Definition of the Subject
For advanced driver assistance systems, the 3D poses and motion states of oncoming and intersecting vehicles represent important information. This work describes methods for 3D vehicle pose estimation based on a motion-attributed 3D point cloud generated. First, stereo and optical flow information is computed for the investigated scene. A four-dimensional clustering approach separates the static from the moving objects in the scene. The iterative closest point algorithm (ICP) estimates the vehicle pose using a cuboid as a weak vehicle model. Classical ICP optimization is based on the Euclidean distance metric. Its computational efficiency can be significantly increased by applying a quaternion-based optimization scheme. In vehicle-based small-baseline stereo systems, it is favorable to use a polar distance metric which especially takes into account the error distribution of the stereo measurement process. To...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Abbreviations
- 3D Pose estimation:
-
Estimation of the translational and rotational degrees of freedom of an object, usually corresponding to its position in 3D space and its orientation angles. For articulated objects additional, internal degrees of freedom are estimated.
- Driver assistance system:
-
A system which helps the driver of a car in specific traffic situations in order to increase safety.
- Iterative closest point (ICP) algorithm:
-
An algorithm which finds a set of translation and rotation parameters fitting a measured point cloud to a model.
- Optical flow:
-
The optical flow vector denotes the motion in image space of the projection of a scene point between two subsequent images of a sequence.
- Quaternion:
-
Number system which extends the system of complex numbers. In computer vision and computer graphics, quaternions are used for the efficient representation of rotations.
- Scene flow:
-
Vector field describing the 3D scene points visible in the image and their current motion in 3D space. Projecting the scene flow into the image plane yields the optical flow.
- Stereo vision:
-
3D reconstruction of a scene based on a pair of images.
- Yaw angle:
-
Angle measuring the rotation of a vehicle around its vertical axis.
- Yaw rate:
-
Temporal derivative of the yaw angle.
Bibliography
Collado JM, Hilario C, de la Escalera A, Armingol JM (2004) Model based vehicle detection for intelligent vehicles. In: Proceedings of the IEEE intelligent vehicles symposium, Parma, pp 572–577
Dellaert F, Thorpe CE (1997) Robust car tracking using kalman filtering and Bayesian templates. In: Proceedings of the conference on intelligent transportation systems, Boston
Koller D, Danilidis K, Nagel H-H (1993) Model-based object tracking in monocular image sequences of road traffic scenes. Int J Comput Vision 10(3):257–281
Kollnig H, Nagel H-H (1997) 3D pose estimation by directly matching polyhedral models to gray value gradients. Int J Comput Vision 23(3):283–302
Haag M, Nagel H-H (1999) Combination of edge element and optical flow estimates for 3D model-based vehicle tracking in traffic image sequences. Int J Comput Vis 35(3):295–319
Kato T, Ninomiya Y, Masaki I (2002) An obstacle detection method by fusion of radar and motion stereo. IEEE Trans Intell Transp Syst 3(3):182–188
Steux B, Laurgeau C, Salesse L, Wautier D (2002) Fade: a vehicle detection and tracking system featuring monocular color vision and radar data fusion. Proceedings of the IEEE Intell Vehicle Symp 2:632–639
Wender S, Dietmayer K (2007) 3D vehicle detection using a laser scanner and a video camera. In: Proceedings of the sixth European congress on ITS in Europe, Aalborg
Kaempchen N (2007) Feature-level fusion of laser scanner and video data for advanced driver assistance systems. PhD thesis, Faculty of Engineering and Computer Science, Ulm University
Knöppel C, Regensburger U, Schanz A, Michaelis B (2000) Robuste Erkennung von Straßenfahrzeugen im Rückraumbereich eines Straßenfahrzeuges. In: Proceedings of the 22nd DAGM symposium. Springer, Heidelberg, pp 35–42
Dang T, Hoffmann C, Stiller C (2002) Fusing optical flow and stereo disparity for object tracking. In: Proceedings of the IEEE international conference on intelligent transportation systems, Singapore
Leibe B, Cornelis N, Cornelis K, van Gool L (2006) Integrating recognition and reconstruction for cognitive traffic scene analysis from a moving vehicle. In: Proceedings of the 28th DAGM annual pattern recognition symposium. Springer, Heidelberg, pp 192–201
Leibe B, Schiele B (2004) Scale-invariant object categorization using a scale-adaptive mean-shift search. In: Proceedings of the 26th DAGM annual pattern recognition symposium. Springer, Heidelberg, pp 145–153
Toulminet G, Bertozzi M, Mousset S, Bensrhair A, Broggi A (2006) Vehicle detection by means of stereo vision-based obstacles features extraction and monocular pattern analysis. IEEE Trans Image Process 15(8):2364–2375
Kubota S, Nakano T, Okamoto Y (2007) A global optimization algorithm for realtime on-board stereo obstacle detection systems. In: Proceedings of the IEEE intelligent vehicles symposium, Istanbul, pp 7–12
Nedevschi S, Danescu R, Marita T, Oniga F, Pocol C, Sobol S, Tomiuc C, Vancea C, Meinecke MM, Graf T, To TB, Obojski MA (2007) A sensor for urban driving assistance systems based on dense stereovision. In: Proceedings of the IEEE intelligent vehicles symposium, Istanbul, pp 276–283
Barth A, Franke U (2008) Where will the oncoming vehicle be the next second? In: Proceedings of the IEEE intelligent vehicles symposium, Eindhoven
Hermes C, Barth A, Wöhler C, Kummert F (2009) Object motion analysis and prediction in stereo image sequences. In: Proceedings of the Oldenburger 3D-Tage, Oldenburg
Barth A, Siegemund J, Franke U, Förstner W (2009) Simultaneous estimation of pose and motion at highly dynamic turn maneuvers. In: Proceedings of the 31st DAGM symposium, Springer, Heidelberg, pp 262–271
Schmidt J, Wöhler C, Krüger L, Gövert T, Hermes C (2007) 3D scene segmentation and object tracking in multiocular image sequences. In: Proceedings of the fifth international conference on computer vision systems, Bielefeld. http://biecoll.ub.uni-bielefeld.de/volltexte/2007/29/
Fielding G, Kam M (1997) Applying the Hungarian method to stereo matching. In: Proceedings of the IEEE conference on decision and control, San Diego, pp 549–558
Stein F (2004) Efficient computation of optical flow using the census transform. In: Proceedings of DAGM annual pattern recognition symposium, Tuebingen, pp 79–86
Franke U, Joos A (2000) Real-time stereo vision for urban traffic scene understanding. In: Proceedings of the IEEE intelligent vehicles symposium, Dearborn, pp 273–278
Bock HH (1974) Automatische Klassifikation. Vandenhoeck & Ruprecht, Göttingen
Barrois B, Wöhler C (2008) Spatio-temporal 3D pose estimation of objects in stereo images. In: Proceedings of the sixth international conference on computer vision systems, vol 5008, Lecture notes in computer science. Springer, Heidelberg, pp 507–516
Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York
Besl PJ, McKay ND (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239–256
Zhang Z (1992) Iterative point matching for registration of free-form curves. IN-RIA, Technical Report. ftp://ftp.inria.fr/INRIA/publication/publi-ps-gz/RR/RR-1658.ps.gz
Press WH, Teukolsky SA, Vetterling WT, Flannery BP (1992) Numerical recipes in C: the art of scientific computing. Cambridge University Press, New Delhi
Horn BKP (1987) Closed-form solution of absolute orientation using unit quaternions. J Opt Soc Am A 4(4):629–642
Hamilton WR (1866) Elements of quaternions. Longmans, Green, London
Hartley R, Zisserman A (2003) Multiple view geometry in computer vision, 2nd edn. Cambridge University Press, Cambridge
Krüger L, Wöhler C (2011) Accurate chequerboard corner localisation for camera calibration and scene reconstruction. Pattern Recognit Lett (to appear)
Hermes C, Einhaus J, Hahn M, Wöhler C, Kummert F (2010) vehicle tracking and motion prediction in complex urban scenarios. In: Proceedings of the IEEE intelligent vehicles symposium, San Diego
Käfer E, Hermes C, Wöhler C, Ritter H, Kummert F (2010) Recognition of situation classes at road intersections. In: Proceedings of the IEEE international conference on robotics and automation, Anchorage
Barrois B, Hristova S, Wöhler C, Kummert F, Hermes C (2009) 3D pose estimation of vehicles using a stereo camera. In: Proceedings of the IEEE intelligent vehicles symposium, Xi‘an
Wöhler C (2009) 3D computer vision. Springer-Verlag, Berlin/Heidelberg
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer Science+Business Media New York
About this entry
Cite this entry
Barrois, B., Wöhler, C. (2013). 3D Pose Estimation of Vehicles Using Stereo Camera. In: Ehsani, M., Wang, FY., Brosch, G.L. (eds) Transportation Technologies for Sustainability. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-5844-9_484
Download citation
DOI: https://doi.org/10.1007/978-1-4614-5844-9_484
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-5843-2
Online ISBN: 978-1-4614-5844-9
eBook Packages: EnergyReference Module Computer Science and Engineering