测绘通报 ›› 2024, Vol. 0 ›› Issue (3): 13-18.doi: 10.13474/j.cnki.11-2246.2024.0303

• 耕地监测的遥感应用 • 上一篇    下一篇

基于深度学习的耕地非农化遥感监测与时空分析——以开阳县为例

张兰兰, 王红雷   

  1. 贵州省第三测绘,贵州 贵阳 550004
  • 收稿日期:2023-09-18 发布日期:2024-04-08
  • 通讯作者: 王红雷,E-mail:77133320@qq.com
  • 作者简介:张兰兰(1987—),女,硕士,高级工程师,研究方向为地理信息开发及应用。E-mail:478306661@qq.com

Non-agricultural monitoring and spatio-temporal analysis study of cultivated land based on deep learning method:a case study of Kaiyang county

ZHANG Lanlan, WANG Honglei   

  1. The Third Surveying and Mapping Institute of Guizhou Province, Guiyang 550004, China
  • Received:2023-09-18 Published:2024-04-08

摘要: 如何快速发现耕地非农化违法行为,并了解其空间分布和变化过程是从根本上减少耕地非农化行为的核心问题。基于多时相遥感影像数据,本文建立了一套耕地非农化监测指标体系和具有本地地形、地物特征的样本库,利用深度学习技术搭建遥感变化检测模型,将其应用于开阳县耕地非农化的时序化监测中。在此基础上,运用核密度估算法分析探讨区域耕地非农化的时空分布特征。应用结果表明,将卫星遥感与深度学习技术相结合,可实现大范围内耕地非农化的快速动态监测,开阳县2021年4月—2022年12月监测到的新增违法非农化行为整体呈下降态势,但存在局部聚集区域,且违法数量的高低表现出较为明显的季节特征。

关键词: 遥感影像, 耕地, 非农化, 深度学习, 核密度估算

Abstract: How to quickly detect illegal cultivated land non-agriculturalization and understand its spatial distribution and change process is a central issue of fundamentally reducing cultivated land non-agriculturalization.Based on multi-temporal remote sensing image,a monitoring index system for land non-agriculturalization and a sample database with local topographic features are established.A remote sensing change detection model is established using deep learning technology,and applied to the temporal monitoring of land non-agriculturalization in Kaiyang county.On this basis,the spatial and temporal distribution characteristics of regional land non-agriculturalization are discussed using kernel density estimation spatial analysis method.The results show that the combination of satellite remote sensing and deep learning technology can achieve rapid and dynamic monitoring of land non-agriculturalization in a large range.The overall trend of new illegal land non-agriculturalization activities monitored in Kaiyang county from April 2021 to December 2022 is decreasing,but there are local aggregation areas and the number of illegal activities shows relatively obvious seasonal characteristics.

Key words: remote sensing images, cultivated land, non-agriculturalization, deep leaming, kernel density estimation

中图分类号: