Page 77 - 《武汉大学学报(信息科学版)》2025年第6期
P. 77

第 50 卷第 6 期          隋百凯等:基于几何先验约束的高点多视角损毁建筑物检测方法                                    1099


               [14]  FATHALLA  R ,  VOGIATZIS  G.   A  Deep          Building  Facade  Damage  Detection  Based  on  the
                    Learning  Pipeline  for  Semantic  Facade  Segmenta‑  Gini Index from Oblique Aerial Images[J].  Geoma‑
                    tion [C]//British  Machine  Vision  Conference ,   tics  and  Information  Science  of  Wuhan  University,
                    London ,  UK ,  2017.                            2017, 42(12): 1744-1748.
               [15]  WENG  X ,  YAN  Y ,  CHEN  S ,  et  al.   Stage-  [21]  眭 海 刚 ,  黄 立 洪 ,  刘 超 贤 .   利 用 具 有 注 意 力 的
                    Aware  Feature  Alignment  Network  for  Real-Time   Mask R-CNN 检测震害建筑物立面损毁[J].  武汉
                    Semantic  Segmentation  of  Street  Scenes[J].   IEEE   大 学 学 报(信 息 科 学 版),  2020,  45(11):  1660-
                    Transactions  on  Circuits  and  Systems  for  Video   1668.
                    Technology, 2022, 32(7): 4444-4459.              SUI  Haigang,  HUANG  Lihong,  LIU  Chaoxian.
               [16]  MOHAN  A,  POOBAL  S.   Crack  Detection  Using   Detecting Building Facade Damage Caused by Earth‑
                    Image  Processing:  A  Critical  Review  and  Analysis  quake  Using  CBAM-Improved  Mask  R-CNN[J].
                    [J].   Alexandria  Engineering  Journal,  2018,  57  Geomatics  and  Information  Science  of  Wuhan  Uni‑
                    (2): 787-798.                                    versity, 2020, 45(11): 1660-1668.
               [17]  SHAN B H, ZHENG S J, OU J P.  A Stereovision-  [22]  CHENG B W, MISRA I, SCHWING A G, et al.
                    Based Crack Width Detection Approach for Concrete   Masked-Attention  Mask  Transformer  for  Universal
                    Surface Assessment[J].  KSCE Journal of Civil En‑  Image  Segmentation[C]//IEEE/CVF  Conference
                    gineering, 2016, 20(2): 803-812.                 on  Computer  Vision  and  Pattern  Recognition
               [18]  PEREIRA F C, PEREIRA C E.  Embedded Image      (CVPR), New Orleans, USA, 2022.
                    Processing  Systems  for  Automatic  Recognition  of   [23]  HE  K  M,  GKIOXARI  G,  DOLLÁR  P,  et  al.
                    Cracks  Using  UAVs[J].   IFAC-PapersOnLine,     Mask  R-CNN[C]//IEEE  International  Conference
                    2015, 48(10): 16-21.                             on Computer Vision (ICCV), Venice, Italy, 2017.
               [19]  LOVERDOS  D ,  SARHOSIS  V.   Automatic    [24]  LIU Z, LIN Y T, CAO Y, et al.  Swin Transformer:
                    Image-Based  Brick  Segmentation  and  Crack  Detec‑  Hierarchical Vision Transformer Using Shifted Win‑
                    tion  of  Masonry  Walls  Using  Machine  Learning  dows[C]//IEEE/CVF  International  Conference  on
                    [J].   Automation  in  Construction ,  2022 ,  140 :   Computer Vision (ICCV), Montreal, Canada, 2021.
                    104389.                                     [25]  LIU J J, HOU Q B, CHENG M M, et al.  Improving
               [20]  涂继辉, 眭海刚, 吕枘蓬, 等 .  基于基尼系数的倾                    Convolutional Networks with Self-Calibrated Convo‑
                    斜航空影像中建筑物立面损毁检测[J].  武汉大学                        lutions[C]//IEEE/CVF  Conference  on  Computer
                    学报(信息科学版), 2017, 42(12): 1744-1748.              Vision  and  Pattern  Recognition (CVPR),  Seattle,
                    TU  Jihui,  SUI  Haigang ,  LÜ  Ruipeng ,  et  al.    USA, 2020.
   72   73   74   75   76   77   78   79   80   81   82