Public Projects
The following are publicly funded competitive projects developed by the group all in the context of driver assistance.
eCo-Drivers: Ecologic Cooperative Driver and Road Intelligent Visual Exploration for Route Safety (2012-present) | |
Funding | TRA2011-29454-C03-00-00 |
Principal Investigator | Antonio M. López |
Participants | 33 researchers from the Computer Vision Center and Universidad Carlos III de Madrid. |
Description |
The aim of this project is to research technologies for bringing ADAS to urban oriented electric vehicles. Two are the major distinctive features of our proposal are: (1) the use of vision as “eco”-sensor; and (2) to follow a driver-centric approach, i.e., rather than thinking in road and driver monitoring as working-alone ADAS, we will make them to cooperate in order to assist the driver only when he/she really need it, or in other words, working as actual co-drivers. Both things together build our concept of eco-driver.
We organize the overall coordinated project “eCo-DRIVERS: Ecologic Cooperative Driver and Road Intelligent Visual Exploration for Route Safety” as three complementary and collaborative subprojects: (1) “Vision-based Driver Assistance Systems for Urban Environments (ViDAS-UrbE)”; (2) “Driver Distraction Detection System (D3System)”; and (3) “Intelligent Agent-based Driver Decision Support (i-Support)”. The core research of subprojects (1) and (2) will focus on computer vision while (3) will address research on machine learning and reasoning under uncertain and incomplete data. Based on this research the project aims to develop two urban-oriented and vision-based co-drivers for (a) driver-centric obstacle detection; and (b) driver-centric pedestrian detection. |
More information | http://www.cvc.uab.es/adas/projects/eco-drivers/ |
SiMeVe – Multispectral Stereo Vision System (2012-present) | |
Funding | TIN2011-25606 |
Principal Investigator | Angel D. Sappa |
Participants | A. Sappa, R. Toledo, J. Álvarez, F. Barrera, N. Onkarappa, D. Aldavert, M. Piñol |
Description |
Imaging system for computing sparse/dense disparity maps from multispectral images. The stereo head consists of two cameras rigidly attached: a color camera (VS: visible spectrum) and an infrared camera (LWIR: Long-Wave InfraRed).
|
More information | http://www.cvc.uab.es/adas/projects/simeve |
FireWATCHER: Fire Warning by Aerial Terrain Control of Hot Embers Regions (2012-present) | |
Funding | Ministry of Economy |
Principal Investigator | Daniel Ponsa |
Participants | N/A |
Description |
The FireWATCHER project (acronym for “Fire Warning by Aerial Terrain Control of Hot Embers Regions”) focuses on the use of Computer Vision algorithms to process data provided by the UAV fleet. Computer Vision is the scientific discipline that addresses the problem of automatically understanding visual information, i.e., to infer the world scenes that have given rise to the raw images, recognizing the meaningful objects they contain. In this subproject, techniques from this field will be applied to detect and characterise hot spots and fire fronts in the remotely acquired aerial images. Fire front monitorization will be done just on nighttime images, since at daytime UAVs may come into conflict with manned aerial vehicles. Hot spot detection will be done on daytime and nighttime sequences, with the aim to assist fire-fighters in post-fire control activities (no manned aircrafts participate during these tasks). Specific algorithms will be needed to extract the required information automatically and georeference it precisely in near real-time. In addition to these topics, we will explore mechanisms to geolocalise UAVs from acquired images. Our aim is providing them with an alternative navigation system for their assistance in situations of low GPS coverage or sensor failure. To fulfil these objectives, we will intend to go beyond the state of the art in topics like near real-time imagery georectification based on low cost equipment, vision-based vehicle localisation, night time fire monitoring, and hot spots detection and characterization. We will cooperate with the other partners of the FireGUARD project, proposing novel collaborative strategies to image the terrain by means of multiple UAVs in order to accurately estimate the data required by the fleet management system. |
More information | http://www.cvc.uab.es/adas/projects/firewatcher/ |
MIPRCV: Multimodal Interaction in Pattern Recognition and Computer Vision (2007-2012) | |
Funding | MEC CONSOLIER-INGENIO (ref. CSD2007-00018) |
Principal Investigator | Antonio M. López and Angel D. Sappa (from Computer Vision Center) (Coordinator: Enrique Vidal Ruiz from Instituto Tecnológico de Informática, Universidad Politécnica de Valencia) |
Participants | 12 |
Description |
Social and industrial demands for Multimodal Interactive (MI) technologies and advanced man-machine interfaces are increasing dramatically. Pattern Recognition (PR) and Computer Vision (CV) play a highly relevant role of in the development of these MI technologies and interfaces. However, MIPRCV establishes a five-years research programme to develop PR and CV approaches that explicitly deal with the challenges and opportunities entailed by the human-interaction paradigm. Based on these approaches, it also aims at implementing actual systems and prototypes for a number of important MI applications. The ultimate goal is to show how existing PR and CV technologies can naturally evolve to help the development of advanced multi-modal interactive systems that will realize the long standing promises of a |
More information | http://miprcv.iti.upv.es |
OnviSuPRA: On board video surveillance platform for railways applications (2009) | |
Funding | CTP-2008ITT-00001 |
Principal Investigator | Angel D. Sappa |
Participants | A. Sappa, A. López, F. Lumbreras, J. Serrat, D. Ponsa. |
Description |
The main objective of this project is to do research towards an intelligent onboard multi-cameras based platform capable to detect potentially dangerous situations and provide more timely prevention and management of events.
|
More information | http://www.cvc.uab.es/~asappa/Onvisupra_Index.htm |
Computer vision based detection and tracking of vehicles and pedestrians for ADAS (2007-2010) | |
Funding |
TRA2007-62526/AUT
|
Principal Investigator | Antonio M. López |
Participants | Antonio M. López, Joan Serrat, Daniel Ponsa, David Gerónimo, José M. Álvarez, Ferran Diego, Felipe Lumbreras. |
Description |
In this project we go one step further from the 2004-2007 project by not only improving the solutions for lane markings and pedestrian/vehicle detection, but also research on other topics such as road segmentation and crowd detection. These functionalities are the base for ADAS applications like adaptive cruise control, lane/road departure warning, lane/road keeping and pedestrian protection systems. From the scientific point of view, the research will address the computer vision topics of multi-class classifiers (feature selection and machine learning), multi-target tracking, color and texture analysis, illumination invariant images, movement analysis (ego-motion, gait pattern), robust model fitting and stereo analysis.
|
Computer Vision Detection and Tracking of Vehicles and Pedestrians. Validation on an Intelligent Vehicle Prototype (2004-2007) | |
Funding |
MEC TRA2004-06702/AUT
|
Principal Investigator | Antonio M. López |
Participants | Antonio M. López, Felipe Lumbreras, Joan Serrat, Angel D. Sappa, Carme Julià. |
Description |
The aim of this project was to devise new machine vision and pattern recognition techniques able to solve the following technological problems: 1) detection and tracking of vehicles with a monocular system, at day and night, 2) pedestrian detection with a stereovision system and deformable templates, 3) Lane markings detection in curves, from parametric robust fitting techniques, and 4) Computation of geometrical measures from images : distance to obstacles and curvature of the actual lane The combination of these former contributions is the base the most important applications of ADAS: Lane departure warning, Lane change assistance, Automated cruise control, Collision warning, Pedestrian awareness and Intelligent lighting. The empirical evaluation was done firstly off-line, from stored sequences and software prototype (e.g in MatLab or the like) and then on-line on a SEAT Alhambra ADAS, which the Centro Técnico de SEAT-Martorell has kindly offered to us. |