Journal of Integrative Agriculture ›› 2026, Vol. 25 ›› Issue (8): 3469-3482.DOI: 10.1016/j.jia.2025.10.014

• • 上一篇    下一篇

无需生成耕地地块图即可识别耕地地块变化：一种轻量化结构变化检测方法

  

  • 收稿日期:2025-06-09 修回日期:2025-10-27 接受日期:2025-09-08 出版日期:2026-08-20 发布日期:2026-07-09

Understanding cropland parcel change without producing cropland parcel maps: A novel structural change detection approach

Shiyao Li1, 2, Qiangyi Yu2, 3#, Yulin Duan2, Huibin Li2, Wenjuan Li2, Zhanli Sun3, Daniel Müller3, 4, 5, Baofeng Su1#, Wenbin Wu2   

  1. 1 College of Mechanical and Electronic Engineering, Northwest A&F University, Yangling 712100, China

    2 State Key Laboratory of Efficient Utilization of Arable Land in China/Key Laboratory of Agricultural Remote Sensing (AGRIRS), Ministry of Agriculture and Rural Affairs/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China

    3 Leibniz Institute of Agricultural Development in Transition Economies (IAMO), Halle (Saale) 06120, Germany

    4 Geography Department, Humboldt-Universität zu Berlin, Berlin 10099, Germany

    5 Integrative Research Institute on Transformations of Human-Environment Systems (IRI THESys), Humboldt-Universität zu Berlin, Berlin 10099, Germany

  • Received:2025-06-09 Revised:2025-10-27 Accepted:2025-09-08 Online:2026-08-20 Published:2026-07-09
  • About author:Shiyao Li, E-mail: shiyaoli@nwafu.edu.cn; #Correspondence Qiangyi Yu, E-mail: yuqiangyi@caas.cn; Baofeng Su, E-mail: bfs@nwsuaf.edu.cn
  • Supported by:

    This work was jointly supported by the National Key Research and Development Program of China (2022YFB3903505) and the Central Public-interest Scientific Institution Basal Research Fund, China (Y2025YC87).  

PDF

摘要：

耕地地块是农业生产的基本单元，其面积与形状可能因土地整治等人类活动的影响而发生变化。虽然遥感技术已广泛应用于耕地地块制图，但基于全域覆盖制图来检测地块变化，成本高、耗时长。为此，本文提出一种无需生成完整地块图的轻量化结构变化检测算法，以边缘像素数量作为地块结构变化的代理指标，快速判定是否发生变化及其空间位置。具体步骤包括：首先，应用Sobel算子从双时相影像中提取地块的总边缘像素；其次，采用连通区域标记法识别并剔除田间建筑、输电塔等造成的伪边缘；随后通过形态学膨胀与骨架提取进行拓扑优化，消除冗余边缘像素，保留地块的主要结构骨架；最后，通过统计并比较双时相影像中的边缘像素数量，判断地块是否发生变化。本文在东亚五个土地整治显著区域开展实验验证，结果表明该方法检测效果稳健：准确率、精确率、召回率及F1分数均超过0.85。通过有效筛除冗余边缘像素，降低了噪声干扰，提升了检测效率和精度。该方法将遥感中的语义变化检测拓展至结构变化检测，可在不生成完整耕地地块图的前提下快速、精准地识别耕地地块变化，为大尺度识别变化热点与土地整治项目监测提供新的技术路径。

Abstract:

Cropland parcels are the basic unit for agricultural production, and their size and shape may change due to human activities, e.g., land consolidation.  Remote sensing has been increasingly used for mapping cropland parcel, yet detecting changes in cropland parcels by wall-to-wall mapping is time-consuming.  This paper proposes a new algorithm to identify whether and where cropland parcel changes have been undertaken without generating complete parcel maps.  We use the number of edge pixels derived from remote sensing imagery as a proxy indicator for cropland parcel changes.  First, we apply a Sobel operator to delineate the total edge pixels of parcels from dual-time images.  Second, we apply the connected-components labeling to remove pseudo-edges arising from non-cropland built structures and transmission towers.  We then perform topological optimization, including morphological dilation and skeleton extraction, to eliminate redundant edge pixels for parcel structure.  Finally, we detect whether parcel changes have been undertaken by counting and comparing the number of edge pixels derived from dual-time images.  We applied this innovative framework in five regions in East Asia where land consolidation has significantly changed cropland parcels.  Our method demonstrated robust detection results, with stable accuracy, precision, recall, and F1-score, all exceeding 0.85.  Screening redundant edge pixels reduced noise and permitted efficient detection of changes in cropland parcels.  Our method extends the traditional detection of semantic change to structural change and can quickly detect cropland parcel changes with high accuracy.  This capability offers the potential to identify hotspot areas of cropland changes on a larger scale without the need to produce full cropland maps, which is particularly useful for monitoring land consolidation programs.

Key words: field boundary delineation , image segmentation ,  change detection ,  land consolidation ,  remote sensing