李生辰,肖建设,等. 天气雷达回波外推技术应用研究[J]. 气象, 2008, 34(7):3-9.(ZHU P, LI S C, XIAO J S,et al. Study on extrapolation technique of weather radar echo and its application to nowcasting[J]. Meteorological Monthly, 2008, 34(7):3-9.)
[4] 卢乃锰,方翔,刘健,等. 气象卫星的云观测[J]. 气象, 2017, 43(3):257-267.(LU N M, FANG X, LIU J, et al. Understanding clouds by meteorological satellites[J]. Meteorological Monthly, 2017, 43(3):257-267.)
[5] 李森,刘健文,刘玉玲. 基于FY2D静止卫星云图的强对流云团识别[J]. 气象水文海洋仪器, 2010, 27(2):72-78.(LI S, LIU J W, LIU Y L. Detection of strong convective clouds based on FY2D geostationary satellite[J]. Meteorological, Hydrological and Marine Instruments, 2010, 27(2):72-78.)
[6] 赵文化,单海滨. 基于红外窗区与水汽通道对流云团识别方法研究[J]. 气象, 2018, 44(6):814-824.(ZHAO W H, SHAN H B. Study of convective cloud identification based on H₂O/IRW observation[J]. Meteorological Monthly, 2018, 44(6):814-824.)
[7] 周晓丽,杨昌军. 基于FY-2D的新疆区域强对流云识别[J]. 沙漠与绿洲气象, 2017, 11(2):82-87.(ZHOU X L, YANG C J. Identification of strong convective cloud in Xinjiang using FY-2D stationary meteorological satellite data[J]. Desert and Oasis Meteorology, 2017, 11(2):82-87.)
[8] 吴晓京,朱小祥,毛紫阳,等. 风云二号气象卫星红外观测在云团降水监测中的应用[J]. 海洋气象学报, 2019, 39(3):1-10.(WU X J, ZHU X X, MAO Z Y, et al. Algorithm design of convective precipitation monitoring and early warning service using FY-2 infrared data[J]. Journal of Marine Meteorology, 2019, 39(3):1-10.)
[9] WOLF D E, HALL D J, ENDLICH R M. Experiments in automatic cloud tracking using SMS-GOES data[J]. Journal of Applied Meteorology, 1977, 16(11):1219-1230.
[10] MAHOVIĆ N S, ZEINER B. Application of meteosat SEVIRI channel difference 0.6μm-1.6μm in convective cells detection[J]. Atmospheric Research, 2009, 93(1/2/3):270-276.
[11] 许玥,冯梦如,皮家甜,等. 基于深度学习模型的遥感图像分割方法[J]. 计算机应用, 2019, 39(10):2905-2914.(XU Y, FENG M R, PI J T, et al. Remote sensing image segmentation method based on deep learning model[J]. Journal of Computer Applications, 2019, 39(10):2905-2914.)
[12] 周明非,汪西莉. 结合纹理去除的遥感图像分割[J]. 计算机应用, 2017, 37(11):3162-3167.(ZHOU M F, WANG X L. Remote sensing image segmentation with texture removal[J]. Journal of Computer Applications, 2017, 37(11):3162-3167.)
[13] 夏勇,赵荣椿. 基于形态学多重分形的遥感图像多尺度分割[J]. 计算机应用, 2006, 26(9):2071-2073.(XIA Y, ZHAO R C. Multiscale segmentation of remote sensing images based on multifractal exponents[J]. Journal of Computer Applications, 2006, 26(9):2071-2073.)
[14] 陈天华,郑司群,于峻川. 采用改进DeepLab网络的遥感图像分割[J]. 测控技术, 2018, 37(11):34-39.(CHEN T H, ZHENG S Q, YU J C. Remote sensing image segmentation based on improved DeepLab network[J]. Measurement and Control Technology, 2018, 37(11):34-39.)
[15] 宋小娜,芮挺,王新晴. 结合语义边界信息的道路环境语义分割方法[J]. 计算机应用, 2019, 39(9):2505-2510.(SONG X N, RUI T, WANG X Q. Semantic segmentation method of road environment combined semantic boundary information[J]. Journal of Computer Applications, 2019, 39(9):2505-2510.)
[16] 吴宗胜,傅卫平,韩改宁. 基于深度卷积神经网络的道路场景理解[J]. 计算机工程与应用, 2017, 53(22):8-15.(WU Z S, FU W P, HAN G N. Road scene understanding based on deep convolutional neural network[J]. Computer Engineering and Applications, 2017, 53(22):8-15.)
[17] WANG P, CHEN P, YUAN Y, et al. Understanding convolution for semantic segmentation[C]//Proceedings of the 2018 IEEE Winter Conference on Applications of Computer Vision. Piscataway:IEEE, 2018:1451-1460.
[18] 郑菲,孟朝晖,郭闯世. 基于反卷积特征学习的图像语义分割算法[J]. 计算机系统应用, 2019, 28(1):149-157.(ZHENG F, MENG Z H, GUO C S. Image semantic segmentation algorithm based on deconvolution feature learning[J]. Computer System and Applications, 2019, 28(1):149-157.)

基于DeepLab v3的西藏地区降雨云团分割方法

Rainfall cloud segmentation method in Tibet based on DeepLab v3

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[2]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[3]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[4]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[5]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[6]	李朝, 兰海, 魏宪. 基于注意力的毫米波-激光雷达融合目标检测[J]. 计算机应用, 2021, 41(7): 2137-2144.
[7]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[8]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.
[9]	张洋, 江铭虎. 基于注意力机制的文本作者识别[J]. 计算机应用, 2021, 41(7): 1897-1901.
[10]	武维, 李泽平, 杨华蔚, 林川, 王忠德. 融合内容特征和时序信息的深度注意力视频流行度预测模型[J]. 计算机应用, 2021, 41(7): 1878-1884.
[11]	李想, 王卫兵, 尚学达. 指针生成网络和覆盖损失优化的Transformer在生成式文本摘要领域的应用[J]. 计算机应用, 2021, 41(6): 1647-1651.
[12]	刘世泽, 朱奕达, 陈润泽, 罗海勇, 赵方, 孙艺, 王宝会. 基于残差时域注意力神经网络的交通模式识别算法[J]. 计算机应用, 2021, 41(6): 1557-1565.
[13]	沈雪雯, 王晓东, 姚宇. 基于空间分频的超声图像分割注意力网络[J]. 计算机应用, 2021, 41(6): 1828-1835.
[14]	胡嵽, 冯子亮. 基于深度学习的轻量级道路图像语义分割算法[J]. 计算机应用, 2021, 41(5): 1326-1331.
[15]	赖雪梅, 唐宏, 陈虹羽, 李珊珊. 基于注意力机制的特征融合-双向门控循环单元多模态情感分析[J]. 计算机应用, 2021, 41(5): 1268-1274.