3D Reconstruction Using Multibaseline Omnidirectional Motion Stereo Based on GPS/Dead-reckoning Compound Navigation System

Abstract

This paper presents a motion-stereo device using the GPS/DR (dead reckoning) combination along with omnidirectional cameras to reconstruct 3-D environments by means of sensors small enough to be installed on a mobile robot. The proposed technique is based on the fact that it is possible to determine epipolar lines by using the precise positions and heading angles measured by a combination of GPS and various sensors; high-precision stereo matching may then be performed by means of geometrical restrictions. Furthermore, in comparison to the other stereo techniques, it is also possible to establish longer baselines for peripheral objects and simultaneously provide a higher precision in calculating the distances to far objects by applying voting processing to a series of distant motion-stereo images, which can be attained by using more than one baseline length, in 3-D spaces based on the precise positions and heading angles. In short, the proposed technique provides a substantial increase in measurement precision as compared to that with the well-known SFM (structure from motion) technique for reconstructing 3-D environments with monocular cameras; this is because the proposed technique utilizes a greater number of mobile parameters, which are determined using precise cameras. In this experiment, the measurement precision of the proposed technique has been evaluated in reconstructing the shapes of vehicles parked alongside a road; the measurements were found to have a standard deviation of 140 mm within a range of 10 m. It can be stated that the proposed omnidirectional motion-stereo technique is robust to environmental perturbations and can accurately estimate distances in the case of highly textured objects.

Keywords

Sensor Fusion Multibaseline Motion Stereo Omnivision GPS/Dead-rekoning compound navigation system 3D reconstruction

Get full access to this article

View all access options for this article.

References

Bolles, R.C. , Baker, H.H. , and Marimont, D.H. (1987). Epipolar-plane image analysis: An approach to determining structure from motion. International Journal of Computer Vision, 1: 7—55.

Carlson, C.R. , Gerdes, J.C. , and Powell, J.D. (2002). Practical position and yaw rate estimation with gps and differential wheelspeeds. In Proceedings of AVEC 2006 6th International Symposium of Advanced Vehicle Control.

Davison, A.J. , Cid, Y.G. , and Kita, N. (2004). Real-time 3D SLAM with WIDE-angle vision. In Proceedings of 5th IFAC Euron Symposium on International Autonomous Vehicle. Instituto Superior Técnico, Lisboa, Portugal, July 5—7.

Diel, D.D. , DeBitetto, P. , and Teller, S. (2005). Epipolar constraints for vision-aided inertial navigation. Proceedings of 7th IEEE Workshop on Applications of Computer Vision/IEEE Workshop on Motion and Video Computing (WACV/MOTION 2005), January, pp. 221—228.

Folkesson, J. , Jensfelt, P. and Christensen, H.I. (2005). Vision SLAM in the measurement subspace. Proceedings of the 2005 IEEE International Conference on Robotics and Automation 2005, 18—22 April, pp. 30—35.

Früh, C. and Zakhor, A. (2001). 3D Model generation for cities using aerial photographs and ground level laser scans. IEEE Conference on Computer Vision and Pattern Recognition, Kauai, USA, Vol. 2.2, pp. II-31—II-38.

Grejner-Brzezinska, D.A. and Toth, C. (2004). High accuracy dynamic highway mapping using a GPS/INS/CCD system with on-the-fly GPS ambiguity resolution, GISS Users Manual Version 2.0.

Hanandhar, D. and Shibasaki, R. (2001). Vehicle-borne laser mapping system (VLMS) for 3-D GIS. Geoscience and Remote Sensing Symposium , pp.2073—2075.

Hartley, R. , Gupta, R. and Chang, T. (1992). Stereo from uncalibrated cameras. Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.761—764.

10.

Hartley, R. and Zisserman, A. (2004). Multiple View Geometry in Computer Vision. Cambridge University Press.

11.

Hirokawa, R. et al. (2004). Autonomous vehicle navigation with carrier phase dgps and laser-scanner augmentation. The Satellite Division Technical Meeting of ION GNSS ION (The Institute of Navigation) GNSS (Global Navigation Satellite System).

12.

Kanade, T. , Okutomi, M. , and Nakahara, T. (1992). A multiple-baseline stereo method. Proceedings of DARPA Image Understanding Workshop, January.

13.

Leberl, F. et al. (2003). The Ultracam large format aerial digital camera system. Proceedings of the ASPRS Annual Convention, Anchorage, USA.

14.

Meguro, J. , Takiguchi, J. et al. (2005a) Development of an autonomous mobile surveillance system using a network-based RTK-GPS. IEEE International Conference on Robotics and Automation (ICRA), Barcelona , Spain.

15.

Meguro, J. , Hirokawa, R. , Takiguchi, J. , and Hashizume, T. (2005b) autonomous mobile surveillance system based on RTK-GPS in urban canyons. Journal of Robotics and Mechatoronics, 17(2): 218—225.

16.

Nistér, D. (2000). Reconstruction from uncalibrated sequences with a hierarchy of trifocal tensors. In Proceedings of European Conference on Computer Vision (ECCV), Dublin , Ireland, Volume 1, pp. 649—663.

17.

Nüchter, A. et al. (2005). Mapping of rescue environments with Kurt3D . Proceedings of the 2005 IEEE, International Workshop on Safety, Security and Rescue Robotics, Kobe, Japan.

18.

Ono, S. , Ikeuchi, K. et al. (2003). 3D Modeling of urban spaces by ego-motion estimation using horizontal range scanning. Proceedings of ITS Symposium, Tokyo, Japan.

19.

Poelman C.J. et al. (1993). A paraperspective factorization method shape and motion recovery. Technical report CMU— CS—93—219 , Computer Science Department, Carnegie Mellon University .

20.

Saito, M. et al. (2003) Network-based RTK-GPS for nationwide high accuracy positioning and navigation in Japan. International Symposium International Space University, Strasbourg, France.

21.

Sato, T. , Kanbara, M. , and Yokoya, N. (2003). 3-D modeling of an outdoor scene from multiple image sequences by estimating camera motion parameters. Proceedings of 13th Scandinavian Conference on Image Analysis, pp. 717— 724.

22.

Surmann, H. , Nüchter, A. , and Hertzberg, J. (2003). An autonomous mobile robot with a 3D laser range finder for 3D exploration and digitalization of indoor environments. Robotics and Autonomous Systems, 45(3-4): 181—198.

23.

Surmann, H. , Nüchter, A. , Lingemann, K. , and Hertzberg, J. (2004).Å@6D SLAM — preliminary report on closing the loop in six dimensions. Proceedings of the 5th Symposium on Intelligent Autonomous Vehicles, Lisbon , Portugal.

24.

Takiguchi, J. , Hashizume, T. et al. (2002). High precision range estimation from an omnidirectional stereo system. IEEE/RSJ International Conference on Intelligent Robots and Systems, EPFL, pp.263—268.

25.

Tao, C.V. (2000). Mobile mapping technology for road network data acquisition. Journal of Geospatial Engineering, 2(2): 1—13

26.

Tao, Y. , Hu, H. , and Zhou, H. (2005) Integration of vision and inertial sensors for home-based rehabilitation. InerVis 2005, the 2nd Workshop on Integration of Vision and Inertial Sensors, Barcelona, Spain.

27.

Tomasi, C. et al. (1992). Shape and motion from image, streams under orthgraphy: a factorization method. International Journal of Computer Vision, 9(2): 137—154.

28.

Tomono, M. (2004). 3-D localization and mapping using a single camera based on structure-from-motion with automatic baseline selection. Proceedings of the 2004 IEEE International Conference on Robotics and Automation.

29.

Zhou, Y.T. and Chellappa, R. (1989). Neural network algorithms for motion stereo. International Joint Conference on Neural Networks, Vol. 2, pp.251—258.

30.

Vidal, R. , Ma, Y. , Soatto, S. , and Sastry, S. (2006). Two-view multibody structure from motion. International Journal of Computer Vision, 68(1): 7—25.

31.

You, S. , Neumann, U. , and Azuma, R. (1999). Hybrid inertial and vision tracking for augmented reality registration. IEEE Virtual Reality Conference , pp.260—267.

32.

Zhao, H. and Shibasaki, R. (2003) Reconstructing a textured CAD model of an urban environment using vehicle-borne laser range scanners and line cameras. Machine Vision and Applications, 14: 35—41.