Developing augmented reality tools to tackle crime and terrorism

Facebook

Twitter

Youtube

About

DARLENE (DEEP AR LAW ENFORCEMENT ECOSYSTEM) is an EU-funded H2020 project aiming to apply cutting-edge augmented reality (AR) technology to help law enforcement agencies (LEAs) and first responders make more informed and rapid decisions when tackling crime and terrorism.

Currently, in its third year, the project partners are developing innovative augmented reality (AR) tools to improve situational awareness of police officers responding to criminal and terrorist activities. Combining innovative AR smart glass technology and powerful computer vision algorithms with 5G network architectures, DARLENE aims for agile processing of real-time data by law enforcement agencies in high-pressure situations. The project will also carry out two pilot use-cases to demonstrate the various capabilities of all its solutions.

The DARLENE project is coordinated by the Centre for Research & Technology, Hellas (CERTH), and Foundation for Research and Technology Hellas (FORTH) as technical manager, joined by twelve partners from ten European countries.

Learn more about the DARLENE Project here.

The DARLENE Project - watch our new video!

DARLENE Project Video

The DARLENE project is focused on security applications where it is vital to detect illegal activities, suspicious, or harmful objects (e.g., weapons). The main aim is to make LEAs and first responders’ job easier and safer when acting under stressful and threatening situations. DARLENE also investigates how police officers can stay ahead of terrorists and take initiative before terrorists execute their plans, as well as how police officers can make quick decisions in high-pressure situations to protect civilians from terrorist activities.

Find out more in our new DARLENE project video on our website or our brand new YouTube channel!

Meetings

6th DARLENE Plenary Meeting in Larnaca, Cyprus

A plenary meeting was held between December 07-08, 2022. The meeting was hosted by our project partner CP at the Larnaca International Airport in Cyprus. The project partners presented the progress made in each Work Package. Moreover, a constructive discussion between the consortium partners took place, which set the foundation for the actions to be taken in the final phase of the project.

During the meeting, the participants, including our LEA partners, had the opportunity to test the DARLENE prototype and provide their feedback. Finally, during the second day, the consortium visited the facilities of the airport that will be utilised for the pilot activities envisaged under Use Case #1.

5th DARLENE Stakeholder Advisory Board Meeting

On 1 March 2023, DARLENE project partner, Trilateral Research, organised and hosted a Stakeholder Board meeting to present the latest news and updates about DARLENE and to provide opportunities for stakeholder feedback to ensure the sharing of knowledge and expertise among professionals.

The main objective of the Workshop was to inform the SB about the backend of the DARLENE technology in use throughout the project, as well as the ethical and legal aspects thereof.

The topics presented and the discussions which took place were:

· The backend of the DARLENE technology: 5G

· The backend of the DARLENE technology: Authentication and cybersecurity

· Ethical and legal aspects of 5G, authentication and cybersecurity in DARLENE

· Q&A Session

Publications

We have some very interesting publications in the works that have been accepted to the PErvasive Technologies Related to Assistive Environments (PETRA) conference 2023!

The PETRA conference is an interdisciplinary conference that focuses on computational and engineering approaches to improve the quality of life and enhance human performance in a wide range of settings, in the workplace, at home, in public spaces, urban environments, etc. PETRA (which means “stone” in Greek) addresses important human living needs. From a technological perspective, PETRA motivates and inspires new scientific innovations and discoveries to improve living environments; a particularly important issue, in an increasingly crowded and complex world where the need for inclusiveness and connectivity with the rest of the world is key.

The two publications that have been accepted for the conference, and will be published after the conference in July 2023, are:

- Real-Time Activity Recognition for Surveillance Applications on Edge Devices
Authors: Vasileios Tsinikos, Ioannis Pastaltzidis, Iason Karakostas, Nikolaos Dimitriou, Katerina Valakou, George Margetis, Constantine Stefanidis, and Dimitrios Tzovaras
- The DARLENE XR platform for intelligent surveillance applications Authors: Christos Ntoumanopoulos, Efstathia Martinopoulou, Iason Karakostas, Nikolaos Dimitriou, and Dimitrios Tzovaras

Real-Time Adaptation of Context-Aware Intelligent User Interfaces, for Enhanced Situational Awareness

In this work, a novel computational approach for the dynamic adaptation of User Interfaces (UIs) is proposed, which aims at enhancing the Situational Awareness (SA) of users by leveraging the current context and providing the most useful information, in an optimal and efficient manner. By combining Ontology modelling and reasoning with Combinatorial Optimization, the system decides what information to present, when to present it, where to visualize it in the display - and how, taking into consideration contextual factors as well as placement constraints. The main objective of the proposed approach is to optimize the SA associated with the displayed UI at run-time, while avoiding information overload and induced stress. In the context of this work, we have deployed our computational approach to the use case of an AR system for LEAs. To explore the benefits and limitations of the developed system, two evaluations have been conducted. The first one was an expert-based evaluation with LEAs and User Experience (UX) experts, assessing the appropriateness of the system’s decisions. The second one was a user-based evaluation involving LEAs from different agencies, estimating the SA, the mental workload and the overall UX associated with the system, through an AR simulation. The results indicate that the system enhances SA, and while not imposing workload, it provides an overall positive UX.

Read the full paper here.

Data augmentation for fairness-aware machine learning: Preventing algorithmic bias in law enforcement systems

Researchers and practitioners in the fairness community have highlighted the ethical and legal challenges of using biased datasets in data-driven systems, with algorithmic bias being a major concern. Despite the rapidly growing body of literature on fairness in algorithmic decision-making, there remains a paucity of fairness scholarship on machine learning algorithms for the real-time detection of crime. This contribution presents an approach for fairness-aware machine learning to mitigate the algorithmic bias/discrimination issues posed by the reliance on biased data when building law enforcement technology. DARLENE analysis is based on RWF-2000, which has served as the basis for violent activity recognition tasks in data-driven law enforcement projects. Hence, the project reveals issues of overrepresentation of minority subjects in violence situations that limit the external validity of the dataset for real-time crime detection systems and propose data augmentation techniques to rebalance the dataset. The experiments on real world data show the potential to create more balanced datasets by synthetically generated samples, thus mitigating bias and discrimination concerns in law enforcement applications.

Read the full paper here.

Conferences

DARLENE was presented at the European Union Agency for Law Enforcement Training (CEPOL) Research & Science Conference

CEPOL is an agency of the European Union dedicated to developing, implementing and coordinating training for law enforcement officials. Mr. Iulian Coman (Training Officer at CEPOL) moderated the panel session of CEPOL Research & Science Conference in Vilnius on 7 April 2022, for the two speakers from Valencia Local Police, Jose Luis Diego and Rubén Fernández.

The speakers’ presentations covered 4 ongoing projects Respond A Project, CC-DRIVER Project, RAYUELA_H2020 and DARLENE - Deep AR Law Enforcement Ecosystem

You can read more about them on the conference page here

DARLENE at the EAB Research Projects Conference 2022

Nikolaos Dimitriou, the coordinator of DARLENE, attended the European Association on Biometrics (EAB) Research Projects Conference 2022, which was held at the premises of Fraunhofer IGD in Germany, on September 12-14, 2022. Dr. Dimitriou had the opportunity to provide an overview of the DARLENE solution during the session titled "DARLENE - The DARLENE AR Helmet Prototype for Improved Situational Awareness".

Learn more about the conference here.

DARLENE at the IOT Solutions World Congress

On the 2nd of February 2023, the project partner CTTC presented the DARLENE project to the IOT Solutions World Congress. This is a technological event cantered around Internet of Things and digital transformation (IoT). CTTC presented the project's results, focusing on “5G Technology for Augmented Reality”.

Learn more about the conference here.

DARLENE at the Mobile World Congress (MWC)

The DARLENE project was represented by CTTC at the Mobile World Congress (MWC) in Barcelona, Spain, between February 27th to March 2nd 2023. The project combines innovative 5G, AR, MEC and AI tools that aim to improve SA when responding to criminal and terrorist activities. CTTC provides 5G technology to support AR and MEC. The DARLENE technology was demonstrated in two representative use cases in real pilot sites:

· Use case 1: “Rapid visual scene analysis to identify suspicious/dangerous objects and injured people”.

· Use case 2: “Tactical neutralization of human adversaries in the presence of friendlies”.

Learn more about the conference here.

News

DARLENE featured in Critical Communications Today

Prominent online magazine Critical Communications Today, featured the DARLENE project through an in-depth interview with project coordinator Dr. Nikolaos Dimitriou of CERTH.

The interview covered the latest applications of AR and VR in law enforcement, and how they will be used in the project’s use cases to show their maximum potential in fighting crime and security.

Check out the full article here.

DARLENE at the European Police Congress

Save the date! Between the 3rd and the 4th of May 2023, DARLENE will attend the European Police Congress in Berlin (Germany), with a dedicated exhibition space.

The European Police Congress is an international congress for decision makers from police forces and security authorities and industries. Its intention is to strengthen the dialogue between the authorities and enable the participants to establish new contacts to colleagues from all over Europe. Every year critical discussions on up-to-date issues are held and the latest developments in technologies for the professional use in the security sector are presented by the exhibitors. The European Police Congress is the largest conference for internal security in the European Union. Annually the conference is a meeting place for experts from more than 20 countries. Representatives of polices, border polices, secret services as well as governments, parliaments and industries participate in the conference.