This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Active Tracking Strategy for Monocular Depth Inference over Multiple Frames
January 1990 (vol. 12 no. 1)
pp. 13-27

The extraction of depth information from a sequence of images is investigated. An algorithm that exploits the constraint imposed by active motion of the camera is described. Within this framework, in order to facilitate measurement of the navigation parameters, a constrained egomotion strategy was adopted in which the position of the fixation point is stabilized during the navigation (in an anthropomorphic fashion). This constraint reduces the dimensionality of the parameter space without increasing the complexity of the equations. A further distinctive point is the use of two sampling rates: the faster (related to the computation of the instantaneous optical flow) is fast enough to allow the local operator to sense the passing edge (or, in other words, to allow the tracking of moving contour points), while the slower (used to perform the triangulation procedure necessary to derive depth) is slow enough to provide a sufficiently large baseline for triangulation. Experimental results on real image sequences are presented.

[1] P. Morasso, G. Sandini, and M. Tistarelli, "Active vision: Integration of fixed and mobile cameras," inProc. NATO ARW Sensors Sensory Syst. Adv. Robots(Berlin, Heidelberg), 1986.
[2] D. H. Ballard and C. M. Brown,Computer Vision. Englewood Cliffs, NJ: Prentice-Hall, 1982.
[3] D. Marr and T. Poggio, "A computational theory of human stereo vision,"Proc. Roy. Soc. London, vol. B 204, pp. 301-328, 1979.
[4] W. Richards, "Structure from stereo and motion," MIT A.I. Lab., Cambridge, MA, A.I. Memo 731, Sept. 1983.
[5] N. J. Bridwell and T. S. Huang, "A discrete spatial representation for lateral motion stereo,"CVGIP, vol. 21, pp.33-57, 1983.
[6] G. Sandini, P. Morasso, and M. Tistarelli, "Motor and spatial aspects in artificial vision," inProc. of 4th Int. Symp. Robotics Res.(Santa Cruz, CA), 1987, MIT Press.
[7] T. Poggio, "Visual algorithms," MIT A.I. Lab., Cambridge, MA, A.I. Memo 683, 1982.
[8] K. Ikeuchi, H. K. Nishihara, B. K. P. Horn, P. Sobalvarro, and S. Nagata, "The PRISM binocular stereo system," MIT A.I. Lab., Cambridge, MA, A.I. Memo 772, Aug. 1984.
[9] H. K. Nishihara, "PRISM: A practical real-time imaging stereo matcher," MIT A.I. Lab., Cambridge, MA, A.I. Memo 780, May 1984.
[10] L. S. Davis, Z. Wu, and H. Sun, "Contour-based motion estimation,"CVGIP, vol. 23, pp. 313-326, 1983.
[11] C. Braccini, G. Gambardella, A. Grattarola, L. Massone, P. Morasso, G. Sandini, and M. Tistarelli, "Objective reconstruction from motion: Comparison and integration of different methods," inProc. II Int. Workshop Time-Varying Image Processing and Moving Object Recognition, Florence, Sept. 8-9, 1987, pp. 220-229.
[12] G. Sandini and M. Tistarelli, "Recovery of depth information: Camera motion as an integration to stereo," inProc. Workshop Motion: Representation and Analysis, Kiawah Island, May 7-9, 1986, pp. 39- 43.
[13] H.-H. Nagel and W. Enkelmann, "An investigation of smoothness constraints for the estimation of displacement vector fields from image sequences,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, no. 5, pp. 565-593, Sept. 1986.
[14] E. Hildreth,The Measurement of Visual Motion, Cambridge, MA: MIT Press, 1983.
[15] A. Bandopadhay, B. Chandra, and D. H. Ballard, "Active navigation: Tracking on environmental point considered beneficial," inProc. Workshop Motion: Representation and Analysis, Kiawah Island, May 7-9, 1986, pp. 23-29.
[16] G. Sandini, V. Tagliasco, and M. Tistarelli, "Analysis of object motion and camera motion in real scenes," inProc. IEEE Int. Conf. Robotics and Automation, San Francisco, CA, Apr. 7-10, 1986, pp. 627-633.
[17] K. Prazdny, "Egomotion and relative depth map from optical flow,"Biol. Cybern., vol. 36, pp. 87-102, 1980.
[18] B. K. P. Horn,Robot Vision. Cambridge, MA: M.I.T. Press, 1986.
[19] N. Sugie and M. Wakakuwa, "Visual target tracking with active head rotation,"IEEE Trans. Syst. Sci. Cybern., vol. SSC-6, pp. 103-108, 1970.
[20] P. Morasso, G. Sandini, V. Tagliasco, and R. Zaccaria, "Control strategies in the eye-head coordination system,"IEEE Trans. Syst., Man., Cybern., vol. SMC-9, pp. 639-651, 1977.
[21] D. T. Lawton, "Processing translational motion sequences,"CVGIP, vol. 22, pp. 116-144, 1983.
[22] S. Bharwani, E. Riseman, and A. Hanson, "Refinement of environmental depth maps over multiple frames," inProc. Workshop Motion: Representation and Analysis, Kiawah Island, May 7-9, 1986, pp. 73-80.
[23] D. Marr and E. Hildreth, "Theory of edge detection,"Proc. Roy. Soc. London, vol. B207, pp. 187-217, 1980.
[24] B. K. P. Horn and B. G. Schunck, "Determining optical flow," Artificial Intell., vol. 17, no. 1, pp. 185-204, 1981.
[25] H. Nagel, "Displacement vectors derived from second-order intensity variations in image sequence,"CVGIP, vol. 21, pp. 85-117, 1983.
[26] A. Huertas, and G. Medioni, "Detection of intensity changes with subpixel accuracy using Laplacian-Gaussian masks,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-8, no. 5, pp. 651-664, Sept. 1986.
[27] G. Sandini and V. Torre, "Thresholding techniques for zero crossings," inProc. Winter 85-Topical Meeting Machine Vision," Incline Village, NV, 1985, pp. ThD5-1-ThD5-4.
[28] J. H. Rieger and D. T. Lawton, "Processing differential image motion," Univ. Massachusetts, Amherst, COINS Tech. Rep. 84-28, 1984.
[29] L. Matthies and T. Kanade, "Using uncertainty models in visual motion and depth estimation," inProc. 4th Int. Symp. Robotics Research, Santa Cruz, CA, Aug. 9-14, 1987, pp. 120-138.
[30] M. A. Snyder, "The accuracy of 3D parameters in correspondence-based techniques: Startup and updating," inProc. Workshop Motion: Representation and Analysis, Kiawah Island, May 7-9, 1986, pp. 53- 59.
[31] S. Ullman, "Maximizing rigidity: The incremental recovery of 3-D structure from rigid and rubbery motion," MIT A.I. Lab., Cambridge, MA, A.I. Memo 721, 1983.
[32] R. Bajcsy, "Active perception versus passive perception," inProc. 3rd IEEE Workshop Vision, 1985, pp. 55-59.

Index Terms:
pattern recognition; picture processing; active tracking strategy; monocular depth inference; active motion; constrained egomotion strategy; fixation point; navigation; passing edge; triangulation procedure; pattern recognition; picture processing
Citation:
G. Sandini, M. Tistarelli, "Active Tracking Strategy for Monocular Depth Inference over Multiple Frames," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 13-27, Jan. 1990, doi:10.1109/34.41380
Usage of this product signifies your acceptance of the Terms of Use.