Description du projet
La vision par ordinateur pour la gestion du trafic
En améliorant les modes de transport doux, y compris le vélo et la marche, les villes deviendront inévitablement plus durables, tout en contribuant à réduire les taux de pollution et la congestion. Pourtant, les autorités municipales de l’Union européenne rencontrent des difficultés pour protéger les usagers vulnérables qui représentent la grande majorité des victimes de la route dans les zones urbaines. UrbanDynamics entend repenser les modèles de mobilité, en mettant au point un suivi du trafic en temps réel et un système de gestion qui utilise les données brutes du trafic fournies par des caméras afin de reconnaître, suivre, et analyser le comportement de tous les participants à la circulation urbaine, y compris les cyclistes et les piétons. UrbanDynamics stimulera la croissance avec des revenus dépassant les 18 millions d’EUR et permettra de créer au moins 15 emplois.
Objectif
The booming urbanisation poses several challenges for cities such as growing traffic volumes, safety, and increasing environmental pressures. Enhancing the use of soft transportation modes (cycling and walking) will make cities more sustainable by reducing congestion and pollution. However city authorities are currently struggling to guarantee the safety of those vulnerable road users: they account for almost 70% of the road victims in urban areas. The objective of increasing the use of soft transport modes can only be achieved with a re-design of current urban mobility models. A holistic approach for managing urban traffic is one the most urgent needs of traffic authorities. Correspondingly, the associated traffic management market is projected to grow at a CAGR = 21% and reach the €19.4 billion by 2022. At ViNotion, a Dutch leading expert in intelligent image interpretation since 2007, we have developed UrbanDynamics, a real-time traffic monitoring and managing system that uses raw traffic data from cameras to recognise, track, and analyse the behaviour of all urban traffic participants, including bicycles and pedestrians. Our solution collects data from pre-existing cameras and by means of machine- and deep learning, analyses the behaviour of all traffic participants providing an in-depth insight into complex urban traffic scenarios. Our competitive advantages rely on the high accuracy, even in broad areas with only one system (false detections < 1% in 18m width lane), and versatility of the traffic information obtained (counting, speed, direction, queue length, waiting time, etc.). At ViNotion we aim at making EU cities more friendly for pedestrians and bicycles and reduce associated traffic fatalities by facilitating an optimal integration of the soft transportation modes into the urban environment. UrbanDynamics will boost our growth with revenues surpassing the €18 million in the 3rd year after market uptake and the creation of up to 15 new position.
Champ scientifique
- engineering and technologycivil engineeringurban engineeringsmart cities
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsoptical sensors
- natural sciencescomputer and information sciencesartificial intelligencecomputer vision
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- social sciencessocial geographytransportsustainable transportintelligent transport systems
Programme(s)
Régime de financement
SME-1 - SME instrument phase 1Coordinateur
5641 JA Eindhoven
Pays-Bas
L’entreprise s’est définie comme une PME (petite et moyenne entreprise) au moment de la signature de la convention de subvention.