Performance analysis of total least squares methods in three-dimensional motion estimation

  title={Performance analysis of total least squares methods in three-dimensional motion estimation},
  author={Subhasis Chaudhuri and Shankar Chatterjee},
  journal={IEEE Trans. Robotics and Automation},
An algorithm is presented to obtain the total least squares (TLS) estimates of the motion parameters of an object from range/stereo data or perspective views in a closed form. TLS estimates are suitable when data in both time frames are corrupted by noise, an appropriate model for motion analysis in practice. We analyze the robustness of different linear least squares methods for the estimation of motion parameters against the sensor noise and possible mismatches in establishing object feature… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS
15 Citations
8 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-8 of 8 references

A geometric approach to errors-in-variables models,

  • CA San Diego
  • Linear Algebra in Signals, Systems & Control…
  • 1989

A unitarily constrained total least squares problem in signal processing,

  • San Diego, CA, 1989. K.S. Arun
  • SIAM J . Matrix Analysis Appl., to be published
  • 1989

The partial total least squares algorithm,

  • S. Van Huffel, J. Vandewalle
  • J. Computl. Appl. Math.,
  • 1988

Robust algorithms for motion estimation based on two sequential stereo image pairs,

  • FL Beach
  • in Proc. IEEE Conf. Computer Vision Pattern…
  • 1986

Similar Papers

Loading similar papers…