News
Objects as Universal Geolocation Cues: A Computer Vision Approach
Congratulations to Kanwal Aftab and co-author Mark Scanlon on the publication of Objects as Universal Geolocation Cues: A Computer Vision Approach in 13th Annual Digital Forensics Research Workshop Europe (DFRWS EU 2026).
Co-authors: Mark Scanlon.
AI-generated summary of the contribution: The authors present a three-stage pipeline for indoor geolocation using electrical plug sockets as universal visual cues. The approach involves socket detection, socket type classification, and geolocation. The method is evaluated on a dataset of hotel images and achieves high accuracy in geolocation. The proposed approach has the potential to assist law enforcement in identifying potential trafficking hotspots and combating crimes such as human trafficking and child exploitation.