A method for estimating mobile robot egomotion is presented, which relies on tracking contours in... more A method for estimating mobile robot egomotion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.
The features inherent in the visual motion field of a mobile robot indicate important clues about... more The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene variations induced by the camera-robot system, is estimated through optical flow calculations. The singular points of the global optical flow field of omnidirectional image sequences indicate the translation direction of the robot as well as the deviation from its planned path. It is also possible to detect motion patterns of near obstacles or independently moving objects of the scene. In this paper, after reviewing the image velocity measurement techniques shortly, we introduce the analysis of the intrinsic features of the omnidirectional motion fields for motion detection, giving some prelimin...
Omnidirectional optical flow and visual motion detection for autonomous robot navigation
... Fachbereich Mathematik/Informatik von Irem Stratmann Gutachter: ... Many members of the FhG-A... more ... Fachbereich Mathematik/Informatik von Irem Stratmann Gutachter: ... Many members of the FhG-AIS have supported my work in many ways. Special thanks to Ralph Breithaupt, Hartmut Surmann, Andreas Nüchter and Erik Solda for their help in providing the image sequences. ...
The features inherent in the visual motion field of a mobile robot indicate important clues about... more The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene variations induced by the camera-robot system, is estimated through optical flow calculations. The singular points of the global optical flow field of omnidirectional image sequences indicate the translation direction of the robot as well as the deviation from its planned path. It is also possible to detect motion patterns of near obstacles or independently moving objects of the scene. In this paper, after reviewing the image velocity measurement techniques shortly, we introduce the analysis of the intrinsic features of the omnidirectional motion fields for motion detection, giving some preliminary examples of this analysis.
A method for estimating mobile robot egomotion is presented, which relies on tracking contours in... more A method for estimating mobile robot egomotion is presented, which relies on tracking contours in real-time images acquired with a calibrated monocular video system. After fitting an active contour to an object in the image, 3D motion is derived from the affine deformations suffered by the contour in an image sequence. More than one object can be tracked at the same time yielding some different pose estimations. Then, improvements in pose determination are achieved by fusing all these different estimations. Inertial information is used to obtain better estimates, as it introduces in the tracking algorithm a measure of the real velocity. Inertial information is also used to eliminate some ambiguities arising from the use of a monocular image sequence. As the algorithms developed are intended to be used in real-time control systems, considerations on computation costs are taken into account.
The features inherent in the visual motion field of a mobile robot indicate important clues about... more The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene variations induced by the camera-robot system, is estimated through optical flow calculations. The singular points of the global optical flow field of omnidirectional image sequences indicate the translation direction of the robot as well as the deviation from its planned path. It is also possible to detect motion patterns of near obstacles or independently moving objects of the scene. In this paper, after reviewing the image velocity measurement techniques shortly, we introduce the analysis of the intrinsic features of the omnidirectional motion fields for motion detection, giving some prelimin...
Omnidirectional optical flow and visual motion detection for autonomous robot navigation
... Fachbereich Mathematik/Informatik von Irem Stratmann Gutachter: ... Many members of the FhG-A... more ... Fachbereich Mathematik/Informatik von Irem Stratmann Gutachter: ... Many members of the FhG-AIS have supported my work in many ways. Special thanks to Ralph Breithaupt, Hartmut Surmann, Andreas Nüchter and Erik Solda for their help in providing the image sequences. ...
The features inherent in the visual motion field of a mobile robot indicate important clues about... more The features inherent in the visual motion field of a mobile robot indicate important clues about its navigation and environment. Combining these visual clues with additional inertial sensor information allows reliable detection of navigation direction for a mobile robot and the independent motion which may be present in the scene. The motion field, which is the 2D projection of the 3D scene variations induced by the camera-robot system, is estimated through optical flow calculations. The singular points of the global optical flow field of omnidirectional image sequences indicate the translation direction of the robot as well as the deviation from its planned path. It is also possible to detect motion patterns of near obstacles or independently moving objects of the scene. In this paper, after reviewing the image velocity measurement techniques shortly, we introduce the analysis of the intrinsic features of the omnidirectional motion fields for motion detection, giving some preliminary examples of this analysis.
Uploads
Papers by irem stratmann