Next Article in Journal
Multi-Parametric Climatological Analysis Reveals the Involvement of Fluids in the Preparation Phase of the 2008 Ms 8.0 Wenchuan and 2013 Ms 7.0 Lushan Earthquakes
Previous Article in Journal
Characterization of Background Temperature Dynamics of a Multitemporal Satellite Scene through Data Assimilation for Wildfire Detection
Previous Article in Special Issue
SPMF-Net: Weakly Supervised Building Segmentation by Combining Superpixel Pooling and Multi-Scale Feature Fusion
Open AccessArticle

A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection

by Hao Chen 1,2,3 and Zhenwei Shi 1,2,3,*
1
Image Processing Center, School of Astronautics, Beihang University, Beijing 100191, China
2
Beijing Key Laboratory of Digital Media, Beihang University, Beijing 100191, China
3
State Key Laboratory of Virtual Reality Technology and Systems, School of Astronautics, Beihang University, Beijing 100191, China
*
Author to whom correspondence should be addressed.
Remote Sens. 2020, 12(10), 1662; https://doi.org/10.3390/rs12101662
Received: 24 April 2020 / Revised: 17 May 2020 / Accepted: 19 May 2020 / Published: 22 May 2020
Remote sensing image change detection (CD) is done to identify desired significant changes between bitemporal images. Given two co-registered images taken at different times, the illumination variations and misregistration errors overwhelm the real object changes. Exploring the relationships among different spatial–temporal pixels may improve the performances of CD methods. In our work, we propose a novel Siamese-based spatial–temporal attention neural network. In contrast to previous methods that separately encode the bitemporal images without referring to any useful spatial–temporal dependency, we design a CD self-attention mechanism to model the spatial–temporal relationships. We integrate a new CD self-attention module in the procedure of feature extraction. Our self-attention module calculates the attention weights between any two pixels at different times and positions and uses them to generate more discriminative features. Considering that the object may have different scales, we partition the image into multi-scale subregions and introduce the self-attention in each subregion. In this way, we could capture spatial–temporal dependencies at various scales, thereby generating better representations to accommodate objects of various sizes. We also introduce a CD dataset LEVIR-CD, which is two orders of magnitude larger than other public datasets of this field. LEVIR-CD consists of a large set of bitemporal Google Earth images, with 637 image pairs (1024 × 1024) and over 31 k independently labeled change instances. Our proposed attention module improves the F1-score of our baseline model from 83.9 to 87.3 with acceptable computational overhead. Experimental results on a public remote sensing image CD dataset show our method outperforms several other state-of-the-art methods. View Full-Text
Keywords: image change detection; attention mechanism; multi-scale; spatial–temporal dependency; image change detection dataset; fully convolutional networks (FCN) image change detection; attention mechanism; multi-scale; spatial–temporal dependency; image change detection dataset; fully convolutional networks (FCN)
Show Figures

Graphical abstract

MDPI and ACS Style

Chen, H.; Shi, Z. A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection. Remote Sens. 2020, 12, 1662.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop