Mirko Felisa - Academia.edu (original) (raw)

Papers by Mirko Felisa

Research paper thumbnail of Studio e applicazione di algoritmi stereoscopici per la ricostruzione tridimensionale in ambiente automotive

Research paper thumbnail of Incremental disparity space image computation for automotive applications

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009

Generating a depth map from a pair of stereo images is a challenging task, which is often further... more Generating a depth map from a pair of stereo images is a challenging task, which is often further complicated by the additional restrictions imposed by the target application; in the automotive field, for example, real-time environment reconstruction is essential for safety and autonomous navigation systems, thus requiring reduced processing times, often at the expense of a somewhat limited degree of accuracy in the results. Nevertheless, a-priori knowledge on the intended use of the algorithm can also be exploited to improve its performance, both in terms of precision and computational burden. This paper presents three different approaches to incremental Disparity Space Image (DSI) computation, which leverage the properties of a stereo-vision system installed on a vehicle to produce accurate depth maps at sustained frame rates on commodity hardware.

Research paper thumbnail of Robust monocular lane detection in urban environments

Intelligent Vehicles Symposium (IV), 2010 …, 2010

An effective lane detection algorithm is a basic, yet fundamental component of both autonomous na... more An effective lane detection algorithm is a basic, yet fundamental component of both autonomous navigation and advanced road safety systems; this paper presents an approach that produces reliable results exploiting a robust polyline matching technique. The proposed solution has been designed from the ground up so that only very limited hardware resources are required: just one camera is used, and the processing is fast enough to be compatible with mainstream DSP units.

Research paper thumbnail of VisLab's Experience on Autonomous Driving in Extreme Environments

... asi2 CACHED: Download as a PDF. by Luglio Luglio , Roma Italia , Massimo Bertozzi , Luca Bomb... more ... asi2 CACHED: Download as a PDF. by Luglio Luglio , Roma Italia , Massimo Bertozzi , Luca Bombini , Alberto Broggi , Michele Buzzoni , Elena Cardarelli , Stefano Cattani , Pietro Cerri , Mirko Felisa , Rean Isabella Fedriga , Luca Gatti , Paolo Grisleri , Luca Mazzei , Pier Paolo ...

Research paper thumbnail of Low Cost 3D Vision: Performance analysis of stereo reconstruction algorithms

Autonomous navigation features, including fully autonomous driving, require 360 degrees perceptio... more Autonomous navigation features, including fully autonomous driving, require 360 degrees perception capabilities in a variety of conditions, in order to timely react to a constantly changing scenario. The vast majority of currently available unmanned vehicles use complex sets of active sensors, installed and wired with limited constraints on their position and size to map the environment. An alternative, lower cost and more integrated solution is to exploit a stereo camera setup to perform dense 3D reconstruction of the vehicle surroundings. This report will provide a detailed analysis of a number of algorithms used to that end, and identify some possible strategies to improve their performance level.

Research paper thumbnail of Sistema per il Controllo di Porte Automatiche

Research paper thumbnail of A Trip from Italy to China using Autonomous Vehicles: Behavior and Testing

This paper describes behavior and testing of the vehicles set up by VisLab to cover, in autonomou... more This paper describes behavior and testing of the vehicles set up by VisLab to cover, in autonomous mode, a long 13.000 km trip from Italy to China, passing through Moscow. The paper, begins with a short description of the hardware and focuses on the vehicle behavior, what kind of situations is able to negotiate and how they are managed. A description of how the system has been tested and how it performs on a test track concludes the paper. The journey started on July 20 from Milan. At the time of writing, the first 10 days of result are positive. A live video demonstration will be shown at the conference talk.

Research paper thumbnail of Combining camera systems for human shape detection

Research paper thumbnail of Test-bed for Unified Perception & Decision Architecture

Advanced Microsystems for Automotive Applications 2009, 2009

This paper presents the test-bed that will be developed for a Unified Perception & Decision Archi... more This paper presents the test-bed that will be developed for a Unified Perception & Decision Architecture (UPDA). Due to the increasing demand of ADAS systems to be mounted on cars, it is more and more important to develop a unified architecture that can communicate and share information between these systems. This is the aim of an ERC-founded project and to develop and test such architecture a car has been set up with many different sensors.

Research paper thumbnail of 3DV — An embedded, dense stereovision-based depth mapping system

2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014

ABSTRACT This paper describes the architecture and hardware implementation of an embedded, low-co... more ABSTRACT This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an initial image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

Research paper thumbnail of Vision Technologies for Intelligent Vehicles

Lecture Notes in Computer Science, 2007

This paper surveys the different technologies involved in the development of computer vision appl... more This paper surveys the different technologies involved in the development of computer vision applications for Intelligent Vehicles derived from the 15 year experience of VisLab. Some illustrative examples are also discussed.

Research paper thumbnail of Low-level Pedestrian Detection by means of Visible and Far Infra-red Tetra-vision

2006 IEEE Intelligent Vehicles Symposium, 2006

This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by the m... more This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by the means of the simultaneous use of one far infra-red and one visible cameras stereo pairs. The main idea is to exploit both the advantages of far infra-red and visible cameras trying at the same time to benefit from the use of each system. Initially, the two stereo flows are independently processed, then the results are fused together. The final result of this low-level processing is a list of obstacles that have a shape and a size compatible with the presence of a potential pedestrian. In addition, the system is able to remove the background from the detected obstacles to simplify a possible further high level processing.

Research paper thumbnail of A pedestrian detector using histograms of oriented gradients and a Support Vector Machine classifier

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2007

This paper details filtering subsystem for a tetravision based pedestrian detection system. The c... more This paper details filtering subsystem for a tetravision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. This list is furtherly refined using symmetry-based assumptions. Then, this results is fed to a number of independent validators that evaluate the presence of human shapes inside the areas of attention.

Research paper thumbnail of Stereo obstacle detection in challenging environments: The VIAC experience

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011

Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has ... more Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has spurred a lot of research over the years, especially in the field of vehicular robotics. The information provided by this class of algorithms is used both in driving assistance systems and in autonomous vehicles, so the quality of the results and the processing times become critical, as detection failures or delays can have serious consequences. The obstacle detection system presented in this paper has been extensively tested during VIAC, the VisLab Intercontinental Autonomous Challenge [1], [2], which has offered a unique chance to face a number of different scenarios along the roads of two continents, in a variety of conditions; data collected during the expedition has also become a reference benchmark for further algorithm improvements.

Research paper thumbnail of Performance analysis of stereo reconstruction algorithms

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), 2013

ABSTRACT Environment mapping is one of the most critical tasks in the development of driving assi... more ABSTRACT Environment mapping is one of the most critical tasks in the development of driving assistance systems and stereo vision has been widely used to accomplish it. However, there are very few datasets that allow assessing the performance of a specific method in a real world application. Most datasets have been created in controlled conditions, thus neglecting scenarios that are impossible to reproduce in a laboratory. In this paper, we present the results of the evaluation of three different dense reconstruction algorithm implementations using a number of well-known strategies that represent different trade-offs in terms of cost, set up time and accuracy. In our tests, we evaluated two variants of the Semi-Global Matching algorithm, and the Efficient Large-Scale Stereo Matching method, as well as different combinations of additional filters in order to assess their influence on the final behavior of the algorithms.

Research paper thumbnail of Multi Stereo-Based Pedestrian Detection by Daylight and Far-Infrared Cameras

Augmented Vision Perception in Infrared, 2009

This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by means... more This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by means of the simultaneous use of two far infrared and visible cameras stereo pairs. The main idea is to exploit the advantages of both far infrared and visible cameras to develop a system that combines the advantages of using far infrared or daylight technologies. Different approaches are used to process the two stereo flows in an independent fashion to produce a list of areas of attention that potentially contain pedestrians. Then, four different following approaches are used to refine and filter this list and to validate the presence of a pedestrian. Preliminary results show that the combined use of two vision systems as well as the use of different and independent validation steps enable the system to effectively detect pedestrians in different conditions of illumination and background.

Research paper thumbnail of VIAC: An out of ordinary experiment

2011 IEEE Intelligent Vehicles Symposium (IV), 2011

This paper presents the preliminary results of VIAC, the VisLab Intercontinental Autonomous Chall... more This paper presents the preliminary results of VIAC, the VisLab Intercontinental Autonomous Challenge, a test of autonomous driving along an unknown route from Italy to China. It took 3 months to run the entire test; all data have been logged, including all data generated by the sensors, vehicle data, and GPS info. This huge amount of information has been packed during the trip, compressed, and transferred back to Parma for further processing. This data is now ready for a deep analysis of the various systems performance, with the aim of virtually running the whole trip multiple times with improved versions of the software.

Research paper thumbnail of Pedestrian Validation in Infrared Images by Means of Active Contours and Neural Networks

EURASIP Journal on Advances in Signal Processing, 2010

This paper presents two different modules for the validation of human shape presence in far-infra... more This paper presents two different modules for the validation of human shape presence in far-infrared images. These modules are part of a more complex system aimed at the detection of pedestrians by means of the simultaneous use of two stereo vision systems in both far-infrared and daylight domains. The first module detects the presence of a human shape in a list of areas of attention using active contours to detect the object shape and evaluating the results by means of a neural network. The second validation subsystem directly exploits a neural network for each area of attention in the far-infrared images and produces a list of votes.

Research paper thumbnail of Pedestrian detection by means of far-infrared stereo vision

Computer Vision and Image Understanding, 2007

This article presents a stereo system for the detection of pedestrians using far-infrared cameras... more This article presents a stereo system for the detection of pedestrians using far-infrared cameras. Since pedestrian detection in far-infrared images can be difficult in some environmental conditions, the system exploits three different detection approaches: warm area detection, edge-based detection, and disparity computation. A final validation process is performed using head morphological and thermal characteristics. Currently, neither temporal correlation, nor motion cues are used in this processing.

Research paper thumbnail of VIDA–VisLab Intelligent Driver Assistant

Originating from specific requirements of future Advanced Driving Assistance Systems, the VIDA sy... more Originating from specific requirements of future Advanced Driving Assistance Systems, the VIDA system offers both basic functionalities and advanced applications. Functionalities such as Lane Departure Warning and Safety Distance Warning are provided by the basic VIDA-W. On the same hardware platform and with the same sensing device, additional features can be added as plug-ins directly interfaced to the vehicle control network, offering vision-based Stop-and-Go, ACC, and other intelligent functions.

Research paper thumbnail of Studio e applicazione di algoritmi stereoscopici per la ricostruzione tridimensionale in ambiente automotive

Research paper thumbnail of Incremental disparity space image computation for automotive applications

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009

Generating a depth map from a pair of stereo images is a challenging task, which is often further... more Generating a depth map from a pair of stereo images is a challenging task, which is often further complicated by the additional restrictions imposed by the target application; in the automotive field, for example, real-time environment reconstruction is essential for safety and autonomous navigation systems, thus requiring reduced processing times, often at the expense of a somewhat limited degree of accuracy in the results. Nevertheless, a-priori knowledge on the intended use of the algorithm can also be exploited to improve its performance, both in terms of precision and computational burden. This paper presents three different approaches to incremental Disparity Space Image (DSI) computation, which leverage the properties of a stereo-vision system installed on a vehicle to produce accurate depth maps at sustained frame rates on commodity hardware.

Research paper thumbnail of Robust monocular lane detection in urban environments

Intelligent Vehicles Symposium (IV), 2010 …, 2010

An effective lane detection algorithm is a basic, yet fundamental component of both autonomous na... more An effective lane detection algorithm is a basic, yet fundamental component of both autonomous navigation and advanced road safety systems; this paper presents an approach that produces reliable results exploiting a robust polyline matching technique. The proposed solution has been designed from the ground up so that only very limited hardware resources are required: just one camera is used, and the processing is fast enough to be compatible with mainstream DSP units.

Research paper thumbnail of VisLab's Experience on Autonomous Driving in Extreme Environments

... asi2 CACHED: Download as a PDF. by Luglio Luglio , Roma Italia , Massimo Bertozzi , Luca Bomb... more ... asi2 CACHED: Download as a PDF. by Luglio Luglio , Roma Italia , Massimo Bertozzi , Luca Bombini , Alberto Broggi , Michele Buzzoni , Elena Cardarelli , Stefano Cattani , Pietro Cerri , Mirko Felisa , Rean Isabella Fedriga , Luca Gatti , Paolo Grisleri , Luca Mazzei , Pier Paolo ...

Research paper thumbnail of Low Cost 3D Vision: Performance analysis of stereo reconstruction algorithms

Autonomous navigation features, including fully autonomous driving, require 360 degrees perceptio... more Autonomous navigation features, including fully autonomous driving, require 360 degrees perception capabilities in a variety of conditions, in order to timely react to a constantly changing scenario. The vast majority of currently available unmanned vehicles use complex sets of active sensors, installed and wired with limited constraints on their position and size to map the environment. An alternative, lower cost and more integrated solution is to exploit a stereo camera setup to perform dense 3D reconstruction of the vehicle surroundings. This report will provide a detailed analysis of a number of algorithms used to that end, and identify some possible strategies to improve their performance level.

Research paper thumbnail of Sistema per il Controllo di Porte Automatiche

Research paper thumbnail of A Trip from Italy to China using Autonomous Vehicles: Behavior and Testing

This paper describes behavior and testing of the vehicles set up by VisLab to cover, in autonomou... more This paper describes behavior and testing of the vehicles set up by VisLab to cover, in autonomous mode, a long 13.000 km trip from Italy to China, passing through Moscow. The paper, begins with a short description of the hardware and focuses on the vehicle behavior, what kind of situations is able to negotiate and how they are managed. A description of how the system has been tested and how it performs on a test track concludes the paper. The journey started on July 20 from Milan. At the time of writing, the first 10 days of result are positive. A live video demonstration will be shown at the conference talk.

Research paper thumbnail of Combining camera systems for human shape detection

Research paper thumbnail of Test-bed for Unified Perception & Decision Architecture

Advanced Microsystems for Automotive Applications 2009, 2009

This paper presents the test-bed that will be developed for a Unified Perception & Decision Archi... more This paper presents the test-bed that will be developed for a Unified Perception & Decision Architecture (UPDA). Due to the increasing demand of ADAS systems to be mounted on cars, it is more and more important to develop a unified architecture that can communicate and share information between these systems. This is the aim of an ERC-founded project and to develop and test such architecture a car has been set up with many different sensors.

Research paper thumbnail of 3DV — An embedded, dense stereovision-based depth mapping system

2014 IEEE Intelligent Vehicles Symposium Proceedings, 2014

ABSTRACT This paper describes the architecture and hardware implementation of an embedded, low-co... more ABSTRACT This paper describes the architecture and hardware implementation of an embedded, low-cost and low-power dense stereo reconstruction system, running at 30 fps at VGA resolution. The processing pipeline includes an initial image rectification stage, a cost generation unit based on the non-parametric census transform, a state-of-the-art Semi-Global cost optimization stage, and a final minimization and noise suppression step. The hardware implementation is based on a Xilinx ZynqTM System-on-Chip, which besides the FPGA provides a physical dual-core ARM CPU, which is exploited for control and to deliver output over the integrated Gigabit Ethernet connection.

Research paper thumbnail of Vision Technologies for Intelligent Vehicles

Lecture Notes in Computer Science, 2007

This paper surveys the different technologies involved in the development of computer vision appl... more This paper surveys the different technologies involved in the development of computer vision applications for Intelligent Vehicles derived from the 15 year experience of VisLab. Some illustrative examples are also discussed.

Research paper thumbnail of Low-level Pedestrian Detection by means of Visible and Far Infra-red Tetra-vision

2006 IEEE Intelligent Vehicles Symposium, 2006

This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by the m... more This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by the means of the simultaneous use of one far infra-red and one visible cameras stereo pairs. The main idea is to exploit both the advantages of far infra-red and visible cameras trying at the same time to benefit from the use of each system. Initially, the two stereo flows are independently processed, then the results are fused together. The final result of this low-level processing is a list of obstacles that have a shape and a size compatible with the presence of a potential pedestrian. In addition, the system is able to remove the background from the detected obstacles to simplify a possible further high level processing.

Research paper thumbnail of A pedestrian detector using histograms of oriented gradients and a Support Vector Machine classifier

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2007

This paper details filtering subsystem for a tetravision based pedestrian detection system. The c... more This paper details filtering subsystem for a tetravision based pedestrian detection system. The complete system is based on the use of both visible and far infrared cameras; in an initial phase it produces a list of areas of attention in the images which can contain pedestrians. This list is furtherly refined using symmetry-based assumptions. Then, this results is fed to a number of independent validators that evaluate the presence of human shapes inside the areas of attention.

Research paper thumbnail of Stereo obstacle detection in challenging environments: The VIAC experience

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011

Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has ... more Obstacle detection by means of stereo-vision is a fundamental task in computer vision, which has spurred a lot of research over the years, especially in the field of vehicular robotics. The information provided by this class of algorithms is used both in driving assistance systems and in autonomous vehicles, so the quality of the results and the processing times become critical, as detection failures or delays can have serious consequences. The obstacle detection system presented in this paper has been extensively tested during VIAC, the VisLab Intercontinental Autonomous Challenge [1], [2], which has offered a unique chance to face a number of different scenarios along the roads of two continents, in a variety of conditions; data collected during the expedition has also become a reference benchmark for further algorithm improvements.

Research paper thumbnail of Performance analysis of stereo reconstruction algorithms

16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013), 2013

ABSTRACT Environment mapping is one of the most critical tasks in the development of driving assi... more ABSTRACT Environment mapping is one of the most critical tasks in the development of driving assistance systems and stereo vision has been widely used to accomplish it. However, there are very few datasets that allow assessing the performance of a specific method in a real world application. Most datasets have been created in controlled conditions, thus neglecting scenarios that are impossible to reproduce in a laboratory. In this paper, we present the results of the evaluation of three different dense reconstruction algorithm implementations using a number of well-known strategies that represent different trade-offs in terms of cost, set up time and accuracy. In our tests, we evaluated two variants of the Semi-Global Matching algorithm, and the Efficient Large-Scale Stereo Matching method, as well as different combinations of additional filters in order to assess their influence on the final behavior of the algorithms.

Research paper thumbnail of Multi Stereo-Based Pedestrian Detection by Daylight and Far-Infrared Cameras

Augmented Vision Perception in Infrared, 2009

This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by means... more This article presents a tetra-vision (4 cameras) system for the detection of pedestrians by means of the simultaneous use of two far infrared and visible cameras stereo pairs. The main idea is to exploit the advantages of both far infrared and visible cameras to develop a system that combines the advantages of using far infrared or daylight technologies. Different approaches are used to process the two stereo flows in an independent fashion to produce a list of areas of attention that potentially contain pedestrians. Then, four different following approaches are used to refine and filter this list and to validate the presence of a pedestrian. Preliminary results show that the combined use of two vision systems as well as the use of different and independent validation steps enable the system to effectively detect pedestrians in different conditions of illumination and background.

Research paper thumbnail of VIAC: An out of ordinary experiment

2011 IEEE Intelligent Vehicles Symposium (IV), 2011

This paper presents the preliminary results of VIAC, the VisLab Intercontinental Autonomous Chall... more This paper presents the preliminary results of VIAC, the VisLab Intercontinental Autonomous Challenge, a test of autonomous driving along an unknown route from Italy to China. It took 3 months to run the entire test; all data have been logged, including all data generated by the sensors, vehicle data, and GPS info. This huge amount of information has been packed during the trip, compressed, and transferred back to Parma for further processing. This data is now ready for a deep analysis of the various systems performance, with the aim of virtually running the whole trip multiple times with improved versions of the software.

Research paper thumbnail of Pedestrian Validation in Infrared Images by Means of Active Contours and Neural Networks

EURASIP Journal on Advances in Signal Processing, 2010

This paper presents two different modules for the validation of human shape presence in far-infra... more This paper presents two different modules for the validation of human shape presence in far-infrared images. These modules are part of a more complex system aimed at the detection of pedestrians by means of the simultaneous use of two stereo vision systems in both far-infrared and daylight domains. The first module detects the presence of a human shape in a list of areas of attention using active contours to detect the object shape and evaluating the results by means of a neural network. The second validation subsystem directly exploits a neural network for each area of attention in the far-infrared images and produces a list of votes.

Research paper thumbnail of Pedestrian detection by means of far-infrared stereo vision

Computer Vision and Image Understanding, 2007

This article presents a stereo system for the detection of pedestrians using far-infrared cameras... more This article presents a stereo system for the detection of pedestrians using far-infrared cameras. Since pedestrian detection in far-infrared images can be difficult in some environmental conditions, the system exploits three different detection approaches: warm area detection, edge-based detection, and disparity computation. A final validation process is performed using head morphological and thermal characteristics. Currently, neither temporal correlation, nor motion cues are used in this processing.

Research paper thumbnail of VIDA–VisLab Intelligent Driver Assistant

Originating from specific requirements of future Advanced Driving Assistance Systems, the VIDA sy... more Originating from specific requirements of future Advanced Driving Assistance Systems, the VIDA system offers both basic functionalities and advanced applications. Functionalities such as Lane Departure Warning and Safety Distance Warning are provided by the basic VIDA-W. On the same hardware platform and with the same sensing device, additional features can be added as plug-ins directly interfaced to the vehicle control network, offering vision-based Stop-and-Go, ACC, and other intelligent functions.