Plug to Place: Indoor Multimedia Geolocation from Electrical Sockets for Digital Investigation
Kanwal Aftab, Graham Adams, Mark Scanlon
TL;DR
This paper proposes a three-stage indoor geolocation pipeline that uses electrical sockets as consistent visual markers to constrain location in forensics. It introduces two new CV datasets for socket detection and socket-type classification and validates the approach on the Hotels-50K TraffickCam dataset, demonstrating practical feasibility despite challenges like small socket size and variable lighting. The Stage One detector (best: YOLOv11s with augmentation and K-fold CV) localizes sockets; Stage Two (best: Xception with 5-fold CV) classifies 12 socket types; Stage Three maps socket types to countries, achieving up to 96.29% geolocation accuracy at high confidence on real-world data. The work highlights the potential of socket-based cues for scalable, context-aware forensic analysis and provides open-source resources to foster further research.
Abstract
Computer vision is a rapidly evolving field, giving rise to powerful new tools and techniques in digital forensic investigation, and shows great promise for novel digital forensic applications. One such application, indoor multimedia geolocation, has the potential to become a crucial aid for law enforcement in the fight against human trafficking, child exploitation, and other serious crimes. While outdoor multimedia geolocation has been widely explored, its indoor counterpart remains underdeveloped due to challenges such as similar room layouts, frequent renovations, visual ambiguity, indoor lighting variability, unreliable GPS signals, and limited datasets in sensitive domains. This paper introduces a pipeline that uses electric sockets as consistent indoor markers for geolocation, since plug socket types are standardised by country or region. The three-stage deep learning pipeline detects plug sockets (YOLOv11, mAP@0.5 = 0.843), classifies them into one of 12 plug socket types (Xception, accuracy = 0.912), and maps the detected socket types to countries (accuracy = 0.96 at >90% threshold confidence). To address data scarcity, two dedicated datasets were created: socket detection dataset of 2,328 annotated images expanded to 4,072 through augmentation, and a classification dataset of 3,187 images across 12 plug socket classes. The pipeline was evaluated on the Hotels-50K dataset, focusing on the TraffickCam subset of crowd-sourced hotel images, which capture real-world conditions such as poor lighting and amateur angles. This dataset provides a more realistic evaluation than using professional, well-lit, often wide-angle images from travel websites. This framework demonstrates a practical step toward real-world digital forensic applications. The code, trained models, and the data for this paper are available open source.