Unsupervised change detection using Spatial Transformer Networks

Change detection in images or video sequences is used to detect anomalies or important variations in the scene. Although much research has focused on change detection in surveillance videos, there is little work related to change detection on aerial or satellite imagery. This paper presents a deep learning approach for change detection in satellite images. The proposed approach utilizes Spatial Transformer Networks (STNs) which learn to perform a coordinate transformation to localize potential change regions. With unsupervised training the STN system examines differences between images for significant change activity. Our initial results illustrate the merit of this method.

[1]  Yun Zhang,et al.  CHANGE DETECTION FOR AERIAL PHOTO DATABASE UPDATE , 2008 .

[2]  Maoguo Gong,et al.  Change Detection in Synthetic Aperture Radar Images Based on Deep Neural Networks , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Hélène Laurent,et al.  Comparative study of background subtraction algorithms , 2010, J. Electronic Imaging.

[4]  Chris Clifton.  Change Detection in Overhead Imagery Using Neural Networks , 2004, Applied Intelligence.

[5]  Ole Winther,et al.  Recurrent Spatial Transformer Networks , 2015, ArXiv.

[6]  K. E. Price,et al.  Change detection and analysis in multi-spectral images , 1977 .

[7]  Mark J. Carlotto,et al.  A Signal-Symbol Approach to Change Detection , 1986, AAAI.

[8]  Michael Nowak,et al.  Layered Sensing: Its Definition, Attributes, and Guiding Principles for AFRL Strategic Technology Development , 2008 .

[9]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[10]  Ariel Schlamm,et al.  Change detection using mean-shift and outlier-distance metrics , 2011, Defense + Commercial Sensing.

[11]  Ashish Ghosh,et al.  A Neural Approach to Unsupervised Change Detection of Remote-Sensing Images , 2008, Speech, Audio, Image and Biomedical Signal Processing using Neural Networks.

[12]  Kevin L. Priddy,et al.  Automated recognition challenges for wide-area motion imagery , 2012, Defense + Commercial Sensing.

[13]  Adam A. Goodenough,et al.  DIRSIG 5: core design and implementation , 2012, Defense + Commercial Sensing.

[14]  Hichem Sahbi,et al.  Constrained optical flow for aerial image change detection , 2011, 2011 IEEE International Geoscience and Remote Sensing Symposium.

[15]  David W. Messinger,et al.  Graph theoretic metrics for spectral imagery with application to change detection , 2011, Defense + Commercial Sensing.

[16]  Raj Reddy,et al.  Change Detection and Analysis in Multispectral Images , 1977, IJCAI.

[17]  Erik Blasch,et al.  Vehicle change detection from aerial imagery using detection response maps , 2014, Defense + Security Symposium.