S. Álvarez

Provenance in Agent-Mediated Healthcare Systems

People are increasingly cooperating to share electronic information and techniques throughout various industries. In healthcare applications, data (a single patients healthcare history), workflow (procedures carried out on that patient), and logs (a recording of meaningful procedural events) are often distributed among several heterogeneous and autonomous information systems. Understanding a patients treatment history can help healthcare providers make treatment decisions. Provenance-aware applications can facilitate this process by tracing events, event dependencies, and provider decisions across various healthcare institutions

An Experimental Study on Pitch Compensation in Pedestrian-Protection Systems for Collision Avoidance and Mitigation

This paper describes an improved stereovision system for the anticipated detection of car-to-pedestrian accidents. An improvement of the previous versions of the pedestrian-detection system is achieved by compensation of the cameras pitch angle, since it results in higher accuracy in the location of the ground plane and more accurate depth measurements. The system has been mounted on two different prototype cars, and several real collision-avoidance and collision-mitigation experiments have been carried out in private circuits using actors and dummies, which represents one of the main contributions of this paper. Collision avoidance is carried out by means of deceleration strategies whenever the accident is avoidable. Likewise, collision mitigation is accomplished by triggering an active hood system.

Applying provenance in distributed organ transplant management

The use of ICT solutions applied to Healthcare in distributed scenarios should not only provide improvements in the distributed processes and services they are targeted to assist but also provide ways to trace all the meaningful events and decisions taken in such distributed scenario. Provenance is an innovative way to trace such events and decisions in Distributed Health Care Systems, by providing ways to recover the origin of the collected data from the patients and/or the medical processes. Here we present a work in progress to apply provenance in the domain of distributed organ transplant management.

Real-Time Vision-Based Vehicle Detection for Rear-End Collision Mitigation Systems

This paper describes a real-time vision-based system that detects vehicles approaching from the rear in order to anticipate possible rear-end collisions. A camera mounted on the rear of the vehicle provides images which are analysed by means of computer vision techniques. The detection of candidates is carried out using the top-hat transform in combination with intensity and edge-based symmetries. The candidates are classified by using a Support Vector Machine-based classifier (SVM) with Histograms of Oriented Gradients (HOG features). Finally, the position of each vehicle is tracked using a Kalman filter and template matching techniques. The proposed system is tested using image data collected in real traffic conditions.

Hierarchical camera auto-calibration for traffic surveillance systems

In this paper, a hierarchical monocular camera auto-calibration method is presented for applications in the framework of intelligent transportation systems (ITS). It is based on vanishing point extraction from common static elements present on the scene, and moving objects as pedestrians and vehicles. This process is very useful to recover metrics from images or applying information of 3D models to estimate 2D pose of targets, making a posterior object detection and tracking more robust to noise and occlusions. Moreover, the algorithm is independent of the position of the camera, and it is able to work with variable pan-tilt-zoom (PTZ) cameras in fully self-adaptive mode. The objective is to obtain the camera parameters without any restriction in terms of constraints or the need of prior knowledge, to deal with most traffic scenarios and possible configurations. The results achieved up to date in real traffic conditions are presented and discussed.

Perception advances in outdoor vehicle detection for automatic cruise control

This paper describes a vehicle detection system based on support vector machine (SVM) and monocular vision. The final goal is to provide vehicle-to-vehicle time gap for automatic cruise control (ACC) applications in the framework of intelligent transportation systems (ITS). The challenge is to use a single camera as input, in order to achieve a low cost final system that meets the requirements needed to undertake serial production in automotive industry. The basic feature of the detected objects are first located in the image using vision and then combined with a SVM-based classifier. An intelligent learning approach is proposed in order to better deal with objects variability, illumination conditions, partial occlusions and rotations. A large database containing thousands of object examples extracted from real road scenes has been created for learning purposes. The classifier is trained using SVM in order to be able to classify vehicles, including trucks. In addition, the vehicle detection system described in this paper provides early detection of passing cars and assigns lane to target vehicles. In the paper, we present and discuss the results achieved up to date in real traffic conditions.

3D Candidate Selection Method for Pedestrian Detection on Non-Planar Roads

This paper describes a stereo-vision-based candidate selection method for pedestrian detection from a moving vehicle. Non-dense 3D maps are computed by using epipolar geometry and a robust correlation process. Non-flat road assumption is used for correcting pitch angle variations. Thus, non obstacle points can be easily removed since they lay on the road. Generic obstacles are selected by using Subtractive Clustering algorithm in a 3D space with an adaptive radius. This clustering technique can be configurable for different types of obstacles. An optimal configuration for pedestrian detection is presented in this work.

Vision-based blind spot detection using optical flow

This paper describes a vision-based system for blind spot detection in intelligent vehicle applications. A camera is mounted in the lateral mirror of a car with the intention of visually detecting cars that can not be perceived by the vehicle driver since they are located in the so-called blind spot. The detection of cars in the blind spot is carried out using computer vision techniques, based on optical flow and data clustering, as described in the following lines.

Vision-based parking assistance system for leaving perpendicular and angle parking lots

Backing-out maneuvers in perpendicular or angle parking lots are one of the most dangerous maneuvers, specially in cases where side parked cars block the driver view of the potential traffic flow. In this paper a new vision-based Advanced Driver Assistance System (ADAS) is proposed to automatically warn the driver in such scenarios. A monocular gray-scale camera is installed at the back-right side of the vehicle. A Finite State Machine (FSM) defined according to three CAN-Bus variables and a manual signal provided by the user is used to handle the activation/deactivation of the detection module. The proposed oncoming traffic detection module computes spatiotemporal images from a set of pre-defined scan-lines which are related to the position of the road. A novel spatio-temporal motion descriptor is proposed (STHOL) accounting the number of lines, their orientation and length of the spatio-temporal images. A Bayesian framework is used to trigger the warning signal using multivariate normal density functions. Experiments are conducted on image data captured from a vehicle parked at different locations of an urban environment, including different lighting conditions. We demonstrate that the proposed approach provides robust results maintaining processing rates close to real-time.

Monocular target detection on transport infrastructures with dynamic and variable environments

This paper describes a target detection system on transport infrastructures, based on monocular vision, for applications in the framework of Intelligent Transportation Systems (ITS). Using structured elements of the image, a vanishing point extraction is proposed to obtain an automatic calibration of the camera, without any prior knowledge. This calibration provides an approximate size of the searched targets (vehicles or pedestrians), improving the performance of the detection steps. After that, a background subtraction method, based on GMM and shadow detection algorithms, is used to segment the image. Next a feature extraction, optical flow analysis and clustering methods are used to track the objects. The algorithm is robust to camera jitter, illumination changes and shadows. Therefore it can work indoor and outdoor, in different conditions and scenarios, and independent of the position of the camera. In the paper, we present and discuss the results achieved up to date in real traffic conditions.