测绘学报 ›› 2024, Vol. 53 ›› Issue (6): 1098-1112.doi: 10.11947/j.AGCS.2024.20230405

• 智能化测绘 • 上一篇    下一篇

遥感影像高可信智能不变检测技术框架与方法实践

宁晓刚(), 张翰超(), 张瑞倩   

  1. 中国测绘科学研究院,北京 100036
  • 收稿日期:2023-09-13 发布日期:2024-07-22
  • 通讯作者: 张翰超 E-mail:ningxg@casm.ac.cn;zhanghc@casm.ac.cn
  • 作者简介:宁晓刚(1979—),男,博士,研究员,主要从事自然资源监测和遥感应用研究。 E-mail:ningxg@casm.ac.cn
  • 基金资助:
    国家重点研发计划(2023YFB3907602)

Practical framework and methodology for high-performance intelligent invariant detection in remote sensing imagery

Xiaogang NING(), Hanchao ZHANG(), Ruiqian ZHANG   

  1. Chinese Academy of Surveying and Mapping, Beijing 100036, China
  • Received:2023-09-13 Published:2024-07-22
  • Contact: Hanchao ZHANG E-mail:ningxg@casm.ac.cn;zhanghc@casm.ac.cn
  • About author:NING Xiaogang (1979—), male, PhD, researcher, majors in natural resource monitoring and remote sensing applications. E-mail: ningxg@casm.ac.cn
  • Supported by:
    The National Key Research and Development Program of China(2023YFB3907602)

摘要:

针对传统变化检测技术面临的样本类别不平衡、算法适用性差和知识应用不足问题,本研究从逆向角度出发,提出了遥感影像高可信智能地类不变检测技术框架。该框架通过智能化算法准确提取各类任务均不感兴趣的稳定不变区域,从而在实际应用中压缩作业面积,提高生产效率。在数据预处理基础上,根据不变检测特点构建样本库,提出先验信息引导的全局-局部不变检测方法消除整体性和局部性“伪变化”,形成格网化不变掩膜,并从精度和效率角度提出压盖准度和压盖幅度两个对象级指标进行评价。在全国多个地区的实践表明,该框架能够在保证精度的同时大幅减少人工目视判读工作量,显著提升提取效率,为实际应用场景下的遥感变化信息提取提供了全新范式。

关键词: 变化检测, 不变检测, 人工智能, 遥感影像

Abstract:

In addressing the challenges posed by sample category imbalance, limited algorithm applicability, and inadequate knowledge application inherent in traditional change detection techniques, we propose a novel framework for high-reliability, intelligent invariant detection of land classes in remote sensing imagery. This framework employs advanced algorithms to precisely extract stable invariant areas that are typically irrelevant to various tasks, thereby reducing the operational footprint and boosting productivity in practical settings. Commencing with data preprocessing, a sample library tailored to the specifics of invariant detection is developed. Additionally, we introduce a method for invariant detection that utilizes prior information to guide the discrimination between global and local pseudo-changes. This approach leads to the creation of a gridded invariant mask and the introduction of two object-level metrics—compression accuracy and compression range—to assess the framework's performance in terms of accuracy and efficiency. Empirical validation across multiple national regions confirms that this framework not only minimizes the workload associated with manual visual interpretation but also significantly improves the efficiency of data extraction, thus offering a groundbreaking solution for extracting change information from remote sensing data in real-world scenarios.

Key words: change detection, changeless detection, artificial intelligence, remote sensing imagery

中图分类号: