Abstract
This paper describes an algorithm for maintaining fixation upon a 3D body-centred point using 3D affine transfer, extending an earlier monocular method to stereo cameras. Transfer is based on corners detected in the image and matched over time and in stereo. The paper presents a method using all available matched data, providing immunity to noise and poor conditioning. The algorithm, implemented at video rates on a multi-processor machine, incorporates controlled degradation in the presence of insufficient data. Results are given from experiments using a four-axis active stereo camera platform, first which show the greater stability of the fixation point over the monocular method, both as it appears in the image and occurs in the scene; and, secondly, which show the recovery and evolution of 3D affine structure during fixation. It is shown that fixation and explicit structure recovery can occur separately, allowing the information required for gaze control to be computed in a fixed time.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Ballard, D.H. 1991. Animate vision. Artificial Intelligence, 48:57-86.
Barber, C.B., Dobkin, D.P., and Huhdanpaa, H. 1993. The quickhull algorithm for convex hulls. Technical Report GCG53, Geometry Center, University of Minnesota. Ftp-able from geom.umn.edu.
Bradshaw, K.J., Reid, I.D., and Murray, D.W. 1997. The active recovery of 3D motion trajectories and their use in prediction. IEEE Trans. on Pattern Analysis and Machine Intelligence, 19(3):219-234.
Demey, S., Zisserman, A., and Beardsley, P. 1992. Affine and projective structure from motion. In Proc. 3rd British Machine Vision Conf., Leeds, D. Hogg and R. Boyle (Eds.), Springer-Verlag, pp. 49-58.
Faugeras, O.D. 1992. What can be seem in three dimensions with an uncalibrated stereo rig? In Proc. 2nd European Conf. on Computer Vision, Santa Margharita Ligure, Italy, G. Sandini (Ed.), Springer-Verlag, pp. 563-578.
Fermüller, C. and Aloimonos, Y. 1993. The role of fixation in visual motion analysis. Int. J. Computer Vision, 11(2):165-186.
Harris, C. 1992. Tracking with rigid models. In Active Vision, A. Blake and A. Yuille (Eds.), MIT Press: Cambridge, MA.
Koenderink, J.J. and van Doorn, A. 1991. Affine structure from motion. J. Opt. Soc. Am. A, 8(2):377-385.
Mundy, J.L. and Zisserman, A.P. (Eds.), 1992. Geometric Invariance in Computer Vision. MIT Press: Cambridge, MA.
Murray, D.W., Bradshaw, K.J., McLauchlan, P.F., Reid, I.D., and Sharkey, P.M. 1995. Driving saccade to pursuit using image motion. Int. J. Computer Vision, 16(3):205-228.
Olson, T.J. and Coombs, D.J. 1991. Real-time vergence control for binocular robots. Int. J. Computer Vision, 7(1):67-89.
Pahlavan, K., Uhlin, T., and Eklundh, J.-O. 1993. Dynamic fixation. In Proc. 4th Int. Conf. on ComputerVision, Berlin, IEEE Computer Society Press: Los Alamitos, CA, pp. 412-419.
Reid, I.D. and Murray, D.W. 1993. Tracking foveated corner clusters using affine structure. In Proc. 4th Int. Conf. on Computer Vision, Berlin, IEEE Computer Society Press: Los Alamitos, CA, pp. 76-83.
Reid, I.D. and Murray, D.W. 1996. Active tracking of foveated corner clusters using affine structure. Int. J. Computer Vision, 18:41-60.
Shapiro, L.S. 1993. Affine analysis of image sequences. D.Phil. Thesis, University of Oxford.
Tomasi, C. and Kanade, T. 1992. Shape and motion from image streams under orthography: A factorization approach. Int. J. Computer Vision, 9(2):137-154.
Wang, H. and Brady, J.M. 1991. Corner detection for 3D vision using array processors. In Proc. BARNAIMAGE-91, Barcelona, Springer-Verlag.
Yuille, A. and Hallinan, P. 1992. Deformable templates. In Active Vision, A. Blake and A. Yuille (Eds.), MIT Press: Cambridge, MA, pp. 21-38.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Fairley, S.M., Reid, I.D. & Murray, D.W. Transfer of Fixation Using Affine Structure: Extending the Analysis to Stereo. International Journal of Computer Vision 29, 47–58 (1998). https://doi.org/10.1023/A:1008038713629
Issue Date:
DOI: https://doi.org/10.1023/A:1008038713629