Hi-UCD: A Large-scale Dataset for Urban Semantic Change Detection in Remote Sensing Imagery

TL;DR

The paper introduces Hi-UCD, a large-scale, high-resolution, semantically annotated dataset for urban change detection in remote sensing imagery, addressing key limitations of existing datasets.

Contribution

It provides a comprehensive, multi-temporal, high-resolution dataset with semantic labels, enabling more accurate and detailed urban change detection research.

Findings

Hi-UCD is challenging but useful for change detection tasks.

Benchmarking with classic methods demonstrates the dataset's effectiveness.

The dataset facilitates refined analysis of urban dynamics.

Abstract

With the acceleration of the urban expansion, urban change detection (UCD), as a significant and effective approach, can provide the change information with respect to geospatial objects for dynamical urban analysis. However, existing datasets suffer from three bottlenecks: (1) lack of high spatial resolution images; (2) lack of semantic annotation; (3) lack of long-range multi-temporal images. In this paper, we propose a large scale benchmark dataset, termed Hi-UCD. This dataset uses aerial images with a spatial resolution of 0.1 m provided by the Estonia Land Board, including three-time phases, and semantically annotated with nine classes of land cover to obtain the direction of ground objects change. It can be used for detecting and analyzing refined urban changes. We benchmark our dataset using some classic methods in binary and multi-class change detection. Experimental results show that Hi-UCD is challenging yet useful. We hope the Hi-UCD can become a strong benchmark accelerating future research.