Page 51 - 《武汉大学学报(信息科学版)》2025年第9期
P. 51

第 50 卷第 9 期          周亚男等:深度时空卷积网络支持的地块尺度作物种植类型分类                                    1779


                    Sensing, 2019, 11(13): 1619.                     Sensing, 2021, 60: 4403216.
               [14]  ZHOU Y N, LI J, FENG L, et al.  Adaptive Scale   [22]  WEI P L, CHAI D F, LIN T, et al.  Large-Scale
                    Selection  for  Multiscale  Segmentation  of  Satellite   Rice  Mapping  Under  Different  Years  Based  on
                    Images[J].  IEEE Journal of Selected Topics in Ap⁃  Time-Series Sentinel-1 Images Using Deep Seman⁃
                    plied  Earth  Observations  and  Remote  Sensing,   tic Segmentation Model[J].  ISPRS Journal of Photo⁃
                    2017, 10(8): 3641-3651.                          grammetry and Remote Sensing, 2021, 174: 198-214.
               [15]  李前景, 刘珺, 米晓飞, 等 .  面向对象与卷积神经               [23]  韩衍欣, 蒙继华 .  面向地块的农作物遥感分类研究
                    网络模型的 GF-6 WFV 影像作物分类 [J].  遥感                   进展[J].  国土资源遥感, 2019, 31(2): 1-9.
                    学报, 2021, 25(2): 549-558.                        HAN Yanxin, MENG Jihua.  A Review of Per-Field
                    LI  Qianjing,  LIU  Jun,  MI  Xiaofei,  et  al.   Object-  Crop Classification Using Remote Sensing[J].  Remote
                    Oriented  Crop  Classification  for  GF-6  WFV  Re⁃  Sensing for Land & Resources, 2019, 31(2): 1-9.
                    mote Sensing Images Based on Convolutional Neural   [24]  杨颖频, 吴志峰, 骆剑承, 等 .  时空协同的地块尺
                    Network[J].   National  Remote  Sensing  Bulletin.    度作物分布遥感提取[J].  农业工程学报, 2021, 37
                    2021, 25(2):549-558.                            (7): 166-174.
               [16]  骆剑承, 吴田军, 吴志峰, 等 .  地理图斑智能计算                    YANG  Yingpin,  WU  Zhifeng,  LUO  Jiancheng,  et
                    及 模 式 挖 掘 方 法 研 究[J].   地 球 信 息 科 学 学 报 ,        al.  Parcel-Based Crop Distribution Extraction Using
                    2020, 22(1): 57-75.                              the Spatiotemporal Collaboration of Remote Sensing
                    LUO Jiancheng, WU Tianjun, WU Zhifeng, et al.    Data[J].  Transactions of the Chinese Society of Ag⁃
                    Methods  of  Intelligent  Computation  and  Pattern   ricultural Engineering, 2021, 37(7): 166-174.
                    Mining  Based  on  Geo-Parcels[J].   Journal  of  Geo ⁃  [25]  SUN Y W, LI Z L, LUO J C, et al.  Farmland Par⁃
                    Information Science, 2020, 22(1): 57-75.         cel-Based  Crop  Classification  in  Cloudy/Rainy
               [17]  XU L, MING D P, ZHOU W, et al.  Farmland Ex⁃    Mountains  Using  Sentinel-1  and  Sentinel-2  Based
                    traction from High Spatial Resolution Remote Sensing   Deep Learning[J].  International Journal of Remote
                    Images Based on Stratified Scale Pre-estimation[J].    Sensing, 2022, 43(3): 1054-1073.
                    Remote Sensing, 2019, 11(2): 108.           [26]  RUßWURM  M,  PELLETIER  C,  ZOLLNER  M,
               [18]  龚健雅 .  人工智能时代测绘遥感技术的发展机遇与                       et al.  Breizhcrops: A Time Series Dataset for Crop
                    挑 战[J].  武 汉 大 学 学 报(信 息 科 学 版), 2018, 43        Type  Mapping[J].   The  International  Archives  of
                    (12): 1788-1796.                                 the  Photogrammetry,  Remote  Sensing  and  Spatial
                    GONG Jianya.  Chances and Challenges for Develop⁃  Information Sciences, 2020, 13(2): 1545-1551.
                    ment of Surveying and Remote Sensing in the Age of   [27]  SONG  C  H,  WOODCOCK  C  E,  SETO  K  C,  et
                    Artificial  Intelligence[J].   Geomatics  and  Informa⁃  al.  Classification and Change Detection Using Land⁃
                    tion  Science  of  Wuhan  University,  2018,  43(12):   sat TM Data when and how to Correct Atmospheric
                    1788-1796.                                       Effects?[J].   Remote  Sensing  of  Environment,
               [19]  周楠 . 基于深度学习的精细化土地覆盖变化遥感提                        2001, 75(2): 230-244.
                    取方法研究[D]. 北京:中国科学院大学,2022.                  [28]  QIU Z F, YAO T, MEI T.  Learning Spatio-Tem⁃
                    ZHOU  Nan.   Deep  Learning-based  Fine-Grained   poral Representation with Pseudo-3D Residual Net⁃
                    Land  Cover  Change  Detection  on  Remote  Sensing   works[C]//IEEE International Conference on Com⁃
                    Images[D]. Beijing:  University  of  Chinese  Acade⁃  puter Vision, Venice, Italy, 2017.
                    my of Sciences, 2022.                       [29]  HARA  K,  KATAOKA  H,  SATOH  Y.   Can  Spa⁃
               [20]  张兵 .  遥感大数据时代与智能信息提取[J].  武汉大                   tiotemporal  3D  CNNS  Retrace  the  History  of  2D
                    学学报(信息科学版), 2018, 43(12): 1861-1871.             CNNS and ImageNet?[C]//IEEE/CVF Conference
                    ZHANG  Bing.   Remotely  Sensed  Big  Data  Era  and   on  Computer  Vision  and  Pattern  Recognition,  Salt
                    Intelligent  Information  Extraction [J].   Geomatics   Lake City, USA, 2018.

                    and  Information  Science  of  Wuhan  University,   [30]  DAI F, LIU H, MA Y K, et al.  Dense Scale Network
                    2018, 43(12): 1861-1871.                         for  Crowd  Counting[C]//International  Conference
               [21]  YANG L B, HUANG R, HUANG J F, et al.  Se⁃       on Multimedia Retrieval, Taipei, China, 2021.
                    mantic  Segmentation  Based  on  Temporal  Features:   [31]  BAI S, KOLTER J Z, KOLTUN V.  An Empirical
                    Learning  of  Temporal – Spatial  Information  from   Evaluation  of  Generic  Convolutional  and  Recurrent
                    Time-Series  SAR  Images  for  Paddy  Rice  Mapping  Networks  for  Sequence  Modeling  [EB/OL].
                    [J].   IEEE  Transactions  on  Geoscience  and  Remote   [2018-12-21] https://arxiv. org/abs/1803. 01271.
   46   47   48   49   50   51   52   53   54   55   56