测绘学报 ›› 2023, Vol. 52 ›› Issue (1): 117-128.doi: 10.11947/j.AGCS.2023.20210286

• 地图学与地理信息 • 上一篇    下一篇

格式塔原则与图形凸分解结合的建筑物群直线模式识别方法

魏智威1,2, 丁愫3, 童莹4, 程璐4, 刘洋4   

  1. 1. 中国科学院网络信息体系技术重点实验室, 北京 100830;
    2. 中国科学院空天信息创新研究院, 北京 100830;
    3. 浙江农林大学环境与资源学院, 浙江 杭州 311300;
    4. 武汉大学资源与环境科学学院, 湖北 武汉 430079
  • 收稿日期:2021-05-20 修回日期:2022-06-21 发布日期:2023-02-09
  • 作者简介:魏智威(1993—),男,博士,研究方向为地理信息智能化处理与可视化。E-mail: 2011301130108@whu.edu.cn
  • 基金资助:
    国家自然科学基金(41871378)

Linear building pattern recognition combining Gestalt principles and convex polygon decomposition

WEI Zhiwei1,2, DING Su3, TONG Ying4, CHENG Lu4, LIU Yang4   

  1. 1. Key Laboratory of Network Information System Technology, Institute of Electronic, Chinese Academy of Sciences, Beijing 100830, China;
    2. The Aerospace Information Research Institute, Chinese Academic of Sciences, Beijing 100830, China;
    3. College of Environmental and Resource Science, Hangzhou 311300, China;
    4. School of Resources and Environment Science, Wuhan University, Wuhan 430079, China
  • Received:2021-05-20 Revised:2022-06-21 Published:2023-02-09
  • Supported by:
    The National Natural Science Foundation of China (No.41871378)

摘要: 建筑物群空间分布模式是重要的城市结构特征。以往研究多基于格式塔原则将建筑物作为整体认知分布模式,忽略了从建筑物局部到整体的视觉认知过程而导致模式的漏识别。本文提出结合格式塔原则和图形凸分解识别直线模式方法:首先,基于三元组和格式塔原则定义直线模式;其次,结合图形凸分解识别直线模式,图形分解时顾及了建筑物图形的直角化特征。试验结果表明,本文方法能有效识别建筑群中直线模式,相比已有直线模式识别方法准确率和召回率分别提高了15.7%和30.5%。

关键词: 空间分布, 建筑物, 直线模式, 凸分解, 格式塔原则

Abstract: Building patterns are important local structures characterizing urban areas. Building patterns in previous studies are mostly recognized based on the Gestalt principles in which buildings are considered as a whole. However, human vision is also proved as a parts-based system, and some visually aware patterns may fail to be recognized with the existing methods. This paper first combines Gestalt principles and the convex polygon decomposition to recognize linear patterns. First, the linear patterns are defined based on the triples and Gestalt principles. Second, linear patterns are recognized combining the convex polygon decomposition, and the buildings' orthogonal features are considered in their decomposition. The experimental results show that proposed method is effective to recognize the linear patterns in study area. Compared with the existing methods, the accuracy and recall have increased by 15.7% and 30.5%, respectively.

Key words: spatial distribution, building, linear pattern, convex decomposition, Gestalt principles

中图分类号: