测绘学报 ›› 2023, Vol. 52 ›› Issue (12): 2197-2208.doi: 10.11947/j.AGCS.2023.20220539

• 地图学与地理信息 • 上一篇    下一篇

典型时间规整算法支持下的建筑物形状相似性度量

李精忠1,2,3, 毛凯楠2,3   

  1. 1. 兰州交通大学测绘与地理信息学院, 甘肃 兰州 730070;
    2. 武汉大学资源与环境科学学院, 湖北 武汉 430079;
    3. 自然资源部城市国土资源监测与仿真重点实验室, 广东 深圳 518000
  • 收稿日期:2022-09-19 修回日期:2023-06-08 发布日期:2024-01-03
  • 通讯作者: 毛凯楠 E-mail:maokainan@whu.edu.cn
  • 作者简介:李精忠(1983-),男,博士,教授,研究方向为地图综合、空间分析与大数据挖掘。E-mail:00009232@whu.edu.cn
  • 基金资助:
    国家自然科学基金(42271454;42001402);湖北省自然科学基金(2022CFB053);自然资源部城市国土资源监测与仿真重点实验室开放基金(KF-2022-07-017);兰州交通大学研究生教育教学质量提升工程(JG202301);中国科学院数字地球重点实验室开放基金(2022LDE004)

A canonical time warping algorithm for building shape similarity measurement

LI Jingzhong1,2,3, MAO Kainan2,3   

  1. 1. Faculty Geomatics, Lanzhou Jiaotong University, Lanzhou 730070, China;
    2. School of Resource and Environmental Sciences, Wuhan University, Wuhan 430079, China;
    3. Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518000, China
  • Received:2022-09-19 Revised:2023-06-08 Published:2024-01-03
  • Supported by:
    The National Natural Science Foundation of China (Nos. 42271454;42001402);The Natural Science Foundation of Hubei Province (No. 2022CFB053);The Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation,Ministry of Natural Resources (No. KF-2022-07-017);The Graduate Education Teaching Quality Improvement Project of Lanzhou Jiaotong University (No. JG202301);The Open Research Fund of Key Laboratory of Digital Earth Science, Chinese Academy of Sciences (No. 2022LDE004)

摘要: 本文提出了一种基于典型时间规整(canonical time warping,CTW)算法的形状相似性度量模型,该模型运用动态时间规整(dynamic time warping,DTW)算法和典型相关分析(canonical correlation analysis,CCA),对齐具有不同节点个数的建筑物坐标序列,并综合评价不同形状轮廓之间的相似性。该方法直接以矢量坐标作为模型输入而无须复杂的形状编码,顾及了建筑物图形原始的轮廓特征,可高效地应用于形状检索等场景。试验表明,CTW算法在度量形状相似性时具有平移、旋转、缩放和镜像不变性,能有效度量建筑物形状之间的形状相似性,其结果符合人类的空间视觉认知。

关键词: 建筑物, 形状相似性, 典型时间规整, 空间认知

Abstract: This paper proposes a shape similarity measurement model based on canonical time warping (CTW) algorithm. The model combines canonical correlation analysis (CCA) and dynamic time warping (DTW) to align building coordinate sequences with different number of vertices, which can comprehensively evaluate the shape similarity between different shape contours. This method directly uses vector coordinates as model input without constructing complex shape coding and considers the original contour features of building shapes, which can be applied efficiently to shape retrieval and other scenarios. Experiments show that CTW algorithm is invariant to translation, rotation, scaling and mirroring when used to measure the similarity of geometric objects, and can effectively measure the shape similarity between building shapes. The results are consistent with human spatial visual cognition.

Key words: buildings, shape similarity, canonical time warping, spatial cognition

中图分类号: