Final Oral Examination for Doctor of Philosophy (Computer Science)
Krishna Regmi
Wednesday, June 30, 2021
3:00PM – 5:00PM
Zoom Meeting
[Bifold] [Thesis] [Video]
Dissertation
We have developed deep neural network based architectures to generate cross-view images, e.g. aerial image corresponding to the ground-level scene, and also developed aĀ method to subsequently utilize the features of synthesized images to facilitate geolocalizationĀ task employing image-based matching. Such localization is useful inĀ vision based navigation in a GPS denied environment, e,g. a moving car can selflocalizeĀ itself in case of GPS failure. Similarly, given the aerial images of a particularĀ region in the world over time, we can analyze the changes (development or destruction)Ā the region undergoes and study its historical evolution. Additionally, the authenticity ofĀ the geo-tagged images/videos uploaded in the social media can be validated, which canĀ help purge the fake information from being circulated in the media.