This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Obstacle Detection Based on Qualitative and Quantitative 3D Reconstruction
January 1997 (vol. 19 no. 1)
pp. 15-26

Abstract—Three different algorithms for obstacle detection are presented in this paper each based on different assumptions. The first two algorithms are qualitative in that they return only yes/no answers regarding the presence of obstacles in the field of view; no 3D reconstruction is performed. They have the advantage of fast determination of the existence of obstacles in a scene based on the solvability of a linear system. The first algorithm uses information about the ground plane, while the second only assumes that the ground is planar. The third algorithm is quantitative in that it continuously estimates the ground plane and reconstructs partial 3D structures by determining the height above the ground plane of each point in the scene. Experimental results are presented for real and simulated data, and the performance of the three algorithms under different noise levels is compared in simulation. We conclude that in terms of the robustness of performance, the third algorithm is superior to the other two.

[1] P. Anandan, "A Computational Framework and an Algorithm for the Measurement of Visual Motion," Int'l J. Computer Vision, vol. 2, no. 3, 1989.
[2] S. Badal, R. Srinivas, B. Draper, and A. Hanson, "A Practical Obstacle Detection and Avoidance System," Proc. Second IEEE Workshop on Applications of Computer Vision, IEEE, 1994.
[3] M.J. Daily, J.G. Harris, and K. Reiser, "Detecting Obstacles in Range Imagery," Proc. IUW. Morgan Kaufmann, 1987.
[4] M.J. Daily, J.G. Harris, and K. Reiser, "An Operational Perception System for Cross-Country Navigation," Proc. IUW. Morgan Kaufmann, 1988.
[5] W. Enkelmann, "Obstacle Detection by Evaluation of Optical Flow Fields," Proc. First ECCV, 1990.
[6] O.D. Faugeras, "What Can Be Seen in Three Dimensions with an Uncalibrated Stereo Rig?" Proc. Second ECCV, pp. 563-578,Santa Margherita Ligure, Italy, May 1992.
[7] O.D. Faugeras, Q.-T. Luong, and S.J. Maybank, "Camera Self-Calibration: Theory and Experiments," Proc. Second ECCV, pp. 321-334,Santa Margherita Ligure, Italy, May 1992.
[8] O.D. Faugeras and F. Lustman, "Motion and Structure from Motion in a Piecewise Planar Environment," Int'l J. Pattern Recognition and Artificial Intelligence, vol. 2, pp. 485-508, 1988.
[9] G.H. Golub and C.F.V. Loan, Matrix Computations, second ed., Baltimore: Johns Hopkins Univ. Press, 1989.
[10] P. Grandjean and L. Matthies, "Perception Control for Obstacle Detection by a Cross Country Rover," Proc. ICRA, pp. 20-27,Atlanta, Georgia, May 1993.
[11] A.R. Hanson, E.M. Riseman, and C.A. Weems, "Progress in Computer Vision at the University of Massachusetts," Proc. IUW, pp. 39-47. Morgan Kaufmann, Apr. 1993.
[12] R. Hartley, R. Gupta, and T. Chang, "Stereo from Uncalibrated Cameras," Proc. CVPR, 1992.
[13] R. Kumar, Model Dependent Inference of 3D Information From a Sequence of 2D Images. PhD dissertation, COINS TR92-04, Univ. of Massachusetts, 1992.
[14] L.H. Matthies, "Toward Stochastic Modeling of Obstacle Detectability in Passive Stereo Range Imagery," Proc. CVPR, June 1992.
[15] L.H. Matthies and P. Grandjean, "Stochastic Performance Modeling and Evaluation of Obstacle Detectability with Imaging Range Sensors," Proc. CVPR, June 1993.
[16] S. Maybank, Theory of Reconstruction from Image Motion.New York: Springer-Verlag, 1993.
[17] R. Mohr, F. Veillon, and L. Quan, “Relative 3D Reconstruction Using Multiple Uncalibrated Images,” Proc. IEEE Fifth Int'l Conf. Computer Vision, pp. 543-548, 1993.
[18] R.C. Nelson and J. Aloimonos,“Using flow field divergence for obstacleavoidance in visual navigation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 10, pp. 1,102-1,106, Oct. 1989.
[19] J. Ponce, T.A. Cass, and D.H. Marimont, "Relative Stereo and Motion Reconstruction," TR AI-RCV-93-07, Univ. Illi nois, 1993.
[20] A. Shashua,“Projective depth: A geometric invariant for 3D reconstruction from two perspective/orthographic views and for visual recognition,” Proc. Int’l Conf. Computer Vision, pp. 583-590,Berlin, May 1993.
[21] U. Solder and V. Graefe, "Object Detection in Real Time," SPIE Mobile Robots V, p. 1,388, 1990.
[22] K. Storjohann, T. Zielke, H.A. Mallot, and W. Von Seelen, "Visual Obstacle Detection for Automatically Guided Vehicles," Proc. ICRA, 1990.
[23] G.-S. Young, T.-H. Hong, M. Herman, and C.S. Yang, "Obstacle Detection for a Vehicle Using Optical Flow," SAE Intelligent Vehicle,Detroit, July 1992.
[24] Z. Zhang, 3D Reconstruction Under Varying Constraints on Camera Geometry for Robotic Navigation Scenarios. PhD dissertation, CMPSCI 96-08, Univ. of Massachusetts, 1996.
[25] Z. Zhang, R. Weiss, and A.R. Hanson, "Qualitative Obstacle Detection," Proc. CVPR, 1994.
[26] Q. Zheng and R. Chellappa, "Automatic feature point extraction and tracking in image sequences from unknown camera motion," Proc. Fourth Int'l Conf. on Computer Vision, pp. 335-339, 1993.

Index Terms:
Motion analysis and stereo, qualitative vision, obstacle detection, 3D reconstruction, partial calibration.
Citation:
Zhongfei Zhang, Richard Weiss, Allen R. Hanson, "Obstacle Detection Based on Qualitative and Quantitative 3D Reconstruction," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 1, pp. 15-26, Jan. 1997, doi:10.1109/34.566807
Usage of this product signifies your acceptance of the Terms of Use.