测绘通报 ›› 2023, Vol. 0 ›› Issue (11): 116-121.doi: 10.13474/j.cnki.11-2246.2023.0338

• 技术交流 • 上一篇    下一篇

基于深度学习的新增违法建设监测框架研究与应用

康停军1, 陈汭新1, 孙颖2, 夏义雄1, 王彬1   

  1. 1. 佛山市测绘地理信息研究院, 广东 佛山 528000;
    2. 中山大学地理科学与规划学院, 广东 广州 510275
  • 收稿日期:2023-08-07 出版日期:2023-11-25 发布日期:2023-12-07
  • 通讯作者: 陈汭新。E-mail:fschenrx@qq.com
  • 作者简介:康停军(1981—),男,博士,高级工程师,主要从事摄影测量与地理信息应用研究。E-mail:gisktj@163.com
  • 基金资助:
    国家自然科学基金面上项目(42071441);广东省基础与应用基础区域联合基金-青年基金项目(2020A1515110441)

Research and application of deep learning-based framework for monitoring and detecting new illegal construction

KANG Tingjun1, CHEN Ruixin1, SUN Ying2, XIA Yixiong1, WANG Bin1   

  1. 1. Foshan Surveying Mapping and Geoinformation Research Institute, Foshan 528000, China;
    2. School of Geography and Planning, Sun Yat-Sen University, Guangzhou 510275, China
  • Received:2023-08-07 Online:2023-11-25 Published:2023-12-07

摘要: 科学化、智慧化严控新增违法建设是城市高质量发展的必然要求。针对新增违法建设类型多样、隐蔽性强、管理交叉、多头执法等难点,本文基于高分辨率遥感影像,利用耦合FPN与Mask-RNN多任务的建筑物边界提取算法,构建了“建设行为监测—多源数据融合分析—协同分派治理”的新增违法建设全链条管理框架,提升了高空视角下违法建设的精准发现、动态管理能力,为助力城市精细化管理提供了技术支撑。

关键词: 新增违法建设, 深度学习, 高分辨率影像, 全链条管理框架

Abstract: Scientific and intelligent control of new illegal constructions is an inevitable requirement for high-quality urban development. Aiming at the characteristics of new illegal constructions with diverse types, strong concealment, administrative intersection and difficult disposal, this paper adopts a building boundary extraction algorithm based on high-resolution remote sensing images and management data of functional departments, coupled with FPN and Mask-RCNN multi-task fusion. It constructs a whole chain management framework of new illegal constructions from “Construction Behavior Monitoring-Multi-source Data Fusion Analysis-Collaborative Assignment Governance”, which provides technical support for dynamic monitoring and precise management under the high-altitude perspective of the city.

Key words: new illegal construction, deep learning, high resolution, the whole chain of management framework

中图分类号: