Privacy-Preserving Security Cameras based on Metalenses
The project aims to develop MetaCam, a privacy-preserving camera system using advanced metalenses for pose estimation without capturing identifiable details, targeting market readiness.
Projectdetails
Introduction
Surveillance cameras are widely used by governments, businesses, and ordinary citizens to monitor private and public areas to deter crime and identify offenders. As of 2021, it was estimated that there are over 1 billion surveillance cameras worldwide.
Privacy Concerns
However, there are great concerns that continuous monitoring severely restricts people's privacy and freedom of movement. There have been reports of abuse of surveillance footage, including by businesses and government institutions. Regulators, civil rights groups, and citizens are thus rightly concerned about infringements on freedoms of speech and association, especially in this era of AI when monitoring, tracking, and profiling techniques have been made easier, cheaper, and more accurate.
Project Objective
An initial step in video scene analysis is pose estimation, which enables monitoring the flux of people and detecting criminal actions or intent. Considering the privacy concerns of continuously recording citizens and automated image analysis, this project intends to develop a novel camera system that captures just enough detail required for pose estimation but excludes identifying information.
Limitations of Existing Methods
Existing software methods of deidentifying videos require a clear video to be taken first, and so do not entirely solve this problem. Proposed experimental hardware methods that avoid this issue using lenses have bulky optics and a limited set of parameters.
Implementation of MetaCam
With MetaCam, we will implement the optimized optical devices (metalenses) that allow ultimate control of all the light degrees of freedom. In this project, we will:
- Design and fabricate the metalenses.
- Build an optical table prototype of the camera to demonstrate its secure privacy-preserving performance.
Business Development
Supported by business developers, we will examine the business potential and map and engage the stakeholders later required to get from a proof-of-concept to a market-ready product.
Financiële details & Tijdlijn
Financiële details
Subsidiebedrag | € 150.000 |
Totale projectbegroting | € 150.000 |
Tijdlijn
Startdatum | 1-10-2023 |
Einddatum | 31-3-2025 |
Subsidiejaar | 2023 |
Partners & Locaties
Projectpartners
- FONDAZIONE ISTITUTO ITALIANO DI TECNOLOGIApenvoerder
Land(en)
Vergelijkbare projecten binnen European Research Council
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
A Robust, Real-time, and 3D Human Motion Capture System through Multi-Cameras and AIReal-Move aims to develop a marker-less, real-time 3D human motion tracking system using multi-camera views and AI to enhance workplace safety and ergonomics, reducing costs and improving quality of life. | ERC Proof of... | € 150.000 | 2024 | Details |
Enhancing Protections through the Collective Auditing of Algorithmic PersonalizationThe project aims to develop mathematical foundations for auditing algorithmic personalization systems while ensuring privacy, autonomy, and positive social impact. | ERC Consolid... | € 1.741.309 | 2024 | Details |
Facial Recognition Technologies. Etho-Assemblages and Alternative FuturesThe fAIces project explores the implications of facial recognition technologies by integrating diverse perspectives to expand ethics and foster public engagement and alternative futures. | ERC Advanced... | € 2.467.635 | 2025 | Details |
Dynamical Recurrent Visual PerceiverThe project aims to develop DRVis, an algorithm that enhances computer vision tasks using low-resolution frames from moving cameras, targeting applications in smart agriculture and drone navigation. | ERC Proof of... | € 150.000 | 2022 | Details |
A Robust, Real-time, and 3D Human Motion Capture System through Multi-Cameras and AI
Real-Move aims to develop a marker-less, real-time 3D human motion tracking system using multi-camera views and AI to enhance workplace safety and ergonomics, reducing costs and improving quality of life.
Enhancing Protections through the Collective Auditing of Algorithmic Personalization
The project aims to develop mathematical foundations for auditing algorithmic personalization systems while ensuring privacy, autonomy, and positive social impact.
Facial Recognition Technologies. Etho-Assemblages and Alternative Futures
The fAIces project explores the implications of facial recognition technologies by integrating diverse perspectives to expand ethics and foster public engagement and alternative futures.
Dynamical Recurrent Visual Perceiver
The project aims to develop DRVis, an algorithm that enhances computer vision tasks using low-resolution frames from moving cameras, targeting applications in smart agriculture and drone navigation.
Vergelijkbare projecten uit andere regelingen
Project | Regeling | Bedrag | Jaar | Actie |
---|---|---|---|---|
Onopvallend en onherkenbaar in beeldDit project onderzoekt de haalbaarheid van een anonimisatiecamera die privacy waarborgt zonder herkenbaarheid van personen. | Mkb-innovati... | € 20.000 | 2021 | Details |
TruProtectHet project ontwikkelt een innovatief 'privacy first' detectie- en alarmeringssysteem voor thuiszorg en beveiliging, dat gebruikmaakt van RF tomografie en AI om zorgkwaliteit en veiligheid te verbeteren. | Mkb-innovati... | € 195.090 | 2020 | Details |
CrimeSenseHet project onderzoekt de haalbaarheid van een automatisch geweldsdetectiesysteem voor bewakingscamera's op basis van virtual gaming data. | Mkb-innovati... | € 20.000 | 2022 | Details |
SparrowMapture.ai en BrainCreators ontwikkelen een privacyveilige drone-oplossing voor het automatisch surveilleren van grote gebieden, waarbij verdachte situaties geautomatiseerd worden herkend en gefilterd. | Mkb-innovati... | € 135.030 | 2022 | Details |
Multistage ruisreductie voor bewakingscamera’sV-Silicon onderzoekt de haalbaarheid van een multistage ruisreductieoplossing voor beveiligingscamera's, gericht op beeldverbetering in het donker. | Mkb-innovati... | € 20.000 | 2022 | Details |
Onopvallend en onherkenbaar in beeld
Dit project onderzoekt de haalbaarheid van een anonimisatiecamera die privacy waarborgt zonder herkenbaarheid van personen.
TruProtect
Het project ontwikkelt een innovatief 'privacy first' detectie- en alarmeringssysteem voor thuiszorg en beveiliging, dat gebruikmaakt van RF tomografie en AI om zorgkwaliteit en veiligheid te verbeteren.
CrimeSense
Het project onderzoekt de haalbaarheid van een automatisch geweldsdetectiesysteem voor bewakingscamera's op basis van virtual gaming data.
Sparrow
Mapture.ai en BrainCreators ontwikkelen een privacyveilige drone-oplossing voor het automatisch surveilleren van grote gebieden, waarbij verdachte situaties geautomatiseerd worden herkend en gefilterd.
Multistage ruisreductie voor bewakingscamera’s
V-Silicon onderzoekt de haalbaarheid van een multistage ruisreductieoplossing voor beveiligingscamera's, gericht op beeldverbetering in het donker.