OSRM-CCTV: Open-source CCTV-aware routing and navigation system for privacy, anonymity and safety (Preprint)

Abstract

For the last several decades, the increased, widespread, unwarranted, and unaccountable use of Closed-Circuit TeleVision (CCTV) cameras globally has raised concerns about privacy risks. Additional recent features of many CCTV cameras, such as Internet of Things (IoT) connectivity and Artificial Intelligence (AI)-based facial recognition, only increase concerns among privacy advocates. Therefore, on par CCTVaware solutions must exist that provide privacy, safety, and cybersecurity features. We argue that an important step forward is to develop solutions addressing privacy concerns via routing and navigation systems (e.g., OpenStreetMap, Google Maps) that provide both privacy and safety options for areas where cameras are known to be present. However, at present no routing and navigation system, whether online or offline, provide corresponding CCTV-aware functionality.In this paper we introduce OSRM-CCTV -the first and only CCTV-aware routing and navigation system designed and built for privacy, anonymity and safety applications. We validate and demonstrate the effectiveness and usability of the system on a handful of synthetic and real-world examples. To help validate our work as well as to further encourage the development and wide adoption of the system, we release OSRM-CCTV as opensource.

CCTV-Exposure: System for Measuring User’s Privacy Exposure to CCTV Cameras

“…Subsequently, Lahtinen et al [12] applied and validated an early prototype of OSRM-CCTV to demonstrate the feasibility of OSRM-CCTV in real cities (e.g., Jyväskylä, Finland), and to study the impact of CCTV cameras on users' route planning when privacy or safety is a crucial factor. Our present work is different yet complementary to these studies [16,12].…”

“…The immediate city center area is relatively compact and rather CCTV congested. The camera mapping was conducted in the summer of 2020 [12,16], and the routes for this study were captured in early 2022.…”

“…Turtiainen et al [19] were the first to propose and develop a dedicated computer vision (CV) model -CCTVCV -designed specifically to detect CCTV cameras from street view and other images, with the primary intended purpose of building various privacy-enhancing technologies (PET), tools, and large-scale datasets (e.g., global mapping of CCTV cameras in public spaces). Building on the applicative ideas from Turtiainen et al [19], Sintonen et al [16] developed and proposed OSRM-CCTV, which is the first of its kind route planning and management. PET solution offers pro-active route planning optimized for individual privacy and public safety.…”

CCTV-FullyAware: toward end-to-end feasible privacy-enhancing and CCTV forensics applications

“…Inherently, the "privacy-first" and "safety-first" routing modes are just descriptive names, and we do not guarantee any actual privacy or safety. As detailed in OSRM-CCTV paper [87], we leave the large-scale quantitative and qualitative evaluation of both privacy-first and safety-first for immediate future work in a separate publication.…”

CCTVCV: Computer Vision model/dataset supporting CCTV forensics and privacy applications

“…Contributions. : In this paper, we develop a novel dataset with high practical applicability [12], [16], [17]. From a scientific method point of view, we use state-of-the-art CV methods and toolsets to build, train and evaluate our models.…”