Manipulation Detection in Satellite Images Using Vision Transformer

TL;DR

This paper introduces an unsupervised Vision Transformer-based method for detecting manipulated regions in satellite images, addressing the limitations of existing techniques designed for consumer camera images.

Contribution

It presents a novel unsupervised approach using Vision Transformers and a new dataset for improved manipulation detection in satellite imagery.

Findings

Outperforms existing unsupervised detection methods

Introduces a new dataset of manipulated satellite images

Demonstrates effectiveness of Vision Transformer in this domain

Abstract

A growing number of commercial satellite companies provide easily accessible satellite imagery. Overhead imagery is used by numerous industries including agriculture, forestry, natural disaster analysis, and meteorology. Satellite images, just as any other images, can be tampered with image manipulation tools. Manipulation detection methods created for images captured by "consumer cameras" tend to fail when used on satellite images due to the differences in image sensors, image acquisition, and processing. In this paper we propose an unsupervised technique that uses a Vision Transformer to detect spliced areas within satellite images. We introduce a new dataset which includes manipulated satellite images that contain spliced objects. We show that our proposed approach performs better than existing unsupervised splicing detection techniques.