Ignacio Parra - Academia.edu (original) (raw)

Papers by Ignacio Parra

IEEE Access

This paper introduces a novel method of lane-change and lane-keeping detection and prediction of ... more This paper introduces a novel method of lane-change and lane-keeping detection and prediction of surrounding vehicles based on Convolutional Neural Network (CNN) classification approach. Context, interaction, vehicle trajectories, and scene appearance are efficiently combined into a single RGB image that is fed as input for the classification model. Several state-of-the-art classification-CNN models of varying complexity are evaluated to find out the most suitable one in terms of anticipation and prediction. The model has been trained and evaluated using the PREVENTION dataset, a specific dataset oriented to vehicle maneuver and trajectory prediction. The proposed model can be trained and used to detect lane changes as soon as they are observed, and to predict them before the lane change maneuver is initiated. Concurrently, a study on human performance in predicting lane-change maneuvers using visual inputs has been conducted, so as to establish a solid benchmark for comparison. The empirical study reveals that humans are able to detect the 83.9% of lane changes on average 1.66 seconds in advance. The proposed automated maneuver detection model increases anticipation by 0.43 seconds and accuracy by 2.5% compared to human results, while the maneuver prediction model increases anticipation by 1.03 seconds with an accuracy decrease of only 0.5%.

2016 6th International Conference on IT Convergence and Security (ICITCS), 2016

This paper describes an improved stereo vision system for anticipated detection of car-to-pedestr... more This paper describes an improved stereo vision system for anticipated detection of car-to-pedestrian accidents. An improvement of previous versions of the pedestrian dection 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 pedestrian detection system has been applied to collision avoidance and mitigation. Collision avoidance is carried out by means of deceleration strategies, whenever the accident is evitable. Likewise, collision mitigation is accomplished by activating an active hood system. For that purpose, the system has been mounted and tested on two different prototype cars and tested on private circuits using dummies.

In this paper, we present a method for computing velocity using a single camera onboard a road ve... more In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on ego-motion computation. By doing so, cumulative errors inherent to odometry-based systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm. They are detected in the image plane and grouped in couples in order to provide geometrically constrained vectors that make viable the computation of vehicle motion in a sequence of images. The applications of this method can be mainly found in the domains of Robotics and Intelligent Vehicles.

Lecture Notes in Computer Science, 2009

This paper describes a real-time vision-based system that detects vehicles approaching from the r... more 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.

In this paper we present a 6DOF metric SLAM system for outdoor enviroments using a stereo camera,... more In this paper we present a 6DOF metric SLAM system for outdoor enviroments using a stereo camera, mounted next to the rear view mirror, as the only sensor. By means of SLAM the vehicle global position and a sparse map of natural landmarks are both estimated at the same time. The system combines both bearing and depth information using two different types of feature parametrization: inverse depth and 3D. Through this approach near and far features can be mapped, providing orientation and depth information respectively. Natural landmarks are extracted from the image and are stored as 3D or inverse depth points, depending on a depth threshold. At the moment each landmark is initialized, the normal of the patch surface is computed using the information of the stereo pair. In order to improve long-term tracking a 2D warping is done considering the normal vector information of each patch. This Visual SLAM system is focused on the localization of a vehicle in outdoor urban environments and can be fused with other cheap sensors such as GPS, so as to produce accurate estimations of vehicle's localization in a road. Some experimental results under outdoor environments and conclusions are presented.

Lecture Notes in Computer Science, 2007

In this paper, we present a method for computing velocity using a single camera onboard a road ve... more In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on egomotion computation. By doing so, cumulative errors inherent to odometrybased systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm. They are detected in the image plane and grouped in couples in order to provide geometrically constrained vectors that make viable the computation of vehicle motion in a sequence of images. The applications of this method can be mainly found in the domains of Robotics and Intelligent Vehicles.

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper describes a stereo-vision-based candidate selection method for pedestrian detection fr... more 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.

2012 IEEE Intelligent Vehicles Symposium, 2012

In this paper, a real-time free space detection system is presented using a medium-cost lidar sen... more In this paper, a real-time free space detection system is presented using a medium-cost lidar sensor and a low cost camera. The extrinsic relationship between both sensors is obtained after an off-line calibration process. The lidar provides measurements corresponding to 4 horizontal layers with a vertical resolution of 3.2 degrees. These measurements are integrated in time according to the relative motion of the vehicle between consecutive laser scans. A special case is considered here for Spanish speed humps, since these are usually detected as an obstacle. In Spain, speed humps are directly related with raised zebra-crossings so they should have painted white stripes on them. Accordingly the conditions required to detect a speed hump are: detect a slope shape on the road and detect a zebra crossing at the same time. The first condition is evaluated using lidar sensor and the second one using the camera.

2007 IEEE International Symposium on Intelligent Signal Processing, 2007

The goal of this paper is to develop a method This is becoming more and more tractable to impleme... more The goal of this paper is to develop a method This is becoming more and more tractable to implement for estimating the 2D trajectory of a road vehicle using on standard PC-based systems nowadays. However, visual odometry. To do so, the ego-motion of the vehicle there are still open issues that constitute a challenge in relative to the road is computed using a stereo-vision achieving highly robust ego-motion estimation in real traffic system mounted next to the rear view mirror. Feature points are computed using Harris detector. After conditions. These are discussed in the following lines.

IEEE International Symposium on Industrial Electronics, 2005

This paper describes a monocular vision-based Vehicle Recognition System in which the basic compo... more This paper describes a monocular vision-based Vehicle Recognition System in which the basic components of road vehicles are first located in the image and then combined with a SVM-based classifier. The challenge is to use a single camera as input. This poses the problem of vehicle detection and recognition in real, cluttered road images. A distributed learning approach is proposed in order to better deal with vehicle variability, illumination conditions, partial occlusions and rotations. The vehicle searching area in the image is constrained to the limits of the lanes, which are determined by the road lane markings. By doing so, the rate of false positive detections is largely decreased. A large database containing thousands of vehicle examples extracted from real road images has been created for learning purposes. We present and discuss the results achieved up to date.

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2011

Driving inattention is a major factor to highway crashes. The National Highway Traffic Safety Adm... more Driving inattention is a major factor to highway crashes. The National Highway Traffic Safety Administration (NHTSA) estimates that approximately 25% of police-reported crashes involve some form of driving inattention. Increasing use of in-vehicle information systems (IVISs) such as cell phones or GPS navigation systems has exacerbated the problem by introducing additional sources of distraction. Enabling drivers to benefit from IVIS without diminishing safety is an important challenge. In this paper, an automatic distraction monitoring system based on gaze focalization for the assessment of IVISs induced distraction is presented. Driver's gaze focalization is estimated using a non-intrusive vision-based approach. This system has been tested in a naturalistic simulator with more than 15 hours of driving in different scenarios and conditions and 12 different professional drivers. The purpose of this work is, on the one hand, to assess the detection capacity of the monitoring system and, in the other hand, to study drivers reactions to different IVISs. Gathering this information the optimal IVISs location and the way the indications should be delivered to the drivers can be studied to reduce the interference with their driving.

2008 IEEE Intelligent Vehicles Symposium (IV), 2008

In this paper we present an effective system for detecting vehicles in front of a camera-assisted... more In this paper we present an effective system for detecting vehicles in front of a camera-assisted vehicle (preceding vehicles traveling in the same direction and oncoming vehicles traveling in the opposite direction) during night time driving conditions in order to automatically change vehicle head lights between low beams and high beams avoiding glares for the drivers. Accordingly, high beams output will be selected when no other traffic is present and will be turned on low beams when other vehicles are detected. Our system uses a B&W micro-camera mounted in the windshield area and looking at forward of the vehicle. Digital image processing techniques are applied to analyze light sources and to detect vehicles in the images. The algorithm is efficient and able to run in real-time. Some experimental results and conclusions are presented.

Lecture Notes in Computer Science, 2007

This paper describes a vision-based system for blind spot detection in intelligent vehicle applic... more 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.

2007 IEEE International Symposium on Intelligent Signal Processing, 2007

This paper describes a method for tracking the for the towel, are used. In [4] a single Extended ... more This paper describes a method for tracking the for the towel, are used. In [4] a single Extended Particle filter hands/arms of a person performing hand washing. A hand washing (XPF) is used to track multiple and dynamic objects in complex quality assessment system needs to know if the hands are joined environments where a multi-modal distribution represents the or separated, if they are under water, if they are in contact with .l the towel or the tap, and it has to be robust to different lighting conditions, occlusions, reflections and changes in color on the steel In our approach a skin color segmentation process is applied. surface. In the proposed system hands/arms are extracted by using The hands/arms are modeled by using an area based ellipse skin color segmentation. An area based ellipse model is used for fitting method. A single multi-modal distribution is then used in representing each hand/arm. A Particle filter (PF) in combination. .. with a k-means based clustering technique is used for tracking odrt est the positio an orientao n o f both hands/arms. both hands/arms. A supervision algorithm measures the number of That is not the case of the KF which needs two different filters for objects being tracked and the quality of the tracking itself. Finally each one of the hands. The results obtained by PF are analyzed the PF performance is discussed and compared with the standard and compared with those given by KF estimator. Kalman filter (KF) estimator. The remainder of the paper is organized as follows: Section KeVwords-Hand washing, Kalman filter, Particle filter, Skin 1I provides a description of the hands/arms segmentation process detection, Tracking. and the proposed model. PF is described in Section III. The results achieved up to date are presented in Section IV. Finally, conclusions and the description of our future lines of research

2006 IEEE Intelligent Transportation Systems Conference, 2006

This paper describes a comprehensive combination of feature extraction methods for vision-based p... more This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in the framework of Intelligent Tansportation Systems. The basic components of pedestrians are first located in the image and then combined with a SVM-based classifier. This poses the problem of pedestrian detection in real, cluttered road images. Candidate pedestrians are located using a subtractive clustering attention mechanism based on stereo vision. A bycomponents learning approach is proposed in order to better deal with pedestrians variability, illumination conditions, partial occlusions, and rotations. Extensive comparisons have been carried out using different feature extraction methods, as a key to image understanding in real traffic conditions. A database containing thousands of pedestrian samples extracted from real traffic images has been created for learning purposes, either at daytime and nighttime. The results achieved up to date show interesting conclusions that suggest a combination of feature extraction methods as an essential clue for enhanced detection performance.

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper describes a method for estimating the vehicle global position in a network of roads by... more This paper describes a method for estimating the vehicle global position in a network of roads by means of visual odometry. To do so, the ego-motion of the vehicle relative to the road is computed using a stereo-vision system mounted next to the rear view mirror. Feature points are matched between pairs of frames and linked into 3D trajectories. The resolution of the equations of the system at each frame is carried out under the non-linear, photogrametric aproach using RANSAC. This iterative technique enables the formulation of a robust method that can ignore large numbers of outliers as encountered in real traffic scenes. The resulting method is defined as visual odometry and can be used in conjunction with other sensors, such as GPS, to produce accurate estimates of the vehicle global position. The obvious application of the method is to provide on-board driver assistance in navigation tasks, or to provide a means for autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene nor the vehicle motion. We provide examples of estimated vehicle trajectories using the proposed method and discuss the key issues for further improvement.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

In this work a system for traffic-sign detection and classification under different lighting cond... more In this work a system for traffic-sign detection and classification under different lighting conditions is shown. It is intended for circular and triangular signs. The system is composed of three stages: first, detection, using the Hough transform for lines and circumferences from the information of the edges of the image instead of the whole image information; second, tracking, making use of a Kalman filter, which provides the system with memory, and third, classification, using a neural network. Some results are presented, obtained with real images recorded by only one camera placed on board a conventional vehicle, in sunny, cloudy and rainy days, and also at night, in order to show the reliability and robustness of the system with different light conditions. The average processing time is 30 ms per frame, what makes this work a good approach to work in real time conditions.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

In this paper, it is presented an algorithm for processing visual data to obtain relevant informa... more In this paper, it is presented an algorithm for processing visual data to obtain relevant information that will be afterwards used to track the different moving objects in complex indoor environments. In autonomous robots applications, visual detection of the obstacles in a dynamic environment from a mobile platform is a complicated task. The robustness of this process is fundamental in tracking and navigation reliability for autonomous robots. The solution exposed in the document is based on a stereo-vision system; so that 3D information related to each object position in the local environment of the robot is extracted directly form the cameras. In the proposed application, all objects, both dynamic and static, in the local environment of the robot but the structure of the environment itself are considered to be obstacles. With this specification a distinction between building elements (ceiling, walls, columns and so on) and the rest of items in the robot surroundings is needed. Therefore, a classification has to be developed altogether with the detection task. On the other hand, the obtained data can be used to implement a partial reconstruction of the environmental structure that surrounds the robot. All these algorithms explained in detail in the following paragraphs and visual results are also included at the end of the paper.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

This paper describes a stereo-vision-based pedestrian detection system for Intelligent Transporta... more This paper describes a stereo-vision-based pedestrian detection system for Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a SVM-based classifier. Generic obstacles are located using a subtractive clustering attention mechanism based on stereo vision. A by-components learning approach is proposed and different feature extraction methods are tested in order to better deal with pedestrian variability and justify what features are better to be learnt for pedestrian detection. Candidate selection mechanisms usually yield pedestrians with inaccurate bounding boxes. Then a decrease in detection rate takes place if the SVM classifier is trained only with wellfitted pedestrians. Using several off-line databases containing thousands of pedestrians samples the effect of bounding box accuracy is studied. A multi-candidate generation mechanism is also developed in order to enhance the single frame performance, decreasing the number of false positives due to inaccurate bounding boxes.

IEEE Access

This paper introduces a novel method of lane-change and lane-keeping detection and prediction of ... more This paper introduces a novel method of lane-change and lane-keeping detection and prediction of surrounding vehicles based on Convolutional Neural Network (CNN) classification approach. Context, interaction, vehicle trajectories, and scene appearance are efficiently combined into a single RGB image that is fed as input for the classification model. Several state-of-the-art classification-CNN models of varying complexity are evaluated to find out the most suitable one in terms of anticipation and prediction. The model has been trained and evaluated using the PREVENTION dataset, a specific dataset oriented to vehicle maneuver and trajectory prediction. The proposed model can be trained and used to detect lane changes as soon as they are observed, and to predict them before the lane change maneuver is initiated. Concurrently, a study on human performance in predicting lane-change maneuvers using visual inputs has been conducted, so as to establish a solid benchmark for comparison. The empirical study reveals that humans are able to detect the 83.9% of lane changes on average 1.66 seconds in advance. The proposed automated maneuver detection model increases anticipation by 0.43 seconds and accuracy by 2.5% compared to human results, while the maneuver prediction model increases anticipation by 1.03 seconds with an accuracy decrease of only 0.5%.

2016 6th International Conference on IT Convergence and Security (ICITCS), 2016

This paper describes an improved stereo vision system for anticipated detection of car-to-pedestr... more This paper describes an improved stereo vision system for anticipated detection of car-to-pedestrian accidents. An improvement of previous versions of the pedestrian dection 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 pedestrian detection system has been applied to collision avoidance and mitigation. Collision avoidance is carried out by means of deceleration strategies, whenever the accident is evitable. Likewise, collision mitigation is accomplished by activating an active hood system. For that purpose, the system has been mounted and tested on two different prototype cars and tested on private circuits using dummies.

In this paper, we present a method for computing velocity using a single camera onboard a road ve... more In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on ego-motion computation. By doing so, cumulative errors inherent to odometry-based systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm. They are detected in the image plane and grouped in couples in order to provide geometrically constrained vectors that make viable the computation of vehicle motion in a sequence of images. The applications of this method can be mainly found in the domains of Robotics and Intelligent Vehicles.

Lecture Notes in Computer Science, 2009

This paper describes a real-time vision-based system that detects vehicles approaching from the r... more 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.

In this paper we present a 6DOF metric SLAM system for outdoor enviroments using a stereo camera,... more In this paper we present a 6DOF metric SLAM system for outdoor enviroments using a stereo camera, mounted next to the rear view mirror, as the only sensor. By means of SLAM the vehicle global position and a sparse map of natural landmarks are both estimated at the same time. The system combines both bearing and depth information using two different types of feature parametrization: inverse depth and 3D. Through this approach near and far features can be mapped, providing orientation and depth information respectively. Natural landmarks are extracted from the image and are stored as 3D or inverse depth points, depending on a depth threshold. At the moment each landmark is initialized, the normal of the patch surface is computed using the information of the stereo pair. In order to improve long-term tracking a 2D warping is done considering the normal vector information of each patch. This Visual SLAM system is focused on the localization of a vehicle in outdoor urban environments and can be fused with other cheap sensors such as GPS, so as to produce accurate estimations of vehicle's localization in a road. Some experimental results under outdoor environments and conclusions are presented.

Lecture Notes in Computer Science, 2007

In this paper, we present a method for computing velocity using a single camera onboard a road ve... more In this paper, we present a method for computing velocity using a single camera onboard a road vehicle, i.e. an automobile. The use of computer vision provides a reliable method to measure vehicle velocity based on egomotion computation. By doing so, cumulative errors inherent to odometrybased systems can be reduced to some extent. Road lane markings are the basic features used by the algorithm. They are detected in the image plane and grouped in couples in order to provide geometrically constrained vectors that make viable the computation of vehicle motion in a sequence of images. The applications of this method can be mainly found in the domains of Robotics and Intelligent Vehicles.

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper describes a stereo-vision-based candidate selection method for pedestrian detection fr... more 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.

2012 IEEE Intelligent Vehicles Symposium, 2012

In this paper, a real-time free space detection system is presented using a medium-cost lidar sen... more In this paper, a real-time free space detection system is presented using a medium-cost lidar sensor and a low cost camera. The extrinsic relationship between both sensors is obtained after an off-line calibration process. The lidar provides measurements corresponding to 4 horizontal layers with a vertical resolution of 3.2 degrees. These measurements are integrated in time according to the relative motion of the vehicle between consecutive laser scans. A special case is considered here for Spanish speed humps, since these are usually detected as an obstacle. In Spain, speed humps are directly related with raised zebra-crossings so they should have painted white stripes on them. Accordingly the conditions required to detect a speed hump are: detect a slope shape on the road and detect a zebra crossing at the same time. The first condition is evaluated using lidar sensor and the second one using the camera.

2007 IEEE International Symposium on Intelligent Signal Processing, 2007

The goal of this paper is to develop a method This is becoming more and more tractable to impleme... more The goal of this paper is to develop a method This is becoming more and more tractable to implement for estimating the 2D trajectory of a road vehicle using on standard PC-based systems nowadays. However, visual odometry. To do so, the ego-motion of the vehicle there are still open issues that constitute a challenge in relative to the road is computed using a stereo-vision achieving highly robust ego-motion estimation in real traffic system mounted next to the rear view mirror. Feature points are computed using Harris detector. After conditions. These are discussed in the following lines.

IEEE International Symposium on Industrial Electronics, 2005

This paper describes a monocular vision-based Vehicle Recognition System in which the basic compo... more This paper describes a monocular vision-based Vehicle Recognition System in which the basic components of road vehicles are first located in the image and then combined with a SVM-based classifier. The challenge is to use a single camera as input. This poses the problem of vehicle detection and recognition in real, cluttered road images. A distributed learning approach is proposed in order to better deal with vehicle variability, illumination conditions, partial occlusions and rotations. The vehicle searching area in the image is constrained to the limits of the lanes, which are determined by the road lane markings. By doing so, the rate of false positive detections is largely decreased. A large database containing thousands of vehicle examples extracted from real road images has been created for learning purposes. We present and discuss the results achieved up to date.

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2011

Driving inattention is a major factor to highway crashes. The National Highway Traffic Safety Adm... more Driving inattention is a major factor to highway crashes. The National Highway Traffic Safety Administration (NHTSA) estimates that approximately 25% of police-reported crashes involve some form of driving inattention. Increasing use of in-vehicle information systems (IVISs) such as cell phones or GPS navigation systems has exacerbated the problem by introducing additional sources of distraction. Enabling drivers to benefit from IVIS without diminishing safety is an important challenge. In this paper, an automatic distraction monitoring system based on gaze focalization for the assessment of IVISs induced distraction is presented. Driver's gaze focalization is estimated using a non-intrusive vision-based approach. This system has been tested in a naturalistic simulator with more than 15 hours of driving in different scenarios and conditions and 12 different professional drivers. The purpose of this work is, on the one hand, to assess the detection capacity of the monitoring system and, in the other hand, to study drivers reactions to different IVISs. Gathering this information the optimal IVISs location and the way the indications should be delivered to the drivers can be studied to reduce the interference with their driving.

2008 IEEE Intelligent Vehicles Symposium (IV), 2008

In this paper we present an effective system for detecting vehicles in front of a camera-assisted... more In this paper we present an effective system for detecting vehicles in front of a camera-assisted vehicle (preceding vehicles traveling in the same direction and oncoming vehicles traveling in the opposite direction) during night time driving conditions in order to automatically change vehicle head lights between low beams and high beams avoiding glares for the drivers. Accordingly, high beams output will be selected when no other traffic is present and will be turned on low beams when other vehicles are detected. Our system uses a B&W micro-camera mounted in the windshield area and looking at forward of the vehicle. Digital image processing techniques are applied to analyze light sources and to detect vehicles in the images. The algorithm is efficient and able to run in real-time. Some experimental results and conclusions are presented.

Lecture Notes in Computer Science, 2007

This paper describes a vision-based system for blind spot detection in intelligent vehicle applic... more 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.

2007 IEEE International Symposium on Intelligent Signal Processing, 2007

This paper describes a method for tracking the for the towel, are used. In [4] a single Extended ... more This paper describes a method for tracking the for the towel, are used. In [4] a single Extended Particle filter hands/arms of a person performing hand washing. A hand washing (XPF) is used to track multiple and dynamic objects in complex quality assessment system needs to know if the hands are joined environments where a multi-modal distribution represents the or separated, if they are under water, if they are in contact with .l the towel or the tap, and it has to be robust to different lighting conditions, occlusions, reflections and changes in color on the steel In our approach a skin color segmentation process is applied. surface. In the proposed system hands/arms are extracted by using The hands/arms are modeled by using an area based ellipse skin color segmentation. An area based ellipse model is used for fitting method. A single multi-modal distribution is then used in representing each hand/arm. A Particle filter (PF) in combination. .. with a k-means based clustering technique is used for tracking odrt est the positio an orientao n o f both hands/arms. both hands/arms. A supervision algorithm measures the number of That is not the case of the KF which needs two different filters for objects being tracked and the quality of the tracking itself. Finally each one of the hands. The results obtained by PF are analyzed the PF performance is discussed and compared with the standard and compared with those given by KF estimator. Kalman filter (KF) estimator. The remainder of the paper is organized as follows: Section KeVwords-Hand washing, Kalman filter, Particle filter, Skin 1I provides a description of the hands/arms segmentation process detection, Tracking. and the proposed model. PF is described in Section III. The results achieved up to date are presented in Section IV. Finally, conclusions and the description of our future lines of research

2006 IEEE Intelligent Transportation Systems Conference, 2006

This paper describes a comprehensive combination of feature extraction methods for vision-based p... more This paper describes a comprehensive combination of feature extraction methods for vision-based pedestrian detection in the framework of Intelligent Tansportation Systems. The basic components of pedestrians are first located in the image and then combined with a SVM-based classifier. This poses the problem of pedestrian detection in real, cluttered road images. Candidate pedestrians are located using a subtractive clustering attention mechanism based on stereo vision. A bycomponents learning approach is proposed in order to better deal with pedestrians variability, illumination conditions, partial occlusions, and rotations. Extensive comparisons have been carried out using different feature extraction methods, as a key to image understanding in real traffic conditions. A database containing thousands of pedestrian samples extracted from real traffic images has been created for learning purposes, either at daytime and nighttime. The results achieved up to date show interesting conclusions that suggest a combination of feature extraction methods as an essential clue for enhanced detection performance.

2007 IEEE Intelligent Vehicles Symposium, 2007

This paper describes a method for estimating the vehicle global position in a network of roads by... more This paper describes a method for estimating the vehicle global position in a network of roads by means of visual odometry. To do so, the ego-motion of the vehicle relative to the road is computed using a stereo-vision system mounted next to the rear view mirror. Feature points are matched between pairs of frames and linked into 3D trajectories. The resolution of the equations of the system at each frame is carried out under the non-linear, photogrametric aproach using RANSAC. This iterative technique enables the formulation of a robust method that can ignore large numbers of outliers as encountered in real traffic scenes. The resulting method is defined as visual odometry and can be used in conjunction with other sensors, such as GPS, to produce accurate estimates of the vehicle global position. The obvious application of the method is to provide on-board driver assistance in navigation tasks, or to provide a means for autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene nor the vehicle motion. We provide examples of estimated vehicle trajectories using the proposed method and discuss the key issues for further improvement.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

In this work a system for traffic-sign detection and classification under different lighting cond... more In this work a system for traffic-sign detection and classification under different lighting conditions is shown. It is intended for circular and triangular signs. The system is composed of three stages: first, detection, using the Hough transform for lines and circumferences from the information of the edges of the image instead of the whole image information; second, tracking, making use of a Kalman filter, which provides the system with memory, and third, classification, using a neural network. Some results are presented, obtained with real images recorded by only one camera placed on board a conventional vehicle, in sunny, cloudy and rainy days, and also at night, in order to show the reliability and robustness of the system with different light conditions. The average processing time is 30 ms per frame, what makes this work a good approach to work in real time conditions.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

In this paper, it is presented an algorithm for processing visual data to obtain relevant informa... more In this paper, it is presented an algorithm for processing visual data to obtain relevant information that will be afterwards used to track the different moving objects in complex indoor environments. In autonomous robots applications, visual detection of the obstacles in a dynamic environment from a mobile platform is a complicated task. The robustness of this process is fundamental in tracking and navigation reliability for autonomous robots. The solution exposed in the document is based on a stereo-vision system; so that 3D information related to each object position in the local environment of the robot is extracted directly form the cameras. In the proposed application, all objects, both dynamic and static, in the local environment of the robot but the structure of the environment itself are considered to be obstacles. With this specification a distinction between building elements (ceiling, walls, columns and so on) and the rest of items in the robot surroundings is needed. Therefore, a classification has to be developed altogether with the detection task. On the other hand, the obtained data can be used to implement a partial reconstruction of the environmental structure that surrounds the robot. All these algorithms explained in detail in the following paragraphs and visual results are also included at the end of the paper.

IECON 2006 - 32nd Annual Conference on IEEE Industrial Electronics, 2006

This paper describes a stereo-vision-based pedestrian detection system for Intelligent Transporta... more This paper describes a stereo-vision-based pedestrian detection system for Intelligent Transportation Systems. The basic components of pedestrians are first located in the image and then combined with a SVM-based classifier. Generic obstacles are located using a subtractive clustering attention mechanism based on stereo vision. A by-components learning approach is proposed and different feature extraction methods are tested in order to better deal with pedestrian variability and justify what features are better to be learnt for pedestrian detection. Candidate selection mechanisms usually yield pedestrians with inaccurate bounding boxes. Then a decrease in detection rate takes place if the SVM classifier is trained only with wellfitted pedestrians. Using several off-line databases containing thousands of pedestrians samples the effect of bounding box accuracy is studied. A multi-candidate generation mechanism is also developed in order to enhance the single frame performance, decreasing the number of false positives due to inaccurate bounding boxes.