MARVEL

Assets

MARVEL Assets

the main aspects of the list of MARVEL Assets

MARVEL is a comprehensive framework consisting of 35 innovative technologies designed to help cities become smarter, more sustainable, and more efficient. Our software/hardware developments, methodologies, and services provide tangible outcomes such as sensors and software solutions, help formalize user requirements into technological requirements, and aim to improve the effective use of MARVEL solutions.

Our technologies are designed to be validated in industrial-relevant smart city environments, such as in Malta, Trento, and Novi Sad. With a Technology Readiness Level (TRL) of 5-6 on average, you can be sure that MARVEL is the perfect solution to meet your smart city needs.

Contact us  today to learn more about our innovative solutions and start your smart city journey with MARVEL.

smartc4

MARVEL Assets: Advancing Smart Cities with extreme-Scale Analytics

Welcome to MARVEL, a comprehensive framework for extreme-scale multi-modal AI-based analytics in smart cities environments. Our innovative solutions provide real-time decision-making and improve overall efficiency for cities and communities. Our solutions go beyond traditional Big Data, cloud-only or edge-only architectures, adopting the edge-fog-cloud Computing Continuum paradigm.

Beyond Big Data: Multimodal Intelligence for Real-Time Decision-Making

Our vision is to create smarter, more sustainable and livable cities by utilizing the power of big data analytics. We provide privacy-aware multimodal AI tools and methods, multimodal audio-visual data capture and processing, and advanced visualization techniques. We utilize federated learning, edge and fog ML/DL models, and extreme-scale multimodal analytics to provide comprehensive data-driven application workflows.

smartc1
smartc5

Empowering Citizens for a Smarter Future

Our goal is to provide (almost) real-time response to incidents happening at different locations within the city, improving public safety, well-being, care, and transportation.  Our solutions have been developed according to the scope of MARVEL, a project classified as research and innovation. We prioritize the effective use of our solutions to provide in-depth customized assistance. We look forward to helping your city achieve its smart city goals. If you find one or more of our MARVEL Assets interesting, please contact us.

1

Software/Hardware Developments

Τhis category refers to tangible outcomes, namely sensors and software solutions.

2

Methodologies

Τhey help to formalise user requirements into technological requirements.

3

Services

The word “Service” refers to the traditional meaning of IT services. These are future services offered around MARVEL, which aim at improving the effective use of MARVEL solutions and at providing in-depth customised assistance.

Advanced MEMS microphones

Collect high-quality acoustic data for speech recognition, audio recording, and noise cancellation.

Audio Tagging

AT component in MARVEL implements a state-of-the-art method for audio tagging, which is used to analyze continuous audio streams and recognize active sound classes in the stream.

AVDrone

System that classifies crowd behavior while ensuring user privacy.

AVRegistry

Store and access metadata of MARVEL Audio-Visual sources using a RESTful API compliant with Smart Data Models standard.

sensMiner

SensMiner Android app records and annotates environmental acoustics.

EdgeSec-VPN

The EdgeSec VPN is a security and privacy solution that is part of the E2F2C framework developed in the MARVEL project. It uses peer-to-peer VPN technology to encrypt data transferred between MARVEL components, ensuring strict communication security.

EdgeSec-TEE

EdgeSec TEE ensures confidential computing for Python apps that process sensitive user data using Trusted Execution Environments.

VideoAnony

VideoAnony component detects faces and number plates, and performs anonymization to simplify surveillance camera data analysis in public spaces.

AudioAnony

AudioAnony component anonymizes audio streams by replacing speaker voices with preserved speech features and environmental background.

Data Fusion Bus

The Data Fusion Bus (DFB) allows efficient and trustworthy transfer of heterogeneous data between connected components and permanent storage.

StreamHandler

StreamHandler is a powerful distributed streaming platform based on Apache Kafka, designed for big data applications. It provides high performance, interoperability, resilience, scalability, and security.

DatAna

DatAna is a versatile platform that allows for scalable acquisition, transformation, and communication of streaming data across different layers of computing.

Hierarchical Data Distribution (HDD)

HDD (High-speed Distributed Data) is a software component that optimizes the topic partitioning process in Apache Kafka, a popular distributed streaming platform.

CATFlow

CATFLOW is a powerful tool for anonymizing road camera data and presenting it in a user-friendly dashboard.

devAIce

devAIce SDK is a powerful software development kit designed to help customers implement advanced audio analytics on their local premises.

Visual Anomaly Detection

Visual Anomaly Detection is an advanced tool that utilizes cutting-edge deep learning models to detect abnormal events in video streams with high accuracy.

SED@Edge

SED@Edge is an innovative solution that enables the detection of urban acoustic events using deep learning models on low-cost, low-power microcontrollers with limited computational capabilities.

Audio-Visual Anomaly Detection

Audio-Visual Anomaly Detection is a powerful component for detecting abnormal events in multimodal streams.

Visual Crowd Counting

The VCC uses computer vision and deep learning techniques to accurately count and classify vehicles passing through a given area.

Audio-Visual Crowd Counting

The AVCC (Audio-Visual Crowd Counting) component is a solution for counting the number of people in a crowd from audio-visual data.

Automated Audio Captioning

The MARVEL Dashboard provides an intuitive interface that allows users to visualize and interact with the data generated by audio captioning systems.

Sound Event Detection

SED component implements a state-of-the-art method for sound event detection.

Sound Event Localisation and Detection

SELD component is a state-of-the-art method for sound event localization and detection.

GPURegex

FORTH platform includes a real-time stream processing engine designed to handle large volumes of data in real-time.

DynHP

DynHP, short for Dynamic Headroom Management, is a software solution that optimizes the use of computing resources in edge devices that have limited capabilities.

Federated learning

Federated learning is a distributed machine learning approach that allows multiple clients to collaboratively train a shared model while keeping their data private.

MARVdash

MARVdash is a platform that provides a web-based environment for data science in Kubernetes-based environments.

HPC Infrastracture

High-performance computing resources can greatly enhance the speed and efficiency of AI-based algorithms, especially when dealing with large amounts of data.

Management and orchestration of HPC resources

PSNC's role as a technology partner in the MARVEL project includes providing technical support and tools for managing and orchestrating computing resources, including high-performance computing resources, as well as various storage services.

SmartViz

SmartViz is a data visualization solution that aims to help domain experts understand complex data sets.

MARVEL Data Corpus-as-a-Service

MARVEL Data Corpus has the potential to create significant impact on both SMEs and the international scientific and research community. By providing access to these data assets, SMEs and startups can test and build innovative applications, potentially creating new business opportunities.

SubSystem: Audio, Visual and Multimodal AI SubSystem

RBAD, a Python-based, logic-driven anomaly detector, uses predefined rules and data from CATFlow to alert on specific anomalies like jaywalking, off-schedule buses, rush-hour heavy vehicles, and pavement bikers.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

MARVEL Assets Demo Series - YOLO SED Demo

YOLO-SED component combines YOLO visual and SED audio analyses for anomaly detection in audiovisual data, enhancing accuracy and sending alerts via an MQTT broker.

SubSystem: Audio, Visual and Multimodal AI SubSystem

RBAD, a Python-based, logic-driven anomaly detector, uses predefined rules and data from CATFlow to alert on specific anomalies like jaywalking, off-schedule buses, rush-hour heavy vehicles, and pavement bikers.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

Advanced MEMS microphones

Collect high-quality acoustic data for speech recognition, audio recording, and noise cancellation.

AVDrone

System that classifies crowd behavior while ensuring user privacy.

AVRegistry

Store and access metadata of MARVEL Audio-Visual sources using a RESTful API compliant with Smart Data Models standard.

sensMiner

SensMiner Android app records and annotates environmental acoustics.

EdgeSec-VPN

The EdgeSec VPN is a security and privacy solution that is part of the E2F2C framework developed in the MARVEL project. It uses peer-to-peer VPN technology to encrypt data transferred between MARVEL components, ensuring strict communication security.

EdgeSec-TEE

EdgeSec TEE ensures confidential computing for Python apps that process sensitive user data using Trusted Execution Environments.

VideoAnony

VideoAnony component detects faces and number plates, and performs anonymization to simplify surveillance camera data analysis in public spaces.

AudioAnony

AudioAnony component anonymizes audio streams by replacing speaker voices with preserved speech features and environmental background.

Data Fusion Bus

The Data Fusion Bus (DFB) allows efficient and trustworthy transfer of heterogeneous data between connected components and permanent storage.

StreamHandler

StreamHandler is a powerful distributed streaming platform based on Apache Kafka, designed for big data applications. It provides high performance, interoperability, resilience, scalability, and security.

DatAna

DatAna is a versatile platform that allows for scalable acquisition, transformation, and communication of streaming data across different layers of computing.

CATFlow

CATFLOW is a powerful tool for anonymizing road camera data and presenting it in a user-friendly dashboard.

devAIce

devAIce SDK is a powerful software development kit designed to help customers implement advanced audio analytics on their local premises.

Visual Anomaly Detection

Visual Anomaly Detection is an advanced tool that utilizes cutting-edge deep learning models to detect abnormal events in video streams with high accuracy.

SED@Edge

SED@Edge is an innovative solution that enables the detection of urban acoustic events using deep learning models on low-cost, low-power microcontrollers with limited computational capabilities.

Audio-Visual Anomaly Detection

Audio-Visual Anomaly Detection is a powerful component for detecting abnormal events in multimodal streams.

Visual Crowd Counting

The VCC uses computer vision and deep learning techniques to accurately count and classify vehicles passing through a given area.

Audio-Visual Crowd Counting

The AVCC (Audio-Visual Crowd Counting) component is a solution for counting the number of people in a crowd from audio-visual data.

GPURegex

FORTH platform includes a real-time stream processing engine designed to handle large volumes of data in real-time.

SmartViz

SmartViz is a data visualization solution that aims to help domain experts understand complex data sets.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

SubSystem: Audio, Visual and Multimodal AI SubSystem

RBAD, a Python-based, logic-driven anomaly detector, uses predefined rules and data from CATFlow to alert on specific anomalies like jaywalking, off-schedule buses, rush-hour heavy vehicles, and pavement bikers.

MARVEL Assets Demo Series - YOLO SED Demo

YOLO-SED component combines YOLO visual and SED audio analyses for anomaly detection in audiovisual data, enhancing accuracy and sending alerts via an MQTT broker.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

AVRegistry

Store and access metadata of MARVEL Audio-Visual sources using a RESTful API compliant with Smart Data Models standard.

Data Fusion Bus

The Data Fusion Bus (DFB) allows efficient and trustworthy transfer of heterogeneous data between connected components and permanent storage.

StreamHandler

StreamHandler is a powerful distributed streaming platform based on Apache Kafka, designed for big data applications. It provides high performance, interoperability, resilience, scalability, and security.

Automated Audio Captioning

The MARVEL Dashboard provides an intuitive interface that allows users to visualize and interact with the data generated by audio captioning systems.

Sound Event Detection

SED component implements a state-of-the-art method for sound event detection.

Sound Event Localisation and Detection

SELD component is a state-of-the-art method for sound event localization and detection.

Federated learning

Federated learning is a distributed machine learning approach that allows multiple clients to collaboratively train a shared model while keeping their data private.

MARVdash

MARVdash is a platform that provides a web-based environment for data science in Kubernetes-based environments.

HPC Infrastracture

High-performance computing resources can greatly enhance the speed and efficiency of AI-based algorithms, especially when dealing with large amounts of data.

Management and orchestration of HPC resources

PSNC's role as a technology partner in the MARVEL project includes providing technical support and tools for managing and orchestrating computing resources, including high-performance computing resources, as well as various storage services.

MARVEL Data Corpus-as-a-Service

MARVEL Data Corpus has the potential to create significant impact on both SMEs and the international scientific and research community. By providing access to these data assets, SMEs and startups can test and build innovative applications, potentially creating new business opportunities.

Audio Tagging

AT component in MARVEL implements a state-of-the-art method for audio tagging, which is used to analyze continuous audio streams and recognize active sound classes in the stream.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

Hierarchical Data Distribution (HDD)

HDD (High-speed Distributed Data) is a software component that optimizes the topic partitioning process in Apache Kafka, a popular distributed streaming platform.

Visual Anomaly Detection

Visual Anomaly Detection is an advanced tool that utilizes cutting-edge deep learning models to detect abnormal events in video streams with high accuracy.

Audio-Visual Anomaly Detection

Audio-Visual Anomaly Detection is a powerful component for detecting abnormal events in multimodal streams.

Visual Crowd Counting

The VCC uses computer vision and deep learning techniques to accurately count and classify vehicles passing through a given area.

Audio-Visual Crowd Counting

The AVCC (Audio-Visual Crowd Counting) component is a solution for counting the number of people in a crowd from audio-visual data.

DynHP

DynHP, short for Dynamic Headroom Management, is a software solution that optimizes the use of computing resources in edge devices that have limited capabilities.

MARVEL Assets Demo Series - YOLO SED Demo

YOLO-SED component combines YOLO visual and SED audio analyses for anomaly detection in audiovisual data, enhancing accuracy and sending alerts via an MQTT broker.

SubSystem: Audio, Visual and Multimodal AI SubSystem

RBAD, a Python-based, logic-driven anomaly detector, uses predefined rules and data from CATFlow to alert on specific anomalies like jaywalking, off-schedule buses, rush-hour heavy vehicles, and pavement bikers.

Data Management Platform (DMP)

The Data Management Platform is a holistic solution for real-time analytics, with DatAna, DFB, StreamHandler, and HDD components for data processing and optimization.

IPR Management

There are 32 assets owned by various owners. In addition, although it is still early, as some partners have not yet decided under which type of license, they want to market their results, there is a perceived mix of Open Source licenses, but also Proprietary licenses, so a 100% Open Source approach will not be possible. In the future, the asset owners will consider the possibility of releasing parts of the developed technologies under MARVEL as Open Source approach. The Open Source licenses provided up to now, as MIT or Apache 2.0 do not present incompatibilities among them.

Experience the Future of Smart Cities Now! Join MARVEL!

Contact Us Today to Start Your Smart City Journey, request a Demo !

Key Facts

  • Project Coordinator: Dr. Sotiris Ioannidis
  • Institution: Foundation for Research and Technology Hellas (FORTH)
  • E-mail: marvel-info{at}marvel-project.eu 
  • Start: 01.01.2021
  • Duration: 36 months
  • Participating Organisations: 17
  • Number of countries: 12

Get Connected

Funding

eu FLAG

This project has received funding from the European Union’s Horizon 2020 Research and Innovation program under grant agreement No 957337. The website reflects only the view of the author(s) and the Commission is not responsible for any use that may be made of the information it contains.