Project description
The goal of BeCamGreen project is to develop a solution based on computer vision and big data, to contribute to traffic reduction, especially of vehicles with a single occupant, and boost new policies for sustainable mobility.
The solution will make it possible for local authorities and other transport infrastructure managers, like road and parking operators, to know mobility patterns and define strategies and policies to reduce traffic congestion, prioritize and promote the use of public transportation, high-occupancy and low-emission vehicles, with the resulting improvement in traffic, air quality and noise levels.
BeCamGreen solution will provide an automatic and non-intrusive solution to help infrastructure mangers to deploy strategies for traffic reduction by:
- Understanding mobility patterns, predicting traffic situation, and helping to deploy strategies to reduce the number of single-occupancy car trips
- Detecting the number of occupants in a vehicle and the type of vehicle, and based on this, applying discounts or penalties, variable rates (for example, at parkings or tolls), or access restrictions to certain roads, especially in city centers
- Encouraging citizens to use High Occupancy Vehicles (HOV), carsharing, park&ride, collective modes and low emission vehicles.
This type of solution is highly demanded in USA, were the number of HOV/HOT (High Occupancy Vehicles / High Occupancy Toll) lanes is increasing. In Europe, this solution intends to be a key element also for the demand management and city access strategies that are being gradually deployed in many cities since the past few years, based on the number of occupants, type of vehicle, plate or peak hours.
Collaborating Companies or Organisations
Indra´s Role
Indra intends to take advantage of previous R&D projects to perfect and test, in a real setting with traffic, a product that is fully marketable and unique, for the automated, real-time High Occupancy Vehicles Detection, capable of detecting occupants in both front and back seats.
Universities and Technological Centers
Technologies used
The key technologies used in the project are:
- Vision subsystem to collect information from vehiclesand detect the number of occupants in front and rear seats: use of artificial Intelligence techniques, computer vision, deep learning and multispectral analysis.
- Big Data engine to detect and predict traffic situations by using and integrating data in real time from IoT sensors, social networks, different types of open data and of the vision subsystem itself developed during the project.
More information
This project, under reference ID 7058, has been co-financed by the EIT Digital and included in its 2017 Business Plan.
ONU Sustainable Development Goals:
