Article
Plug to place: Indoor multimedia geolocation from electrical sockets for digital investigation
Contribution Summary
This paper introduces a pipeline that uses electrical sockets as consistent indoor markers for geolocation, addressing the challenges of similar room layouts, frequent renovations, visual ambiguity, and limited datasets in sensitive domains. The three-stage deep learning pipeline detects plug sockets, classifies them into one of 12 plug socket types, and maps the detected socket types to countries. The approach is evaluated on the Hotels-50K dataset, focusing on the TraffickCam subset of crowd-sourced hotel images, and demonstrates its practical utility for law enforcement in human trafficking investigations. The paper also presents two dedicated datasets: a 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 code, trained models, and data for this paper are available open source.
Keywords: Indoor multimedia geolocation; Electrical sockets; Deep learning pipeline; Hotel recognition; Human trafficking investigations; Digital forensics; Computer vision; Plug socket classification
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 electrical 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 2328 annotated images expanded to 4074 through augmentation, and a classification dataset of 3187 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.
BibTeX
@article{AFTAB2026302056,
title = {Plug to place: Indoor multimedia geolocation from electrical sockets for digital investigation},
journal = {Forensic Science International: Digital Investigation},
volume = {56},
pages = {302056},
year = {2026},
note = {DFRWS EU 2026 - Selected Papers from the 13th Annual Digital Forensics Research Conference Europe},
issn = {2666-2817},
doi = {https://doi.org/10.1016/j.fsidi.2026.302056},
url = {https://www.sciencedirect.com/science/article/pii/S2666281726000132},
author = {Kanwal Aftab and Graham Adams and Mark Scanlon},
keywords = {Multimedia Geolocation, Computer Vision, Hotels-50K, Indoor, Multimedia forensics, Human trafficking},
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 electrical 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 2328 annotated images expanded to 4074 through augmentation, and a classification dataset of 3187 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.}
}