Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Los términos de búsqueda han de ser en inglés.

Ciudad inteligente: monitorización del tráfico de vehículos en rotondas mediante software de seguimiento de vehículos

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOIT20150413001
Publicado:
14/07/2015
Caducidad:
13/07/2016
Resumen:
Una universidad técnica italiana ha desarrollado un software (seguimiento de vehículos para análisis de rotondas) que permite obtener trayectorias y variables cinemáticas de los vehículos dentro de una rotonda. Las trayectorias generadas por el sistema de seguimiento ofrecen una matriz de entrada/salida (E/E), trayectorias del vehículo, perfiles de velocidad y aceleración y clasificación de vehículos. Se busca un socio industrial interesado en licenciar el software y know-how relacionado y establecer acuerdos de cooperación técnica.

Details

Tittle:
Smart city: monitoring vehicular flow in roundabout through reliable software for vehicle tracking
Summary:
An Italian engineering university, based in Milan, developed a software program, called Vehicle Tracking for Roundabout Analysis, to obtain paths and kinematic variables of vehicles inside a roundabout. Trajectories produced by the tracking system provide entry/exit matrix (E/E), vehicle trajectories, speed and acceleration profiles, vehicle classification. The research team is looking for an industrial partner, interested in licensing software and related know how, with technical cooperation.
Description:
A software program, called Vehicle Tracking for Roundabout Analysis (VeTRA), was developed by an Italian university to obtain paths, kinematic variables of vehicles inside a roundabout, and the entry/exit (E/E) demand matrix through video recording. In VeTRA, a model of the background is simulated so that the image areas corresponding to moving vehicles are derived by difference. As the generation of E/E matrices demands the independent tracking of each vehicle from the entry and exit sections of a roundabout, multiple Kalman filters have been used to integrate information with that resulting at each frame from background difference. Vehicles are also tracked when small occlusions are present in the scene (e.g., high vegetation in the central island, electricity poles, and vehicle intersections). VeTRA-computed trajectories are compared with the positions (accurate to within a few centimeters) measured by the Real Time Kinematic (RTK) GPS receiver, which is mounted on a probe vehicle. Software algorithms are highly reliable. The instrumentation used to collect and evaluate data consists of a vision system and a RTK-GPS system, both connected to a dedicated PC.
The vision system provides information on vehicular flow through the processing of images recorded by the video camera (mounted on a fixed pole or a flying drone), whereas the RTK-GPS system produces data useful for calibrating and evaluating the vision system. Collected data require processing before use. In particular, images need conversion, undistortion and rectification, whereas RTK-GPS data need data conversion (for rover data) and synchronization between the base station and rover timestamps. A few issues confronted in VeTRA illustrate how robust and accurate the software is: changeable wind conditions, sudden changes in light conditions because passing clouds, occlusions caused by fixed objects (e.g., trees, poles) or moving vehicles, perspective deformation of the shape of moving objects significantly, and this has to be taken into account when performing data association.
The key algorithm of the VeTRA tool is the tracking system which performs the following functions: (1) Adaptive background modeling and subtraction to detect moving objects in the scene; (2) Foreground identification through shadow and noise removal to give image areas representing vehicles (hereafter referred to as "blobs"); (3) Association of newly detected blobs with previously tracked vehicles; (4) Trajectory update for the tracked vehicles according to new information.
All these activities rely on a proper model of the background that has to be sufficiently robust to contend with changes in light conditions and camera movement. In VeTRA, this is achieved by the adaptation mechanism, whereby each pixel is updated in the model by using a convex combination between its present value and the observed image. This updating mechanism is continuously performed in the areas of the image where no vehicles are present.
Once the background model is available, vehicles can be extracted by simply subtracting the current frame and the background model. Pixels differing from the background by more than a given threshold (different for each pixel and derived from an estimate of the image noise for that pixel) are considered to be vehicles. Trajectories produced by the tracking system are then processed in order to provide entry/exit matrix, vehicle trajectories, speed and acceleration profiles, vehicle classification. Practical utility of VeTRA concerns capability of extracting (a large quantity of) data from images by a reasonable effort.
The software is now at a prototypal stage and requires engineerisation to be practical for final user.
The university team is looking for an industrial partner (e.g.: engineering company, software house) active in smart city projects and interested in acquisition or licensing VeTRA software and know how. Technical cooperation agreement is also welcome.
Advantages and Innovations:
The main feature of the software is that it allows the automatic computation of the main variables necessary to rank and evaluate a generic roundabout: the Entry/Exit (E/E) matrix with classification of vehicles (e.g., heavy, light and motorbikes), vehicle trajectories and vehicular speed diagrams along the paths inside the roundabout.
Possible customers are civil engineering and software companies active in smart city projects, such as traffic analysis and road design.
Stage of Development:
Available for demonstration
IPs:
Patent(s) applied for but not yet granted

Partner sought

Type and Role of Partner Sought:
The university team is looking for an industrial partner interested in licensing of VeTRA software and related know how. Technical cooperation agreement is also considered.

Client

Type and Size of Client:
University
Already Engaged in Trans-National Cooperation:
Si
Languages Spoken:
English
Italian

Keywords

Technology Keywords:
01004003 Aplicaciones para transportes y logística