A Spatial-Temporal Attention-Based Method and a New Dataset for Remote Sensing Image Change Detection
Top Cited Papers
Open Access
- 22 May 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (10) , 1662
Abstract
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.Keywords
Funding Information
- the National Key R&D Programof China (2017YFC1405605)
- The Beijing Natural Science Foundation (4192034)
- Shanghai Association for Science and Technology (SAST2018096)
- National Natural Science Foundation of China (61671037)
This publication has 65 references indexed in Scilit:
- Spatiotemporal Group Context for Pedestrian CountingIEEE Transactions on Circuits and Systems for Video Technology, 2014
- Multi-Decadal Mangrove Forest Change Detection and Prediction in Honduras, Central America, with Landsat Imagery and a Markov Chain ModelRemote Sensing, 2013
- Change detection of buildings from satellite imagery and lidar dataInternational Journal of Remote Sensing, 2012
- PCA‐based land‐use change detection and analysis using multitemporal and multisensor satellite dataInternational Journal of Remote Sensing, 2008
- Multiple support vector machines for land cover change detection: An application for mapping urban extensionsISPRS Journal of Photogrammetry and Remote Sensing, 2006
- A change detection model based on neighborhood correlation image analysis and decision tree classificationRemote Sensing of Environment, 2005
- An image change detection algorithm based on Markov random field modelsIEEE Transactions on Geoscience and Remote Sensing, 2002
- Change vector analysis: A technique for the multispectral monitoring of land cover and conditionInternational Journal of Remote Sensing, 1998
- Review Article Digital change detection techniques using remotely-sensed dataInternational Journal of Remote Sensing, 1989
- A feature-integration theory of attentionCognitive Psychology, 1980