Thorsten Graf
Research Subjects
Thorsten Graf has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jianwei Zhang
Universität Hamburg
2 shared publications - Sergiu Nedevschi
Department of Computer Science, Technical University of Cluj-Napoca, Cluj-Napoca, Romania
2 shared publications - C. Rotaru
Volkswagen AG
1 shared publication - Calin Rotaru
Group Research Electronics
1 shared publication - Florin Oniga
Technical University of Cluj-Napoca
1 shared publication - M.M. Meinecke
Volkswagen AG, Driving Assistance Electronics department
1 shared publication
Latest Publications
- 19 March 2008
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 3 (4) , 311-322
Color image segmentation in HSI space for automotive applications
- 19 March 2008
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 3 (4) , 311-322
Color image segmentation in HSI space for automotive applications
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530009,p. 400-404
Stereovision Based Vehicle Tracking in Urban Traffic Environments
This paper presents an algorithm for tracking the cuboids generated from grouping the 3D points obtained through stereovision. The solution described in the paper takes into consideration the particularities of the scenario and of the sensor, and brings considerable improvement in all the phases of tracking: initialization, prediction, measurement and update. The corner of the cuboid becomes the central working concept, thus improving the handling of partially occluded objects, of objects partially out of the field of view, and of objects whose measurement is fragmented by the sensor inaccuracies. After association at corner level, multiple measurements or validated parts of a measurement form a virtual object, the meta measurement, which is used for track update. The size of a vehicle is tracked using a histogram voting method. The resulted algorithm shows robustness and accuracy in the crowded urban scenario.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21530009,p. 400-404
Stereovision Based Vehicle Tracking in Urban Traffic Environments
This paper presents an algorithm for tracking the cuboids generated from grouping the 3D points obtained through stereovision. The solution described in the paper takes into consideration the particularities of the scenario and of the sensor, and brings considerable improvement in all the phases of tracking: initialization, prediction, measurement and update. The corner of the cuboid becomes the central working concept, thus improving the handling of partially occluded objects, of objects partially out of the field of view, and of objects whose measurement is fragmented by the sensor inaccuracies. After association at corner level, multiple measurements or validated parts of a measurement form a virtual object, the meta measurement, which is used for track update. The size of a vehicle is tracked using a histogram voting method. The resulted algorithm shows robustness and accuracy in the crowded urban scenario.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-118
Calibration Accuracy Assessment Methods for Stereovision Sensors Used in Vehicles
Stereovision systems mounted in vehicles are generally used by obstacle and lane detection applications with working ranges up to 100 m. The stereo reconstruction process for such depths is a high demanding one, regarding increased accuracy camera parameters. Among the parameters, some of them have a critical influence in the quality of the 3D reconstruction process and need special attention during calibration and should be monitored during time. This paper presents a set of original methods used to evaluate the accuracy of the camera parameters. The methods can be applied off-line using a dedicated setup with a known ground-truth or online in week-structured road scenarios.
- 1 September 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 111-118
Calibration Accuracy Assessment Methods for Stereovision Sensors Used in Vehicles
Stereovision systems mounted in vehicles are generally used by obstacle and lane detection applications with working ranges up to 100 m. The stereo reconstruction process for such depths is a high demanding one, regarding increased accuracy camera parameters. Among the parameters, some of them have a critical influence in the quality of the 3D reconstruction process and need special attention during calibration and should be monitored during time. This paper presents a set of original methods used to evaluate the accuracy of the camera parameters. The methods can be applied off-line using a dedicated setup with a known ground-truth or online in week-structured road scenarios.
- 1 January 2005
- Published by Springer Nature
- p. 61-69
Special Cases of Lane Detection in Construction Areas
- 1 January 2005
- Published by Springer Nature
- p. 61-69
Special Cases of Lane Detection in Construction Areas