Ekinnox is a Inria start-up to improve the rehabilitation process for caregivers and patients. Thanks to a computer vision based system (camera combined with algorithms detecting human motion), Ekinnox provides a simple and efficient tool to quantify and visualize the performance of patients (e.g. gait parameters computation such as side-byside video comparison, automatic sequencing of video or 3D display) during their rehabilitation process. In order to secure the integration in the everyday habits of caregivers, we are actually developing our system in collaboration with the Helio-Marin Center in Vallauris. A video of demonstration of the prototype used in this rehabilitation center is shown in the web-site.
For more information, see the Ekinnox (ex-Bomotech) site and video1 & video2.
The ACTIVIS project is an ANR project (CES19: Technologies pour la santé) started in January 2020 and will end in December 2023 (48 months). This project is based on an objective quantification of the atypical behaviors on which the diagnosis of autism is based, with medical (diagnostic assistance and evaluation of therapeutic programs) and computer scientific (by allowing a more objective description of atypical behaviors in autism) objectives. This quantification requires video analysis of the behavior of people with autism. In particular, we propose to explore the issues related to the analysis of ocular movement, gestures and posture to characterize the behavior of a child with autism.
The partners are Aix-Marseille Université - LIS, Hôpitaux Pédiatriques Nice CHU-Lenval - CoBTeK, Nively and Inria. INRIA Grant is 205 Keuros out of 784 Keuros.
Solitaria is a UCA project, which performs a multi-sensor activity analysis for monitoring and safety of older and isolated people. With the increase of the ageing population in Europe and in the rest of the world, keeping elderly people at home, in their usual environment, as long as possible, becomes a priority and a challenge of modern society. A system for monitoring activities and alerting in case of danger, in permanent connection with a device (an application on a phone, a surveillance system ...) to warn relatives (family, neighbours, friends ...) of isolated people still living in their natural environment could save lives and avoid incidents that cause or worsen the loss of autonomy. In this R\&D project, we propose to study a solution allowing the use of a set of innovative heterogeneous sensors in order to: 1) detect emergencies (falls, crises, etc.) and call relatives (neighbours, family, etc.); 2) detect, over short or longer predefined periods, behavioural changes in the elderly through an intelligent analysis of data from sensors.
Fantastic Sourcing is collaborating with Stars through the UCA Solitaria project, by providing their Nodeus system. Nodeus is a IoT (Internet of Things) system for home support for the elderly, which consists of a set of small sensors (without video cameras) to collect precious data on the habits of isolated people. Fantastic Sourcing is a French SME specialized in micro-electronics, it develops e-health technologies.
Nively is collaborating with Stars through the UCA Solitaria project, by providing their MentorAge system. This software allows the monitoring of elderly people in nursing homes in order to detect all the abnormal events in the lives of residents (falls, runaways, strolls, etc.). Nively's technology is based on RGBD video sensors (Kinects type) and a software platform for event detection and data visualization. Nively is a French SME specialized in e-health technologies, it develops position and activity monitoring of activities of daily living platforms based on video technology. Nively's mission is to use technological tools to put people back at the center of their interests, with their emotions, identity and behavior.
The company ESI (European System Integration) has a collaboration with Stars, which runs from September 2018 until March 2022 to develop a novel Re-Identification algorithm which can be easily set-up with low interaction for video-surveillance applications. ESI provides software solutions for remote monitoring stations, remote assistance, video surveillance, and call centers. It was created in 1999 and ESI is a leader in the French remote monitoring market. Nowadays, ensuring the safety of goods and people is a major problem. For this reason, surveillance technologies are attracting growing interest and their objectives are constantly evolving: it is now a question of automating surveillance systems and helping video surveillance operators in order to limit interventions and staff. One of the current difficulties is the human processing of video, as the multiplication of video streams makes it difficult to understand meaningful events. It is therefore necessary to give video surveillance operators suitable tools to assist them with tasks that can be automated. The integration of video analytics modules will allow surveillance technologies to gain in efficiency and precision. In recent times, deep learning techniques have been made possible by the advent of GPU processors, which offer significant processing possibilities. This leads to the development of new automatic video processing algorithms.
Kontron has a collaboration with Stars, which runs from April 2018 until April 2021 to embed CNN based people tracker within a video-camera. Their system uses Intel VPU modules, such as Myriad X (MA2485), based on OpenVino library.
Vedecom is interested in developing algorithms for people detection for self-driving cars. Among many challenges in pedestrian detection, the ones of interest are a) Scale- handling, b) Occlusion-handling and c) Cross-dataset generalization. Each of the aforementioned challenges is critical to enable modern applications like self-driving vehicles become safe enough for active deployment. To improve the performance of contemporary pedestrian detectors, one of our first major idea is to use multiple layers of a CNN simultaneously. Towards this, we proposed a new pedestrian detection system called Multiple-RPN. Another work is adding pseudo-segmentation information to pedestrian detection. The proposed features of our system perform close to the best performing detectors today.
The ReMinAry is a FUI project started in September 2016 and will end in September 2019 (36 months + 18 month extension). This project is based on the use of motor imagery (MI), a cognitive process consisting of the mental representation of an action without concomitant movement production. This technique consists in imagining a movement without realizing it, which entails an activation of the brain circuits identical to those activated during the real movement. By starting rehabilitation before the end of immobilization, a patient operated on after a trauma will gain rehabilitation time and function after immobilization is over. The project therefore consists in designing therapeutic video games to encourage the patient to re-educate in a playful, autonomous and active way in a phase where the patient is usually passive. The objective will be to measure the usability and the efficiency of the reeducative approach, through clinical trials centered on two pathologies with immobilization: post-traumatic (surgery of the shoulder) and neurodegenerative (amyotrophic lateral sclerosis).
The partners are GENIOUS Systèmes, MENSIA technologies - MindMaze France, Institut du Cerveau et de la Moelle épinière, la Pitié-Salpêtrière hospital and Inria. INRIA Grant is 197 Keuros.
For more information, see the ReMiNary Project Web-Page and dissemination in French student Journal Sciences et Avenir.
We are involved in the EIT Health, from January 2019 to June 2020 with IA, Uni. Maastricht, DFKI, Inria, Janssen and ki Elements. The goal is to develop and market a AI-empowered speech analysis system for neurological/psychological screening tool. DeepSpa will deliver a telecommunication-based neurocognitive assessment tool for patient monitoring in clinical trials addressing neurodegenerative diseases, in particular Alzheimer's disease, but also neuropsychiatric symptoms like depression. Built on existing speech technologies, this first-of-its-kind service will allow to remotely conduct neurocognitive tests. Enabling fast, automated, remote assessment of cognitive/emotional states; multiple European languages will be catered for.
INRIA Grant is 285 Keuros out of 732 Keuros.
For more information, see the EIT Health website.
We are involved in the EIT ICT Labs - Well Being, from January 2016 to December 2018 with IA, CoBTeK, DFKI, Inria, UoE and ki Elements. The goal is to develop and market a AI-empowered speech analysis system for neurological/psychological diagnosis support. he goal of this activity has been directed towards automated screening for cognitive decline in non-clinical settings, resulting in faster, earlier diagnosis and intervention. Inria in collaboration with the association Innovation Alzheimer (IA) created the French speech corpus allowing automatic detection of dementia on the basis of speech analysis. The employed speech analysis has been augmented by the means of facial expression recognition.
In 2017, target use case scenario and user requirements were defined. ki elements UG (haftungs-beschraenkt) was established on March 15th, 2017, with the purpose of commercializing the technologies matured and integrated within the ELEMENT project. Significant efforts have been invested in the preparation of the first public demonstration of the product’s prototype Delta. In collaboration with DFKI, several research papers were published on the audio data collected in Nice.
For more information, see the Delta site and the flyer.
StoreConnect is a FUI project started in Sept 2016 and that will end in Sept 2018 (24 months). The goal is to improve the shopping experience for customers inside supermarkets by adding new sensors such as cameras, beacons and RFID. By gathering data from all the sensors and combining them, it is possible to improve the way to communicate between stores and customers in a personalized way. StoreConnect acts as a middleware platform between the sensors and the stores to process the data and extract interesting knowledge (meta-data) organized via onthologies.
The partners are Ubudu, Tevolys, Smile, STIME and Inria.
NeoSensys is a spin off of the Stars team which aims at commercializing video surveillance solutions for the retail domain (supermarket, hypermarket, DIY stores ...). This SAS company has been created in September 2014. Neosensys was created from the encounter between people coming from the world of retail, who perfectly master customer needs; and the research team Stars, whose one of the main activities is video-surveillance and works on the latest scientific advances of the domain. Neosensys aims at entering into the retail CCTV market using traditional solutions to retain customers based on high-quality customer service. Simultaneously, Neosensys works on innovative solutions that will be, in a second time, offered to customers. The purpose of these solutions is to improve store financial performance by (i) reducing their costs and (ii) by increasing their sales based on better understanding of consumer behaviours.
For more information, see the Neosensys Web-Page on Business Intelligence.
This European Network on Integrating Vision and Language (iV&L Net): Combining Computer Vision and Language Processing For Advanced Search, Retrieval, Annotation and Description of Visual Data, COST Action IC1307, is designed to bring together two previously unconnected research communities, Computer Vision (CV) and Natural Language Processing (NLP). It is set up to allow researchers to meet, exchange ideas, expertise and technology, and form new partnerships. Building on the successful EPSRC Network on Vision and Language (V&L Net), the aim of the COST Action is to create a lasting interdisciplinary research community situated at the nexus between language processing and computer vision. This is hugely important because of the explosive growth of visual and textual data (both on the World Wide Web and held in private repositories by diverse institutions and companies).
The central goal of iV&L Net is to build a European CV/NLP research community, targeting 4 focus themes: (i) Integrated Modelling of Vision and Language for CV and NLP Tasks; (ii) Applications of Integrated Models; (iii) Automatic Generation of Image & Video Descriptions; and (iv) Semantic Image & Video Search. iV&L Net will organise annual conferences, technical meetings, partner visits, data/task benchmarking, and industry/end-user liaison. The 1st MC meeting was on the 26 March 2014 and the action will end on March 2018.
For more information, see the iV&L Net Web-Page and also the COST Site.
Goal of this European Network on Video Analytics: Recent years have seen a growth in the use of video surveillance technologies as part of the package of protective security measures used to protect critical infrastructures and other valuable assets. Academia and industry have been investing time and money in relevant technology innovations, but there is a lack of standardisation, testing and accreditation in Europe that would help users to ensure that video surveillance products are fit for their purposes. This ERNCIP Thematic Group will endeavour to identify the activities at European level on video surveillance technologies within the security sector that will assist operators of critical infrastructure improve their protective security.
For more information, see the Video Analytics Web-Page and also the ERNCIP Site.
This French project from industry minister aims at designing a platform to re-educate at home people with visual impairment. This project has started on the 1st of January 2015 and will last 36 months (+ 6 months to end on the 30th of May 2018). INRIA Grant is 242 Keuros.
The prime partner is the Groupe Genious and other partners are: INRIA Sophia-Antipolis, Streetlab, Hopital des Quinze-Vingts, Fondation Ophtalmologique Rothschild, Fondation Hospitaliere Sainte-Marie.
For more information, see the VISIONUM Project Web-Page.
EIT ICT Labs is one of the first three Knowledge and Innovation Communities (KICs) selected by the European Institute of Innovation & Technology (EIT) to accelerate innovation in Europe. This project is largely described at http://eit.ictlabs.eu.
We are involved in the EIT ICT Labs - Smart cities, from January 2015 to December 2016 with Inria, Bosch, Fraunhofer and Neosensys. The goal is to develop and market a camera-based system combining intelligent video-surveillance improving profitability and customers' behavioral analysis enhancing shopping experience. Today, retailers have difficulties to execute a proper multi-channel strategy as there is a major difference in the metrics available to him to measure customer behaviour and satisfaction between on line & "Brick & mortar" stores. Physical stores are threatened by the ability customers now have to use on line shopping. This activity proposes to both protect physical stores profitability and develop fully efficient multi-channel strategies by finalizing, validating & launching a new video system dedicated to "Brick & Mortar" stores. This system will dramatically enhance (i) the consumer shopping experience, (ii) the store resources allocation and (iii) the store financial performance. The system will be based on a network of "smart" video cameras mutualized for both video-surveillance and consumer behaviour analytic. This will allow the system to be quickly amortized and therefore increase the speed of market penetration.
MOVEMENT is a ANR CSOSG 2013 French project, in the Axis 2 "Protection of citizens and infrastructures" and more precisely in the sub-theme 2.2.2 "Protect infrastructures and networks". This project runs from January 1st 2014 to 2017 (3 years and half) on investigating technologies for improving security in airport areas.
MOVEMENT is focusing on the management of security zones in the non public airport areas. These areas, with a restricted access, are dedicated to service activities such as maintenance, aircraft ground handling, airfreight activities, etc. In these areas, personnel movements tracking and traceability have to be improved in order to facilitate their passage through the different areas, while insuring a high level of security to prevent any unauthorized access. Movement aims at proposing a new concept for the airport's non public security zones (e.g.customs control rooms or luggage loading/unloading areas) management along with the development of an innovative supervision system prototype.
INRIA Grant is 263 Keuros out of 990 Keuros for the whole project.
The prime partner is Morpho and other partners are: Sagem, INRIA Sophia-Antipolis, EGIDIUM, EVITECH and CERAPS.
SafEE (Safe Easy Environment) is a ANR TECSAN French project from Dec 1st 2013 to 2017 (3 years and half) on investigating technologies for stimulation and intervention for Alzheimer patients. French partners of the project include clinicians (CoBTeK, Nice Hospital and Nice University), computational research centers (INRIA) and industrials (Aromatherapeutics, SolarGames). Taiwan partners also include clinicians (Taichung Veterans General Hospital TVGH, NCKU Hospital), computational research laboratory (SMILE Lab at National Cheng Kung University NCKU) and industrials (BDE). INRIA Grant is 180 Keuros out of 625 Keuros for the whole project.
The SafEE project aims at improving the safety, autonomy and quality of life of older people at risk or suffering from Alzheimer's disease and related disorders. More specifically the SafEE project : 1) focuses on specific clinical targets in three domains: behavior, motricity and cognition 2) merges assessment and non pharmacological help/intervention and 3) proposes easy ICT device solutions for the end users.
In this project, experimental studies will be conducted both in France (at Hospital and Nursery Home) and in Taiwan.
For more information, see the CoBTeK Project Web-Page and also the Innovation Alzheimer Site.
This project runs from the 1st of August 2013 up to 2017 (4 years). It aims at detecting critical situations in the daily life of older adults living home alone. We believe that a system that is able to detect potentially dangerous situations will give peace of mind to frail older people as well as to their caregivers. This will require not only recognition of ADLs but also an evaluation of the way and timing in which they are being carried out. The system we want to develop is intended to help them and their relatives to feel more comfortable because they know potentially dangerous situations will be detected and reported to caregivers if necessary. The system is intended to work with a Partner Robot (to send real-time information to the robot) to better interact with the older adult.
CENTAUR is a FP7-PEOPLE-2012-IAPP European Project - Marie Curie - (number 324359) which has started on the 1st of January 2013 and will last 48 months. INRIA Grant is 190.1 Keuros.
CENTAUR aims at developing a network of scientific excellence addressing research topics in computer vision and advancing the state of the art in video surveillance. The cross fertilization of ideas and technology between academia, research institutions and industry will lay the foundations to new methodologies and commercial solutions for monitoring crowded scenes. Three thrusts identified will enable the monitoring of crowded scenes: a) multi camera, multicoverage tracking of objects of interest, b) Anomaly detection and fusion of multimodal sensors, c) activity recognition and behavior analysis in crowded environments.
The prime partner is Honeywell (Czech Republic) and other partners are: Neovison (Czech Republic), INRIA Sophia-Antipolis, Queen Mary University of London and EPFL in Lausanne.
Here is the poster presented in Venice at the MCAA event on March 4-5 2016.
For more information, see the CENTAUR Project Web-Page.
PANORAMA is an ENIAC European Project which has started on the 1st of April 2012 and will last 36+9 months. INRIA Grant is 398.5 Keuros (369KE). This project concerns advanced image-video processing algorithms that are typically acquired with multiple cameras and processed on high performance computing hardware.
PANORAMA aims to research, develop and demonstrate generic breakthrough technologies and hardware architectures for a broad range of imaging applications. For example, object segmentation is a basic building block of many intermediate and low level image analysis methods. In broadcast applications, segmentation can find people's faces and optimize exposure, noise reduction and color processing for those faces; even more importantly, in a multi-camera setup these imaging parameters can then be optimized to provide a consistent display of faces (e.g., matching colors) or other regions of interest.
PANORAMA will deliver solutions for applications in medical imaging, broadcasting systems and security & surveillance, all of which face similar challenging issues in the real time handling and processing of large volumes of image data. These solutions require the development of imaging sensors with higher resolutions and new pixel architectures. Furthermore, integrated high performance computing hardware will be needed to allow for the real time image processing and system control. The related ENIAC work program domains and Grand Challenges are Health and Ageing Society - Hospital Healthcare, Communication & Digital Lifestyles - Evolution to a digital lifestyle and Safety & Security - GC Consumers and Citizens security
The project is executed by a strong international consortium, containing large high-tech companies (e.g. Philips Healthcare, Medisys, Grass Valley, Bosch Security Systems, STMicroelectronics, Thales Angenieux, Capna, CMOSIS,...), smaller innovative SMEs (CycloMedia, Q-Free) and is complemented with relevant research groups and departments from well-known universities (TU Eindhoven, University of Leeds, University of Catania) and research institutes (INRIA, ARMINES, IBBT). Participating countries are France, Italie, U.K., Belgium, Netherlands.
For more information, see the PANORAMA Project Web-Page.
This French DGCIS project from industry minister aims at providing evidences concerning the interest of serious games to design non pharmacological approaches to prevent dementia patients from behavioral disturbances, most particularly for the stimulation of apathic patients. This project has started on the 1st of January 2012 and will last 36+6 months. INRIA Grant is 203 Keuros (193KE). The prime partner is the Groupe Genious and other partners are: INRIA Sophia-Antipolis, IDATE, CMMR from Nice Hospital and CobTek team.
The AZ@Game project is funded from the "Investments for the Future" Call e-Health Project No. 1 "Health and Autonomy in the living place thanks to numerical technologies." The main objectives are to improve the quality of life of patient suffering from Alzheimer disease and related disorders and to maintain close social relationships with their professional and family caregivers. Az@game project designs serious games with patient-oriented scenarios so as to : 1) measure evolution of their disease, 2) encourage their physical activities, 3) stimulate their cognitive abilities, 4) maintain their social relationships. The challenge is therefore to create a playful environment that allows the patient to preserve a maximum of his/her autonomy in nursery home or at home.
Az@GAME est un projet DGCIS - Investissements d'Avenir - dans le cadre de l'appel: Santé et autonomie sur lieu de vie grâce au Numérique dans le programme: Développement de l'Economie Numérique volet Usages, Services et contenus innovants. C'est un projet de 3 ans commencant le 1er janvier 2012. Les principaux partenaires sont : Groupe Genious, IDATE, INRIA, CMMR du CHU nice et équipe CobTek. INRIA recoit un financement de 203 872 euros (193 678).
Az@GAME est un dispositif ergonomique, innovant et ludique qui s'adresse aux patients souffrant de la maladie d'Alzheimer, aux aidants familiaux et professionnels. Az@GAME évalue et favorise le maintien de l'autonomie dans la maladie d'Alzheimer et les pathologies associées. Les entrainements cognitifs, fonctionnels et physiques du patient lui permettent de conserver un maximum d'autonomie mais aussi de remonter des informations de suivi auprès des aidants. Les signes de la maladie apparaissent progressivement, l'état du patient évolue, les besoins en formation de l'aidant familial aussi. En fonction des résultats des entrainements du patient et de l'état de ses connaissances, l'aidant se voit proposer un parcours de formation personnalisé et adapté à ses besoins. En EHPAD, les équipes soignantes peuvent suivre grâce à Az@GAME l'état de l'évolution de la maladie de leurs patients et une formation interactive avec mises en situation virtuelles qui permettent un entraînement auto-évaluatif par feedbacks clinique virtuel.
For more information, see the Az@GAME Web-Page , the Serious Game Web-Page and see the video.
Keeneo is a spin off of the Orion team which aims at commercializing video surveillance solutions, such as intrusion detection. This company has been created in July 2005 with six co-founders from the Orion team and one external partner. Keeneo was bought by Digital Barrier in August 2011.
For more information, see The Keeneo Web-Site : Intelligent Video Surveillance (IVS) software solutions.
Dem@Care was a FP7-ICT-2011.5.1 IP European project (Personal Health Systems) which started on November 1st 2011 and ended in 2015 (48 months). This project has addressed Challenge 5: Digital ICT for Health, Ageing Well, Inclusion and Governance.
The objective of Dem@Care was the development of a complete system providing personal health services to persons with dementia, as well as medical professionals, by using a multitude of sensors, for context-aware, multi-parametric monitoring of lifestyle, ambient environment, and health parameters. Multi-sensor data analysis, combined with intelligent decision making mechanisms, have allowed an accurate representation of the person's current status and have provided the appropriate feedback, both to the person and the associated medical professionals. Multi-parametric monitoring of daily activities, lifestyle, behaviour, in combination with medical data, have provided clinicians with a comprehensive image of the person's condition and its progression, without their being physically present, allowing remote care of their condition. There have been several pilots in France, Ireland, Greece and Sweden. The prime partner was the Centre for Research and Technology Hellas (G) and other partners were: INRIA Sophia-Antipolis, University de Bordeaux 1, Cassidian, Nice Hospital, LinkCareServices (FR), Lulea Tekniska Universitet (SE), Dublin City University (IE), IBM Israel (IL), Philips (NL) and Vistek ISRA Vision (TR).
For more information, see the Dem@Care Project Web-Page.
See also the web-page for the Public Greek dataset.
See also the web-page for the Nice dataset.
See also the video on 7 min Dem@Care: piloting in Thessaloniki Alzheimer Daily Center (clinic system and sensors).
and the video on 8 min Dem@Lab: A Comprehensive system for dementia (clinic protocol).
and the video on 11 min Dem@Care: Overview (at home, bed, kitchen,...)
and the video on 20 min Dem@Care: Multisensing Monitoring for Intelligent Remote Management and Decision Support, the technology.
LinkCareServices and Stars have been collaborating on the design of a novel system for Fall Detection since 2010. This study consists in evaluating the performance of video-based systems for Fall Detection in a large variety of situations. Another goal is to design a novel approach base on RGBD sensors with very low rate of false alarms.
EIT ICT Labs is one of the first three Knowledge and Innovation Communities (KICs) selected by the European Institute of Innovation & Technology (EIT) to accelerate innovation in Europe. EIT is a new independent community body set up to address Europe's innovation gap. It aims to rapidly emerge as a key driver of EU's sustainable growth and competitiveness through the stimulation of world-leading innovation. Among the partners, there are strong technical universities ( U Berlin, 3TU / NIRICT, Aalto University, UPMC - Université Pierre et Marie Curie, Université Paris-Sud 11, Institut Telecom, The Royal Institute of Technology); excellent research centres (DFKI, INRIA, Novay , VTT, SICS) and leading companies ( Deutsche Telekom Laboratories, SAP, Siemens, Philips, Nokia, Alcatel-Lucent, France Telecom, Ericsson). This project is largely described at http://eit.ictlabs.eu.
We are involved in the EIT ICT Labs - Health and Wellbeing - 2011 : for sharing ressources - 2012 : for monitoring Indoor Physical Activities.
For more information, see the EIT ICT Labs - Health and Wellbeing - Project Web-Page.
PAL is an INRIA internal large scale initiative action which has started in January 2011. The teams: AROBAS, COPRIN, DEMAR, E-MOTION, STARS, PRIMA, MAIA, TRIO, and LAGADIC are involved in this action. The objective of this project is to create a research infrastructure that will enable experiments with technologies for improving the quality of life for persons who have suffered a loss of autonomy through age, illness or accident. In particular, the project seeks to enable development of technologies that can provide services for elderly and fragile persons, as well as their immediate family, caregivers and social groups.
For more information, see the PAL Project Web-Page.
SUPPORT (Security UPgrade for PORTs) is a FP7-SEC-2009-1 IP European project which started in July 2010 and ended in 2014 (48 months). The aim of this proposal is to study innovative surveillance components for Port Infrastructures. INRIA Grant is 367.2 Keuros out of 9,920 Keuros for the whole project. The prime partner is BMT Group (UK) and other partners are: INRIA Sophia-Antipolis (France), Swedish Defence Research Agency (SE), Securitas (SE), Technical Research Centre of Finland (FI), MARLO (NO), INLECOM Systems (UK)...
SUPPORT is addressing potential threats on passenger life and the potential for crippling economic damage arising from intentional unlawful attacks on port facilities, by engaging representative stakeholders to guide the development of next generation solutions for upgraded preventive and remedial security capabilities in European ports. The overall benefit will be the secure and efficient operation of European ports enabling uninterrupted flows of cargo and passengers while suppressing attacks on high value port facilities, illegal immigration and trafficking of drugs, weapons and illicit substances all in line with the efforts of FRONTEX and EU member states.
INRIA goal is to study the benefit of a Video-Surveillance system integrated in a global security infrastructure to address potential threats in European ports.
For more information, see the SUPPORT leaflet.
Quasper R&D was a FUI project with national funding, from June 2010 to may 2012. It gathered 3 objectives to serve companies and laboratories: (1) to encourage R&D and the design of new perception systems; (2) to develop and support the definition of European standards to evaluate the functional results of perception systems; (3) to support the qualification and certification of sensors, software and integrated perception systems. Target domains are Security, Transportation and Automotive. INRIA participates to the development of the evaluation platform. The coordinator is THALES SERVICES SAS and other partners are AFNOR, AKKA, DURAN, INRETS, SAGEM SECURITE, ST MICROELECT., THALES RT, VALEO VISION SAS, CEA, CITILOG, INSTITUT d'OPTIQUE, CIVITEC, SOPEMEA, ERTE, HGH.
Quasper R&D est un projet FUI avec co-financements territoriaux, de juin 2010 à mai 2012. Il y a 3 objectifs opérationnels au service des entreprises et des laboratoires : 1) Encourager la R&D et la mise au point de nouveaux systèmes de perceptions Identifier, 2) développer et fournir un support pour l'élaboration de standards européens de performances fonctionnelles des systèmes de perception 3) Soutenir la qualification et la certification de capteurs, de logiciels et de systèmes de perception intégrés.
Les secteurs concernés sont la Sécurité, les Transports, l'Automobile. Le budget INRIA est de 124 403 euros pour aider au développement de la plateforme d'évaluation. Le coordinateur est THALES SERVICES SAS et les autres partenaires sont AFNOR, AKKA, DURAN, INRETS, SAGEM SECURITE, ST MICROELECT., THALES RT, VALEO VISION SAS, CEA, CITILOG, INSTITUT d'OPTIQUE, CIVITEC, SOPEMEA, ERTE, HGH.
VANAHEIM (Video/Audio Networked surveillance system enhAncement through Human-cEntered adaptIve Monitoring) was a FP7-ICT-2009-4 Cognitive Systems and Robotics IP European project which started on February 1st 2010 and ended in 2013 (42+3 months). The aim of this proposal was to study innovative surveillance components for Autonomous Monitoring Of Multi-Sensory And Networked Infrastructure Such As Underground Transportation Environment. The prime partner was Multitel (Belgium) and others partners were: INRIA Sophia-Antipolis (France), Thales Communications (France), IDIAP (Switzerland), Torino GTT (Italy) and Rantégie Autonome des Transports Parisiens RATP (France), Ludwig Boltzmann Institute for Urban Ethology (Austria) and Thales Communications (Italy). INRIA Grant was 700 Keuros out of 3 718 Keuros for the whole project. First, we investigated unsupervised modelling techniques for audio/video streams content characterization. Second, moving one step beyond localization-based event recognition, we investigated human-centered vision techniques for behavior monitoring applications. Conducted studies were focused on monitoring how human beings act in a given infrastructure, and how they interact with it and with each other.
For more information, see the VANAHEIM Project Web-Page.
ViCoMo is a ITEA 2 European Project which started on the 1st of October 2009 and lasted 36 months. INRIA Grant was 354.6 Keuros. This project concerned advanced video-interpretation algorithms on video data that are typically acquired with multiple cameras. ViCoMo was focusing on the construction of realistic context models to improve the decision making of complex vision systems and to produce a faithful and meaningful behaviour. The context of an event (a crime, group activity, or computer-aided diagnosis) can be found with multiple sensors, like a multi-camera set-up in a surveillance system. The general goal of the ViCoMo project was thus to find the context of events that were captured by the cameras or image sensors, and model the context such that reliable reasoning about an event can be established. Hence, modelling of events and the 3D surroundings helps to recognize the behaviour of persons, objects and events in a 3D view.
The project was executed by a strong international consortium, containing large high-tech companies (e.g. Philips, Acciona, Thales), smaller innovative SMEs (CycloMedia, VDG Security) and is complemented with relevant research groups and departments from well-known universities (TU Eindhoven, University of Catalonia, Free University of Brussels) and research institutes (INRIA, CEA List, Multitel). Participating countries were France, Spain, Finland, Turkey, Belgium, Netherlands.
For more information, see the ViCoMo Project Web-Page.
SWEET-HOME was a ANR TECSAN French project from Nov 1st 2009 to 2012 (3 years) on long-term monitoring of elderly people at Hospital with Nice City Hospital, Actis Ingenierie, MICA Center (CNRS unit - UMI 2954) in Hanoi, Vietnam, SMILE Lab at National Cheng Kung University, Taiwan and National Cheng Kung University Hospital. INRIA Grant is 240 Keuros out of 689 Keuros for the whole project. SWEET-HOME project aimed at building an innovative framework for modelling activities of daily living (ADLs) at home. These activities can help assessing elderly disease (e.g. Alzheimer, depression, apathy) evolution or detecting pre-cursors such as unbalanced walking, speed, walked distance, psychomotor slowness, frequent sighing and frowning, social withdrawal with a result of increasing indoor hours. The SWEET-HOME project focused on two aspects related to Alzheimer disease: (1) to assess the initiative ability of patient and whether the patient is involved in goal directed behaviours (2) to assess walking disorders and potential risk of falls. In this focus, the goal was to collect and combine multi-sensor (audio-video) information to detect activities and assess behavioural trends to provide user services at different levels. In this project an experimental room was used in Nice-Cimiez Hospital for monitoring Alzheimer patients.
For more information, see the SWEET-HOME Project Web-Page.
CIU-Santé (Centre d'Innovation et d'Usages en Santé) was a DGCIS French project from November 2008 to 30 April 2012 (42 months) on long-term monitoring of elderly people at Hospital with CSTB, the Nice City Hospital, Pole SCS, Thales Aliena Space, Actis Ingenierie, Movea, CEA and UNSA. In this project two experimental rooms have been equipped in Nice-Cimiez Hospital for monitoring Alzheimer patients.
For more information, see the CIU-Santé Project Web-Page.
Using video surveillance, the VIDEO-ID project aimed to achieve real time human activity detection including the prediction of suspect or abnormal activities. This project also aimed to be capable to perform identification using face and iris recognition. Thanks to such identification, a detected person was tracked throughout a network of distant cameras, allowing to draw a person's route and his destination. Without being systematic, a logic set of identification procedures was established: event's situation and abnormal behaviour and people face recognition.
Partners were Thales TSS, INRIA, EURECOM, TELECOM and Management Sud Paris, CREDOF, UIC, RATP,STSI/CTSI, DGA.
For more information, see the VIDEO-ID Project Web-Page.
European project Cofriend aimed at conceiving cognitive vision system for automatic monitoring of human activities. Cofriend project started in February 2008 and ended in February 2011 and follows up the Avitrack project. The project studied all activities occurring around aircraft parked on aprons at Toulouse airport. Most specifically the system had to adapt itself to lighting condition changes, weather changes, to new airport configurations, to the arrival of new servicing vehicles and new aircraft types. The performance of the system to recognise correctly the actions of interest and its capability to adapt itself to unexpected situations was a keypoint of this project. Six teams were involved in Cofriend: INRIA Sophia-Antipolis, Akka Toulouse airport (France), University of Reading and of Leeds (UK), University of Hamburg (Germany).
For more information, see the Cofriend Project Web-Page.
We were participating in the SIC project from the SYSTEM@TIC competitivity cluster (``pole de competivite'') which was a strategic initiative in security from the Paris region. More precisely the SIC project has been founded for 42 months from October 2006 to April 2010 in perimeter security for sensitive buildings. The partners included Thales, EADS, Alcatel, BULL, SAGEM, Bertin, Trusted Logic, CEA, Sodern, Axalto, GET/INT, Paris Sud and RATP. The solutions proposed by SIC project were validated through two demonstrators, RATP subway station and Bobigny administrative building.
MONITORE was an INRIA Exploratory Action from May 2008 to 2009 for the real-time monitoring of imaging diagnostics to detect thermal events in tore plasma. This work was a preparation for the design of the future ITER nuclear reactor and was done in partnership with the Imaging and Diagnostics Group of the CEA Cadarache, France.
For more information, see the MONITORE Project Web-Page.
CARETAKER is an IST-FP6 STREP European project which started in March 2006 and ended in August 2008. The main objective of this project was to discover pertinent information in large multimedia database. The prime partner was Thales Communications (France) and others partners were: Multitel (Belgium), Kingston University (UK), IDIAP (Switzerland), Torino GTT and Roma ATAC Transport Agency (Italy), SOLID software editor for multimedia data basis (Finland) and Brno University of Technology (Czechia). We were clustering people trajectories and recognizing and learning scenarios for frequent or unexpected human activities from both video and audio events. We managed to discover knowledge such as "travelers are 40% quicker to buy ticket during rush hours". Two demonstrators have been done in Torino and Rome subways.
For more information, see the CARETAKER Project Web-Page.
SERKET was a European ITEA project in collaboration with THALES R&T FR, THALES Security Syst, CEA, EADS and Bull (France); Atos Origin, INDRA and Universidad de Murcia (Spanish); XT-I, Capvidia, Multitel ABSL, FPMs, ACIC, BARCO, VUB-STRO and VUB-ETRO (Belgium). The project was at the end of November 2005 and it ended in July 2008. The main objective of this project was to develop techniques to analyze crowd behaviors and to help in terrorist prevention.
We have been in cooperated with STmicroelectronics and Ecole des Mines de Paris at Fontainebleau in the framework of PACA Lab from March 2003 till March 2008. We have designed intelligent cameras integrating image analysis and interpretation capabilities. In particular a PhD doctorate (Bernard Boulay) has developed a new algorithm for 3D human posture recognition in real-time from video cameras. This work has been applied to the long-term monitoring of elderly people living at home.
For more information, see the STmicroelectronics Project Web-Page.
In 2006, we started the GERHOME project in collaboration with CSTB (Centre Scientifique et Technique du Batiment) and the Nice City Hospital (Groupe de Recherche sur la Tophicite et le Viellissement). The GER'HOME project was funded by the PACA region. GER'HOME project is devoted to experiment and develop techniques that allow long-term monitoring of elderly people at home. In this project an experimental home has been built in Sophia Antipolis instrumented with environmental sensors such as pressure contract, water and electric consumption sensors. We have developed unsupervised event learning and recognition techniques to be integrated in a platform to provide services and to perform experiments.
For more information, see the GERHOME Project Web-Page.
In the framework of collaboration with RATP from February 2001 till 2008, we have designed a real-time system for lateral shape recognition. We have developed an operational system which is able to detect and classify people and objects when they access the subway network (validate their ticket). The system is combining information from several sensors (one top camera, five lateral cameras, leds and optical cells) to obtain a very high recognition rate with real-time constraint.
For more information, see the RATP Project Web-Page.
We have led the ETISEO project on performance evaluation of video understanding algorithms. This project began in 2005 and ended in January 2007. It has provided both dataset and evaluation tools which constitute a reference in "vehicles and pedestrians scene understanding". Project ETISEO has focused on the treatment and interpretation of videos involving pedestrians and (or) vehicles, indoor or outdoor, obtained from fixed cameras. This project was part of the Techno-Vision evaluation network funded by the French ministry of defense and the French ministry of research. The main partners were Silogic (coordinator, evaluator and data-provider), INRIA (scientific leader), INRETS-LEOST (data-provider) and CEA-List (data-provider). Moreover, this project had brought together governmental agencies (from UK, US and France) and about 20 international teams that have developed algorithms and wanted to evaluate and compare their technology with each other. ETISEO project had been provided them with free videos, metrics and an automatic tool to run evaluations.
For more information, see the ETISEO project for Video Surveillance Performance Evaluation.
The CASSIOPEE project is a French collaboration among Le Credit Agricole, Ciel and Securitas Systemes - Eurotelis which started in January 2002 and ended in March 2006. We have developed and tested an automatic visual-surveillance platform for detection of predefined scenarios such as bank attack in a bank agency environment. The system has been validated in four bank agencies by the bank security operators located in a distant control security center.
For more information, see the CASSIOPEE Project Web-Page.
SAMSIT was a project in collaboration among ALSTOM, CEA, SNCF, INRETS. It started in January 2004 and ended in March 2006. We have developed techniques to automatically detect human behaviors in trains. Such detection of human behaviors are challenging ones, due to train motion, cluttered environment and fast illumination changes. Thanks to the combination of audio and video signals, we were able to detect scenarios such as scratching the window, cell-phone theft, violence and beggars.
For more information, see the SAMSIT Project Web-Page.
In 2006 we had a project done on trichogramma monitoring in collaboration with INRA that lasted for 6 months. A trichogramma is a millimeter wasp which is brought to fight a corn parasite. Biologists asked us to monitor its behavior to understand more about its life.
For more information, see the Trichogramma Project Web-Page.
AVITRACK was a IST-FP6 European project in collaboration with Silogic S.A. Toulouse (FR), University of Reading (UK), CCI Aeroport Toulouse Blagnac (France), Fedespace (France), Tekever LDA, Lisbon (Portugal), ARC Seibersdorf research GMBH, Wien (Austria), Technique Universities, Vienna (Austria), IKT (Norway) and Euro Inter (Toulouse France). This 2-year project was started in February 2004 and ended in March 2006. During this project, we have developed algorithms to recognize the servicing activities around parked aircrafts in an apron area monitored by eight cameras in Toulouse airport (France). Activities may be simple events involving one mobile object like the arrival or the departure of ground vehicles or complex scenarios like refueling or luggage loading.
For more information, see the AVITRACK Project Web-Page.
TELESCOPE was a project in collaboration with Bull from March 1998 till March 2006. During this project we have developed a toolkit in the domain of cognitive video interpretation for video intelligent surveillance applications (VIS). This toolkit contained components to facilitate the usage and installation of surveillance systems, to ensure more robustness and to extend video surveillance functionalities.
We had participated in the specific Inter-media Semantics Extraction and Reasoning (ISERE) STIC-Asie action from 2004 until December 2006. ISERE project had brought together four research centers one from Asia and three from France. It promoted the development of research on semantics analysis, reasoning and multimedia data, and the application of these results in the domains of e-learning, automatic surveillance and medical databases. Besides allowing sharing scientific results, this cooperation has increased the exchange of researchers between Asia and France. The Asia partners of the ISERE action were IPAL-CNRS, I2R A-STAR and NUS for Singapor, MICA for Vietnam, the National Institute of Informatics NII for Japan and the National Cheng Kung University and the National Taiwan University for Taiwan. The French partners were INRIA-Orion, CLIPS-IMAG CNRS-INPG-UJF and IRIT.
The VIDEA project was in collaboration with Vigitec (Brussels) which began in November 2003 and lasted for 2 years. We have transferred a part of the video surveillance technology of the ORION team into industrial products. During this project, we have developed two applications enabling the recognition of specific human behaviors: control access for buildings and street violence in cities.
The ALSTOM project was began in April 2003 and finished in July 2003. In this project we had realized a feasibility study on an industrial application allowing detecting human behaviors in trains using video understanding techniques.
The RASV project was collaboration with SNCF which began in September 2003 for duration of 18 months. We have applied techniques to automatically detect human behaviors in trains specified by SNCF and security operators.
The KINOMAI project started in December 2003 for duration of four months in collaboration with Kinomai company. We have developed an object recognition platform for image and video indexing and retrieval purposes.
The ADVISOR project - Annotated Digital Video for Intelligent Surveillance and Optimised Retrieval - was an IST European project on multi camera video surveillance systems in subways which lasted 3 years and finished in March 2003. THALES TRT UK, BULL, VIGITEC, Univ. Kingston, Univ. Reading, KCL London has participated in the project. The aim of this work was to automatically analyze, to recognize scenarios of interest, archive and annotate subway video sequences. We were able to recognize six types of behaviors: fighting, over-crowding, fraud (jumping over barrier), graffiti, blocking exit and vandalism (breaking ticket machine). This work has been validated with Brussels and Barcelona subways. A demonstrator was installed in Barcelona subway for 10 days fed continuously by four cameras and observed by real security operators during the operational time.
For more information, see the European Project ADVISOR on Subway Monitoring
The MediaSpace was a national project on smart video conferencing which lasted from January to December 2000 in collaboration with GRAVIR team. The goal was to analyze people behaviors in office in order to improve relationships of employees from team located in different sites. Thanks to this system we were able to detect meeting (with guests) and turn of automatically the video conferencing system to protect employee privacy. We were also able to focus automatically the camera (as an intelligent camera man) on points of interest in the scene when people for instance were writing on the white board.
I have been involved in the V.S.A.M. (Video Surveillance and Activity Monitoring) from DARPA agency through the University of Southern California from October 1997 to January 2000. We have developed techniques to analyze check points depicted by videos taken by drones during the Yugoslavian war. We were able to detect whether cars were passing normally the check points or not.
The PASSWORDS was an IST European project on super market, parking and subways monitoring. It has been done in collaboration with VIGITEC, SEPA, DIBE, AUCHAN from 1994 to 1997. The goal was to show that at the time an automatic process could recognise human behavior such as loitering in the parking lot.
For more information, see the PASSWORDS Project Web-Page.