eduzhai > Applied Sciences > Engineering >

End-to-End Change Detection for High Resolution Drone Images with GAN Architecture

  • Save

... pages left unread,continue reading

Document pages: 5 pages

Abstract: Monitoring large areas is presently feasible with high resolution dronecameras, as opposed to time-consuming and expensive ground surveys. In thiswork we reveal for the first time, the potential of using a state-of-the-artchange detection GAN based algorithm with high resolution drone images forinfrastructure inspection. We demonstrate this concept on solar panelinstallation. A deep learning, data-driven algorithm for identifying changesbased on a change detection deep learning algorithm was proposed. We use theConditional Adversarial Network approach to present a framework for changedetection in images. The proposed network architecture is based on pix2pix GANframework. Extensive experimental results have shown that our proposed approachoutperforms the other state-of-the-art change detection methods.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...