S2Looking: A Satellite Side-Looking Dataset for Building Change Detection

07/20/2021
by   Li Shen, et al.
4

Collecting large-scale annotated satellite imagery datasets is essential for deep-learning-based global building change surveillance. In particular, the scroll imaging mode of optical satellites enables larger observation ranges and shorter revisit periods, facilitating efficient global surveillance. However, the images in recent satellite change detection datasets are mainly captured at near-nadir viewing angles. In this paper, we introduce S2Looking, a building change detection dataset that contains large-scale side-looking satellite images captured at varying off-nadir angles. Our S2Looking dataset consists of 5000 registered bitemporal image pairs (size of 1024*1024, 0.5   0.8 m/pixel) of rural areas throughout the world and more than 65,920 annotated change instances. We provide two label maps to separately indicate the newly built and demolished building regions for each sample in the dataset. We establish a benchmark task based on this dataset, i.e., identifying the pixel-level building changes in the bi-temporal images. We test several state-of-the-art methods on both the S2Looking dataset and the (near-nadir) LEVIR-CD+ dataset. The experimental results show that recent change detection methods exhibit much poorer performance on the S2Looking than on LEVIR-CD+. The proposed S2Looking dataset presents three main challenges: 1) large viewing angle changes, 2) large illumination variances and 3) various complex scene characteristics encountered in rural areas. Our proposed dataset may promote the development of algorithms for satellite image change detection and registration under conditions of large off-nadir angles. The dataset is available at https://github.com/AnonymousForACMMM/.

READ FULL TEXT

page 2

page 4

page 6

page 8

research
09/08/2021

Improving Building Segmentation for Off-Nadir Satellite Imagery

Automatic building segmentation is an important task for satellite image...
research
01/09/2021

Active Fire Detection in Landsat-8 Imagery: a Large-Scale Dataset and a Deep-Learning Study

Active fire detection in satellite imagery is of critical importance to ...
research
10/08/2022

Spatial predictions on physically constrained domains: Applications to Arctic sea salinity data

In this paper, we predict sea surface salinity (SSS) in the Arctic Ocean...
research
02/28/2023

FPCD: An Open Aerial VHR Dataset for Farm Pond Change Detection

Change detection for aerial imagery involves locating and identifying ch...
research
01/20/2021

Self-supervised pre-training enhances change detection in Sentinel-2 imagery

While annotated images for change detection using satellite imagery are ...
research
03/21/2023

Focus or Not: A Baseline for Anomaly Event Detection On the Open Public Places with Satellite Images

In recent years, monitoring the world wide area with satellite images ha...
research
04/14/2022

Deep Vehicle Detection in Satellite Video

This work presents a deep learning approach for vehicle detection in sat...

Please sign up or login with your details

Forgot password? Click here to reset