SHAO Zhenfeng, SUN Yueming, XI Jiangbo, LI Yan. Intelligent Optimization Learning for Semantic Segmentation of High Spatial Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2022, 47(2): 234-241. DOI: 10.13203/j.whugis20200640
Citation: SHAO Zhenfeng, SUN Yueming, XI Jiangbo, LI Yan. Intelligent Optimization Learning for Semantic Segmentation of High Spatial Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2022, 47(2): 234-241. DOI: 10.13203/j.whugis20200640

Intelligent Optimization Learning for Semantic Segmentation of High Spatial Resolution Remote Sensing Images

Funds: 

The National Natural Science Foundation of China 41771454

The National Natural Science Foundation of China 61806022

the Jiangxi Province 03 Special Project and 5G Project 20212ABC03A09

the Natural Science Foundation of Inner Mongolia Autonomous Region 2019MS04017

the Scientific Research Project of Colleges and Universities in Inner Mongolia Autonomous Region NJZY20277

the State Key Laboratory of Geo-Information Engineering SKLGIE2018-M-3-4

the Fundamental Research Funds for the Central Universities, Chang'an University 300102269103

the Fundamental Research Funds for the Central Universities, Chang'an University 300102269304

the Fundamental Research Funds for the Central Universities, Chang'an University 300102269205

More Information
  • Author Bio:

    SHAO Zhenfeng, PhD, professor, specializes in research and education of smart city and urban remote sensing. E-mail: shaozhenfeng@whu.edu.cn

  • Corresponding author:

    SUN Yueming, master. E-mail: sunyueming@whu.edu.cn

    XI Jiangbo, PhD, associate professor. E-mail: xijiangbo@chd.edu.cn

  • Received Date: December 15, 2020
  • Published Date: February 04, 2022
  •   Objectives   With the hardware development of remote sensing sensors, the high spatial resolution remote sensing images are widely used. In the actual classification, typical classification algorithms can not achieve high accuracy and efficiency, while deep learning semantic segmentation algorithms can not achieve good generalization.
      Methods   In order to adapt to the large-scale high-resolution images, we design a semantic segmentation model of simulated annealing hyperparameter optimization and depthwise separable convolution based on U-Net. Firstly, the depthwise separable convolutional module is used to extract the features on the baseline. Then, the intelligent optimization learning model based on simulated annealing searches the global optimal solution of hyperparameters. Finally, experiments were carried out in ISPRS2D and Gaofen image dataset (GID).
      Results   Compared to other classification methods, the proposed method achieves the highest classification accuracy in buildings, low vegetation, trees, cars and overall accuracy, and the total accuracy of classification results reaches 86.5% in ISPRS2D. And in the classification results of GID, the accuracies of the proposed method in water, grassland, forest and general classification are all greatly improved. The mean intersection over union of the proposed method is also higher than that of other methods.
      Conclusions   The results demonstrated the higher efficiency, higher accuracy and robustness of the proposed method.
  • [1]
    陈玲, 贾佳, 王海庆. 高分遥感在自然资源调查中的应用综述[J]. 国土资源遥感, 2019, 31(1): 1-7 https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201901001.htm

    Chen Ling, Jia Jia, Wang Haiqing. An Overview of Applying High Resolution Remote Sensing to Natural Resources Survey[J]. Remote Sensing for Land & Resources, 2019, 31(1): 1-7 https://www.cnki.com.cn/Article/CJFDTOTAL-GTYG201901001.htm
    [2]
    潘银, 邵振峰, 程涛, 等. 利用深度学习模型进行城市内涝影响分析[J]. 武汉大学学报·信息科学版, 2019, 44(1): 132-138 doi: 10.13203/j.whugis20170217

    Pan Yin, Shao Zhenfeng, Cheng Tao, et al. Analysis of Urban Waterlogging Influence Based on Deep Learning Model[J]. Geomatics and Information Science of Wuhan University, 2019, 44(1): 132-138 doi: 10.13203/j.whugis20170217
    [3]
    杨泽宇, 张洪艳, 明金, 等. 深度学习在高分辨率遥感影像冬油菜提取中的应用[J]. 测绘通报, 2020(9): 110-113 https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB202009024.htm

    Yang Zeyu, Zhang Hongyan, Ming Jin, et al. Extraction of Winter Rapeseed from High-Resolution Remote Sensing Imagery via Deep Learning[J]. Bulletin of Surveying and Mapping, 2020(9): 110-113 https://www.cnki.com.cn/Article/CJFDTOTAL-CHTB202009024.htm
    [4]
    贾永红, 周伟伟, 周明婷. 结合规划矢量的高分辨率遥感道路施工进度监测[J]. 测绘地理信息, 2020, 45(2): 106-110 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202002024.htm

    Jia Yonghong, Zhou Weiwei, Zhou Mingting. Road Construction Monitoring Based on Vector Data and High-Resolution Remote Sensing Images[J]. Journal of Geomatics, 2020, 45(2): 106-110 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG202002024.htm
    [5]
    唐尧, 王立娟, 马国超, 等. 基于"高分+"的金沙江滑坡灾情监测与应用前景分析[J]. 武汉大学学报·信息科学版, 2019, 44(7): 1082-1092 doi: 10.13203/j.whugis20190048

    Tang Yao, Wang Lijuan, Ma Guochao, et al. Disaster Monitoring and Application Prospect Analysis of the Jinsha River Landslide Based on "Gaofen+" [J]. Geomatics and Information Science of Wuhan University, 2019, 44(7): 1082-1092 doi: 10.13203/j.whugis20190048
    [6]
    马长辉, 黄登山. 纹理与几何特征信息在高空间分辨率遥感影像分类中的应用[J]. 测绘地理信息, 2019, 44(6): 66-70 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201906017.htm

    Ma Changhui, Huang Dengshan. Application of Texture Features and Geometric Feature Information in High Spatial Resolution Remote Sensing Image Classification[J]. Journal of Geomatics, 2019, 44(6): 66-70 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG201906017.htm
    [7]
    朱卫. 基于随机森林算法的街道场景语义分割[D]. 哈尔滨: 哈尔滨理工大学, 2019

    Zhu Wei. Semantic Segmentation of Street Scene Based on Random Forest Algorithm[D]. Harbin: Harbin University of Science and Technology, 2019
    [8]
    亓祥惠. 基于MRF与模糊聚类的图像分割算法研究[D]. 兰州: 兰州理工大学, 2019

    Qi Xianghui. Research on Image Segmentation Algorithm Based on MRF and Fuzzy Clustering[D]. Lanzhou: Lanzhou University of Technology, 2019
    [9]
    Bruzzone L, Carlin L. A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(9): 2587-2600 doi: 10.1109/TGRS.2006.875360
    [10]
    门计林, 刘越岩, 张斌, 等. 多结构卷积神经网络特征级联的高分影像土地利用分类[J]. 武汉大学学报·信息科学版, 2019, 44(12): 1841-1848 doi: 10.13203/j.whugis20180137

    Jilin Men, Liu Yueyan, Zhang Bin, et al. Land Use Classification Based on Multi-Structure Convolution Neural Network Features Cascading[J]. Geomatics and Information Science of Wuhan University, 2019, 44(12): 1841-1848 doi: 10.13203/j.whugis20180137
    [11]
    季顺平, 田思琦, 张驰. 利用全空洞卷积神经元网络进行城市土地覆盖分类与变化检测[J]. 武汉大学学报·信息科学版, 2020, 45(2): 233-241 doi: 10.13203/j.whugis20180481

    Ji Shunping, Tian Siqi, Zhang Chi. Urban Land Cover Classification and Change Detection Using Fully Atrous Convolutional Neural Network[J]. Geomatics and Information Science of Wuhan University, 2020, 45(2): 233-241 doi: 10.13203/j.whugis20180481
    [12]
    贾文翰, 刘越岩, 胡守庚. 基于ResNet34的高分遥感影像草本湿地信息提取[J]. 测绘地理信息, 2021, 46(S1): 97-99 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG2021S1022.htm

    Jia Wenhan, Liu Yueyan, Hu Shougeng. Extraction of Herbaceous Wetland Information from High Resolution Remote Sensing Image Based on ResNet34[J]. Journal of Geomatics, 2021, 46(S1): 97-99 https://www.cnki.com.cn/Article/CJFDTOTAL-CHXG2021S1022.htm
    [13]
    陈鹏, 汪本康, 高飒, 等. 利用ResNet进行建筑物倒塌评估[J]. 武汉大学学报·信息科学版, 2020, 45(8): 1179-1184 doi: 10.13203/j.whugis20200135

    Chen Peng, Wang Benkang, Gao Sa, et al. Building Collapse Assessment with Residual Network[J]. Geomatics and Information Science of Wuhan University, 2020, 45(8): 1179-1184 doi: 10.13203/j.whugis20200135
    [14]
    Breuel T M. The Effects of Hyperparameters on SGD Training of Neural Networks[EB/OL]. [2015-08-12]. https://arxiv.org/abs/1508.02788
    [15]
    Howard A G, Zhu M L, Chen B, et al. Mobile Nets: Efficient Convolutional Neural Networks for Mobile Vision Applications[EB/OL]. [2017-04-17]. https://arxiv.org/abs/1704.04861
    [16]
    Kang Z, Qu Z Y. Application of BP Neural Network Optimized by Genetic Simulated Annealing Algorithm to Prediction of Air Quality Index in Lanzhou[C]//20172nd IEEE International Conference on Computational Intelligence and Applications (ICCIA), Beijing, China, 2017
    [17]
    Tong X Y, Xia G S, Lu Q K, et al. Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models[J]. Remote Sensing of Environment, 2020, 237: 111322 doi: 10.1016/j.rse.2019.111322
    [18]
    Gerke M. Use of the Stair Vision Library Within the ISPRS2D Semantic Labeling Benchmark (Vaihingen)[EB/OL]. [2014-12-28]http://www2.isprs.org/vaihingen-2d-semantic-labeling-contest.html
    [19]
    Pan X R, Gao L R, Marinoni A, et al. Semantic Labeling of High Resolution Aerial Imagery and LiDAR Data with Fine Segmentation Network[J]. Remote Sensing, 2018, 10(5): 743 doi: 10.3390/rs10050743
    [20]
    Dong R S, Pan X Q, Li F Y. Dense U-Net-Based Semantic Segmentation of Small Objects in Urban Remote Sensing Images[J]. IEEE Access, 2019, 7: 65347-65356 doi: 10.1109/ACCESS.2019.2917952
    [21]
    Xiong D H, He C, Liu X L, et al. An End-to-End Bayesian Segmentation Network Based on a Generative Adversarial Network for Remote Sensing Images[J]. Remote Sensing, 2020, 12(2): 216 doi: 10.3390/rs12020216
  • Related Articles

    [1]ZHANG Xinchang, HUANG Jianfeng, NING Ting. Progress and Prospect of Cultivated Land Extraction from High-Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2023, 48(10): 1582-1590. DOI: 10.13203/j.whugis20230114
    [2]GAO Peng, LI Jiatian, YANG Ruchun, ZHANG Zelong, YANG Chao, ZHANG Xingyi. Remote Sensing Images Segmentation Based on Low-Dimensional Texture Feature Operator and Double-Mutant Butterfly Optimization Algorithm[J]. Geomatics and Information Science of Wuhan University, 2023, 48(1): 165-174. DOI: 10.13203/j.whugis20200496
    [3]YANG Jun, YU Xizi. Semantic Segmentation of High-Resolution Remote Sensing Images Based on Improved FuseNet Combined with Atrous Convolution[J]. Geomatics and Information Science of Wuhan University, 2022, 47(7): 1071-1080. DOI: 10.13203/j.whugis20200305
    [4]ZHANG Haiming, WANG Mingchang, CHEN Xueye, WANG Fengyan, YANG Guodong, GAO Su. Remote Sensing Change Detection Based on Deep Belief Networks Optimized by Domain Knowledge[J]. Geomatics and Information Science of Wuhan University, 2022, 47(5): 762-768. DOI: 10.13203/j.whugis20190471
    [5]CHEN Hang, LUO Bin. Multi-angle Remote Sensing Images Super-Resolution Reconstruction Using Dynamic Upsampling Filter Deep Network[J]. Geomatics and Information Science of Wuhan University, 2021, 46(11): 1716-1726. DOI: 10.13203/j.whugis20200651
    [6]ZHANG Liqiang, LI Yang, HOU Zhengyang, LI Xingang, GENG Hao, WANG Yuebin, LI Jingwen, ZHU Panpan, MEI Jie, JIANG Yanxiao, LI Shuaipeng, XIN Qi, CUI Ying, LIU Suhong. Deep Learning and Remote Sensing Data Analysis[J]. Geomatics and Information Science of Wuhan University, 2020, 45(12): 1857-1864. DOI: 10.13203/j.whugis20200650
    [7]SHAO Zhenfeng, ZHANG Yuan, HUANG Xin, ZHU Xiuli, WU Liang, WAN Bo. Mapping Impervious Surface with 2 m Using Multi-source High Resolution Remote Sensing Images[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12): 1909-1915. DOI: 10.13203/j.whugis20180196
    [8]LU Xuan, WANG Dingwen, SHI Wenxuan. Image Super-resolution with On-line Dictionary Learning[J]. Geomatics and Information Science of Wuhan University, 2018, 43(5): 719-725. DOI: 10.13203/j.whugis20150753
    [9]LIU Shuai, ZHU Yajie, XUE Lei. Remote Sensing Image Super-Resolution Method Using Sparse Representation and Classified Texture Patches[J]. Geomatics and Information Science of Wuhan University, 2015, 40(5): 578-582. DOI: 10.13203/j.whugis20130385
    [10]Du Zhiqiang, Luo Pan, Zhu Xiaoling, Zhang Yeting, Zhu Yixuan. Texture Optimization Methodology for 3D Building Based on Super Face[J]. Geomatics and Information Science of Wuhan University, 2014, 39(12): 1401-1405.
  • Cited by

    Periodical cited type(14)

    1. 高贤君,冉树浩,张广斌,杨元维. 基于多特征融合与对象边界联合约束网络的建筑物提取. 武汉大学学报(信息科学版). 2024(03): 355-365 .
    2. 汪超宇,杜震洪,汪愿愿. 结合通道交互空间组注意力与金字塔池化的高分影像语义分割网络. 浙江大学学报(理学版). 2024(02): 131-142+152 .
    3. 周丹,张国伟,张凯,潘明敏,范素海. 基于MapGIS深度学习的承灾体数据提取工具设计与实践. 测绘地理信息. 2024(03): 118-122 .
    4. 彭博洋,周春霞,朱冬雨,李明慈,肖倩雨,江萌. 利用U-Net的格陵兰冰盖冰面湖提取和面积变化分析. 武汉大学学报(信息科学版). 2024(09): 1621-1629 .
    5. 陈虹,汤军,龚阳春,陈志杰,王文达,王少华. 基于街景与高分遥感影像的超大城市绿地高精度识别与空间特征解析. 地球信息科学学报. 2024(12): 2818-2830 .
    6. 高鹏,李佳田,杨汝春,张泽龙,杨超,张兴忆. 遥感图像分割的低维纹理特征算子与双变异蝴蝶优化算法. 武汉大学学报(信息科学版). 2023(01): 165-174 .
    7. 查燕萍,龙北平. 基于遥感影像增强的林地植被树种分类研究. 测绘技术装备. 2023(02): 17-21 .
    8. 杜培军,张鹏,郭山川,唐鹏飞,潘小全,慕号伟. 融合光谱指数与高分影像的塑料大棚语义分割模型. 武汉大学学报(信息科学版). 2023(10): 1670-1683 .
    9. 张新长,黄健锋,宁婷. 高分辨率遥感影像耕地提取研究进展与展望. 武汉大学学报(信息科学版). 2023(10): 1582-1590 .
    10. 陈宇杨,张丽,陈博伟,邱玉宝. 基于改进U-Net模型的近海水产养殖池塘信息提取. 现代计算机. 2023(16): 8-14 .
    11. 琚丽君,田丰华,曾朝平. NMI特征优化边界敏感的LSC遥感影像分割算法. 遥感信息. 2023(05): 149-156 .
    12. 刘宇承,罗芳,杜清运,黄文丽,石仪玮. 深圳市宝安区土地利用遥感分类方法对比分析. 时空信息学报. 2023(04): 491-499 .
    13. 赵好好,管海燕. 一种结合图特征的高分辨率遥感图像随机行走分割方法. 遥感信息. 2023(06): 95-102 .
    14. 伏晏民,曾涛. 引入残差和注意力机制的U-Net模型在水土保持遥感监管人为扰动地块影像自动分割中的研究. 测绘. 2022(01): 16-21 .

    Other cited types(7)

Catalog

    Article views (1682) PDF downloads (207) Cited by(21)
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return