Abstract

Land use and land cover (LULC) mapping is a basic research topic in geography. In deep-learning (DL)-based LULC mapping, there are primarily the following issues: training and testing samples for DL are typically annotated by indoor visual interpretation without field surveys; remotely sensed scene classification based on DL typically lacks fine geometric boundaries for ground objects; historical big data (HBD) (e.g., vector data) are underutilized in DL; studies of large-scale remote sensing mapping (LSRSM) using DL are rare. To solve above issues, this paper proposes an object-oriented (i.e., polygon-based) and DL-based (OODLB) image classification method assisted by HBD for LSRSM to serve for monitoring the soil erosion and water loss (SEWL) in the Yangtze River Basin that includes the following steps: (1) using HBD and OpenStreetMap data, ground objects are vectorized; (2) a remote sensing interpretation key database is established by field surveys and data augmentation; (3) object-oriented (i.e., polygon-based) and Inception-ResNet-V2-based LULC mapping is performed; (4) DL-based classification results are updated by man-machine mutual verification. The experimental results of one county of the Yangtze River Basin show state-of-the-art performance with an overall accuracy of 90.20% in comparison of 75.60% for eCognition. It provides an excellent framework for OODLB large-scene mapping.

摘要

土地利用和土地覆盖（LULC）制图是地理学的基础研究课题。在基于深度学习 (DL) 的 LULC 映射中，主要存在以下问题：DL 的训练和测试样本通常由室内目视解译注释，无需实地调查；基于深度学习的遥感场景分类通常缺乏地物的精细几何边界；历史大数据 (HBD)（例如矢量数据）在深度学习中未得到充分利用；使用 DL 进行大规模遥感测绘 (LSRSM) 的研究很少见。针对以上问题，本文提出了一种面向对象（即基于多边形）和基于深度学习（OODLB）的图像分类方法，该方法由 HBD 辅助 LSRSM 用于长江水土流失监测（SEWL）。 River Basin 包括以下步骤： (1) 使用 HBD 和 OpenStreetMap 数据，地面物体被矢量化；(2)通过实地调查和数据扩充建立遥感解译重点数据库；（3）进行面向对象（即基于多边形）和基于Inception-ResNet-V2的LULC映射；(4)基于DL的分类结果通过人机相互验证更新。长江流域某县的实验结果显示出最先进的性能，整体准确率为 90.20%，而 eCognition 为 75.60%。它为OODLB大场景映射提供了一个优秀的框架。(4)基于DL的分类结果通过人机相互验证更新。长江流域一个县的实验结果显示出最先进的性能，整体准确率为 90.20%，而 eCognition 为 75.60%。它为OODLB大场景映射提供了一个优秀的框架。(4)基于DL的分类结果通过人机相互验证更新。长江流域某县的实验结果显示出最先进的性能，整体准确率为 90.20%，而 eCognition 为 75.60%。它为OODLB大场景映射提供了一个优秀的框架。