Current Research projects:
Assessing Driver-Vehicle Interactions in Self-Driving Mode
Automation of on-road vehicles has been increasing in the last decades since the first Driver Assistance Systems. Given that, at least for a few years, feasible totally automated driving systems are far from a reality, there are several intermediate levels of driving automation for on-road vehicles. In some of these levels, the human driver can perform other activities while the system is autonomously driving, but he/she might recover the car’s control in case the system requires it. From this situation a main question arises. At which moment and how can the automated driving system return the control to the driver? The answer to this question depends on several points, such as the activity the driver is doing, the general state of the driver, the possible reaction of the driver, the particular situation of the environment, the action the car is doing, etc.
This project approaches two of the three main agents, the behaviours of the car and the driver. The car is controlled by a simulation environment, while the driver is monitored by several cameras that analyse her/his activity.
Finished Research projects:
MIOCARDIA: Definition of an integrated model of the Functionality and Muscular Anatomy of the Left Ventricle
The Left Ventricle (LV) dynamics (motion and deformation) reflects, to a major or minor extend, most of the cardiovascular diseases and, thus, plays a significant role in their diagnosis and treatment. Recent advances in tomographic devices (such as magnetic resonance or TAC) are generating large volumes of data on dynamic processes, which have encourage, in the last years, development of 3D computational models of LV dynamics.
This project addresses the development of an Integrative Model of the Functionality and Muscular Anatomy of the Left Ventricle merging the 3D motion (functionality) with the spatial disposition of the muscular band (anatomy) and allowing the estimation of the electromechanical activation sequence for each patient.
Arterial Dynamics and Structures in IntraVascular Ultrasound Sequences
IntraVascular UltraSound (IVUS) has become a usual imaging technique for the diagnosis and follow up of arterial diseases. IVUS is a catheter-based imaging technique which shows a sequence of cross sections of the artery under study. Inspection of a single image gives information about the percentage of stenosis. Meanwhile, inspection of longitudinal views provides information about artery bio-mechanical properties, which can prevent a fatal outcome of the cardiovascular disease.
This project proposes several image processing tools for exploring vessel dynamics and structures by means of IVUS Sequences processing: a physics-based model to extract, analyze and correct vessel in-plane rigid dynamics and to retrieve cardiac phase and a deterministic-statistical method for automatic vessel borders detection.