A Residual-Dyad Encoder Discriminator Network for Remote Sensing Image Matching


Numan Khurshid1
Mohbat1
Murtaza Taj1
Computer Vision and Graphics Lab1 Visual Computing Lab2
Department of Computer Science1
Lahore School of Management Sciences
Lahore, Pakistan
Faculty of Science2
University of Ontario Institute of Technology
2000 Simcoe St. N., Oshawa ON L1G 0C5

Abstract

We propose a new method for remote sensing image matching. The proposed method uses encoder subnetwork of an autoencoder pre-trained on GTCrossView data to construct image features. A discriminator network trained on University of California Merced Land Use/Land Cover dataset (LandUse) and High-resolution Satellite Scene dataset (SatScene) computes a match score between a pair of computed image features. We also propose a new network unit, called residual-dyad, and empirically demonstrate that networks that use residual-dyad units outperform those that do not. We compare our approach with both traditional and more recent learning-based schemes on LandUse and SatScene datasets, and the proposed method achieves state-of-the-art result in terms of mean average precision and ANMRR metrics. Specifically, our method achieves an overall improvement in performance of 11.26% and 22.41%, respectively, for LandUse and SatScene benchmark datasets.

Publication

For technical details please look at the following publications