Semantic Change Pattern Analysis

TL;DR

This paper introduces a new task called semantic change pattern analysis for aerial images, focusing on identifying both where and what changes occur using semantic information, supported by a new dataset and baseline experiments.

Contribution

It defines the semantic change pattern analysis task, provides a well-annotated dataset, and conducts baseline experiments to facilitate future research in high-level change detection.

Findings

First annotated dataset for semantic change analysis in aerial images

Baseline experiments establish reference performance levels

Framework for comprehensive change type analysis

Abstract

Change detection is an important problem in vision field, especially for aerial images. However, most works focus on traditional change detection, i.e., where changes happen, without considering the change type information, i.e., what changes happen. Although a few works have tried to apply semantic information to traditional change detection, they either only give the label of emerging objects without taking the change type into consideration, or set some kinds of change subjectively without specifying semantic information. To make use of semantic information and analyze change types comprehensively, we propose a new task called semantic change pattern analysis for aerial images. Given a pair of co-registered aerial images, the task requires a result including both where and what changes happen. We then describe the metric adopted for the task, which is clean and interpretable. We further provide the first well-annotated aerial image dataset for this task. Extensive baseline experiments are conducted as reference for following works. The aim of this work is to explore high-level information based on change detection and facilitate the development of this field with the publicly available dataset.