ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies bo... more ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies both central and non-central absolute and relative camera pose computation algorithms within a single library. Each problem type comes with minimal and non-minimal closed-form solvers, as well as non-linear iterative optimization and robust sample consensus methods. OpenGV therefore contains an unprecedented level of com- pleteness with regard to calibrated geometric vision algorithms, and it is the first library with a dedicated focus on a unified real-time usage of non-central multi-camera systems, which are increasingly popular in robotics and in the automotive industry. This paper introduces OpenGV’s flexible interface and abstraction for multi-camera systems, and outlines the performance of all contained algorithms. It is our hope that the introduction of this open-source platform will motivate people to use it and potentially also include more algorithms, which would further contribute to the general accessibility of geometric vision algorithms, and build a common playground for the fair comparison of different solutions.
The Journal of the Acoustical Society of America, Nov 1, 2008
This paper presents a mathematical model for sound localization in space using two-microphone dev... more This paper presents a mathematical model for sound localization in space using two-microphone devices that possess at least two degrees of freedom. It proves a series of theorems and lemmas that are based on time difference of arrival measurements and movements of the interaural axis, forming a powerful instrument for practical robot applications. For instance, it shows that a single determined rotation of the interaural axis is sufficient to exactly yield the azimuth or the elevation of an immobile sound source in the far field, independently of microphone spacing and the speed of sound and hence of the surrounding medium. It proves that at any moment the knowledge of one value determines the magnitude of the other, with the restriction that the sign of the second value is undefined, which means that, depending on the rotation, either the back-front or the up-down ambiguity is kept unsolved. This paper also shows that parallax motion unlocks essential information about the distance and the Cartesian coordinates of the sound source. Shifting the microphone system sideways fixes the distance and the coordinate on the interaural axis. Combining rotation and translation movements completely solves the localization problem. In order to illustrate the efficacy of the model, this paper presents experiments with a low cost robot developer kit during which the azimuth, the elevation, and the distance of continuous sound sources are determined at a precision of 10 degrees and 0.5 m, respectively. Achieving this performance with low power material demonstrates how easily the model can be implemented into any robotic system.
2014 IEEE International Conference on Robotics and Automation (ICRA), 2014
ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies bo... more ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies both central and non-central absolute and relative camera pose computation algorithms within a single library. Each problem type comes with minimal and non-minimal closed-form solvers, as well as non-linear iterative optimization and robust sample consensus methods. OpenGV therefore contains an unprecedented level of com- pleteness with regard to calibrated geometric vision algorithms, and it is the first library with a dedicated focus on a unified real-time usage of non-central multi-camera systems, which are increasingly popular in robotics and in the automotive industry. This paper introduces OpenGV’s flexible interface and abstraction for multi-camera systems, and outlines the performance of all contained algorithms. It is our hope that the introduction of this open-source platform will motivate people to use it and potentially also include more algorithms, which would further contribute to the general accessibility of geometric vision algorithms, and build a common playground for the fair comparison of different solutions.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
ABSTRACT This work presents a method for estimating the egomotion of an aerial vehicle in challen... more ABSTRACT This work presents a method for estimating the egomotion of an aerial vehicle in challenging industrial environments. It combines binocular visual and inertial cues in a tightly-coupled fashion and operates in real time on an embedded platform. An extended Kalman filter fuses measurements and makes motion estimation rely more on inertial data if visual feature constellation is degenerate. Errors in roll and pitch are bounded implicitly by the gravity vector. Inertial sensors are used for efficient outlier detection and enable operation in poorly and repetitively textured environments. We demonstrate robustness and accuracy in an industrial scenario as well as in general indoor environments. The former is accompanied by a detailed performance evaluation supported with ground truth measurements from an external tracking system.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
The objective of this paper is the full 6D relative localization of mobile devices, and direct ro... more The objective of this paper is the full 6D relative localization of mobile devices, and direct robot-robot local- ization in particular. We present a novel relative localization system that consists of two complementary modules: a monoc- ular vision module and a target module with four active or passive markers. The core localization algorithm running on the modules determines the marker
The Journal of the Acoustical Society of America, 2008
This paper presents a mathematical model for sound localization in space using two-microphone dev... more This paper presents a mathematical model for sound localization in space using two-microphone devices that possess at least two degrees of freedom. It proves a series of theorems and lemmas that are based on time difference of arrival measurements and movements of the interaural axis, forming a powerful instrument for practical robot applications. For instance, it shows that a single determined rotation of the interaural axis is sufficient to exactly yield the azimuth or the elevation of an immobile sound source in the far field, independently of microphone spacing and the speed of sound and hence of the surrounding medium. It proves that at any moment the knowledge of one value determines the magnitude of the other, with the restriction that the sign of the second value is undefined, which means that, depending on the rotation, either the back-front or the up-down ambiguity is kept unsolved. This paper also shows that parallax motion unlocks essential information about the distance and the Cartesian coordinates of the sound source. Shifting the microphone system sideways fixes the distance and the coordinate on the interaural axis. Combining rotation and translation movements completely solves the localization problem. In order to illustrate the efficacy of the model, this paper presents experiments with a low cost robot developer kit during which the azimuth, the elevation, and the distance of continuous sound sources are determined at a precision of 10 degrees and 0.5 m, respectively. Achieving this performance with low power material demonstrates how easily the model can be implemented into any robotic system.
ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies bo... more ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies both central and non-central absolute and relative camera pose computation algorithms within a single library. Each problem type comes with minimal and non-minimal closed-form solvers, as well as non-linear iterative optimization and robust sample consensus methods. OpenGV therefore contains an unprecedented level of com- pleteness with regard to calibrated geometric vision algorithms, and it is the first library with a dedicated focus on a unified real-time usage of non-central multi-camera systems, which are increasingly popular in robotics and in the automotive industry. This paper introduces OpenGV’s flexible interface and abstraction for multi-camera systems, and outlines the performance of all contained algorithms. It is our hope that the introduction of this open-source platform will motivate people to use it and potentially also include more algorithms, which would further contribute to the general accessibility of geometric vision algorithms, and build a common playground for the fair comparison of different solutions.
The Journal of the Acoustical Society of America, Nov 1, 2008
This paper presents a mathematical model for sound localization in space using two-microphone dev... more This paper presents a mathematical model for sound localization in space using two-microphone devices that possess at least two degrees of freedom. It proves a series of theorems and lemmas that are based on time difference of arrival measurements and movements of the interaural axis, forming a powerful instrument for practical robot applications. For instance, it shows that a single determined rotation of the interaural axis is sufficient to exactly yield the azimuth or the elevation of an immobile sound source in the far field, independently of microphone spacing and the speed of sound and hence of the surrounding medium. It proves that at any moment the knowledge of one value determines the magnitude of the other, with the restriction that the sign of the second value is undefined, which means that, depending on the rotation, either the back-front or the up-down ambiguity is kept unsolved. This paper also shows that parallax motion unlocks essential information about the distance and the Cartesian coordinates of the sound source. Shifting the microphone system sideways fixes the distance and the coordinate on the interaural axis. Combining rotation and translation movements completely solves the localization problem. In order to illustrate the efficacy of the model, this paper presents experiments with a low cost robot developer kit during which the azimuth, the elevation, and the distance of continuous sound sources are determined at a precision of 10 degrees and 0.5 m, respectively. Achieving this performance with low power material demonstrates how easily the model can be implemented into any robotic system.
2014 IEEE International Conference on Robotics and Automation (ICRA), 2014
ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies bo... more ABSTRACT OpenGV is a new C++ library for calibrated real- time 3D geometric vision. It unifies both central and non-central absolute and relative camera pose computation algorithms within a single library. Each problem type comes with minimal and non-minimal closed-form solvers, as well as non-linear iterative optimization and robust sample consensus methods. OpenGV therefore contains an unprecedented level of com- pleteness with regard to calibrated geometric vision algorithms, and it is the first library with a dedicated focus on a unified real-time usage of non-central multi-camera systems, which are increasingly popular in robotics and in the automotive industry. This paper introduces OpenGV’s flexible interface and abstraction for multi-camera systems, and outlines the performance of all contained algorithms. It is our hope that the introduction of this open-source platform will motivate people to use it and potentially also include more algorithms, which would further contribute to the general accessibility of geometric vision algorithms, and build a common playground for the fair comparison of different solutions.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
ABSTRACT This work presents a method for estimating the egomotion of an aerial vehicle in challen... more ABSTRACT This work presents a method for estimating the egomotion of an aerial vehicle in challenging industrial environments. It combines binocular visual and inertial cues in a tightly-coupled fashion and operates in real time on an embedded platform. An extended Kalman filter fuses measurements and makes motion estimation rely more on inertial data if visual feature constellation is degenerate. Errors in roll and pitch are bounded implicitly by the gravity vector. Inertial sensors are used for efficient outlier detection and enable operation in poorly and repetitively textured environments. We demonstrate robustness and accuracy in an industrial scenario as well as in general indoor environments. The former is accompanied by a detailed performance evaluation supported with ground truth measurements from an external tracking system.
2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011
The objective of this paper is the full 6D relative localization of mobile devices, and direct ro... more The objective of this paper is the full 6D relative localization of mobile devices, and direct robot-robot local- ization in particular. We present a novel relative localization system that consists of two complementary modules: a monoc- ular vision module and a target module with four active or passive markers. The core localization algorithm running on the modules determines the marker
The Journal of the Acoustical Society of America, 2008
This paper presents a mathematical model for sound localization in space using two-microphone dev... more This paper presents a mathematical model for sound localization in space using two-microphone devices that possess at least two degrees of freedom. It proves a series of theorems and lemmas that are based on time difference of arrival measurements and movements of the interaural axis, forming a powerful instrument for practical robot applications. For instance, it shows that a single determined rotation of the interaural axis is sufficient to exactly yield the azimuth or the elevation of an immobile sound source in the far field, independently of microphone spacing and the speed of sound and hence of the surrounding medium. It proves that at any moment the knowledge of one value determines the magnitude of the other, with the restriction that the sign of the second value is undefined, which means that, depending on the rotation, either the back-front or the up-down ambiguity is kept unsolved. This paper also shows that parallax motion unlocks essential information about the distance and the Cartesian coordinates of the sound source. Shifting the microphone system sideways fixes the distance and the coordinate on the interaural axis. Combining rotation and translation movements completely solves the localization problem. In order to illustrate the efficacy of the model, this paper presents experiments with a low cost robot developer kit during which the azimuth, the elevation, and the distance of continuous sound sources are determined at a precision of 10 degrees and 0.5 m, respectively. Achieving this performance with low power material demonstrates how easily the model can be implemented into any robotic system.
Uploads
Papers by Laurent Kneip