Abstract
A classical problem in machine vision is the range identification of an object moving in three-dimensional space from the two-dimensional image sequence obtained with a monocular camera. This study presents a novel reduced-order optical flow-based nonlinear observer that renders the proposed scheme suitable for depth estimation applications in both well-structured and unstructured environments. In this study, a globally exponentially stable observer is synthesized, where optical flow estimates are derived from tracking feature trajectory on the image plane over successive camera frames, to yield asymptotic estimates of feature depth at a desired convergence rate. Furthermore, the observer is shown to be finite-gain \(\mathcal {L}_{p}\) stable ∀p∈[1,∞] in the presence of exogenous disturbance influencing camera motion, and is applicable to a wider class of perspective systems than those considered by alternative designs. The observer requires minor apriori system information for convergence, and the convergence condition arises in a natural manner with an apparently intuitive interpretation. Numerical and experimental studies are used to validate and demonstrate robust observer performance in the presence of significant measurement noise.
Similar content being viewed by others
References
Soatto, S., Perona, P.: Reducing structure from motion”: A general framework for dynamic vision part 1: modeling. IEEE Trans. Pattern Anal. Mach. Intell. 20(9), 933–942 (1998)
Chen, X., Kano, H.: A new state observer for perspective systems. IEEE Trans. Autom. Control 47(4), 658–663 (2002)
Karagiannis, D., Astol, A.: A new solution to the problem of range identification in perspective vision systems. IEEE Trans. Autom. Control 50(12), 2074–2077 (2005)
Jankovic, M., Ghosh, B.K.: Visually guided ranging from observations of points, lines and curves via an identier based nonlinear observer. Syst. Control Lett. 25, 63–73 (1995)
Dixon, W.E., Fang, Y., Dawson, D.M., Flynn, T.J.: Range identication for perspective vision systems. IEEE Trans. Autom. Control 48(12), 2232–2238 (2003)
Luca, A.D., Oriolo, G., Giordano, P.R.: On-Line Estimation of Feature Depth for Image-Based Visual Servoing Schemes. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 2823–2828, Roma (2007)
Dani, A.P., Fischer, N.R., Kan, Z., Dixon, W.E.: Globally exponentially stable observer for vision-based range estimation. Mechatronics 22(4), 381–389 (2012)
Ma, L., Chen, Y., Moore, K.L.: Range Identi?cation for Perspective Dynamic System with Single Homogeneous Observation. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 5207 −5211, New Orleans (2004)
Morbidi, F., Prattichizzo, D.: Range Estimation from a Moving Camera: an Immersion and Invariance Approach. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 2810–2815, Kobe (2009)
Grave, I., Tang, Y.: A new observer for perspective vision systems under noisy measurements. IEEE Trans. Autom. Control 60(2), 503–508 (2015)
Karagiannis, D., Carnevale, D., Astolfi, A.: Invariant manifold based reduced-order observer design for nonlinear systems. IEEE Trans. Autom. Control 53(11), 2602–2614 (2008)
Dahl, O., Wang, Y., Lynch, A.F., Heyden, A.: Observer forms for perspective systems. Automatica 46(11), 1829–1834 (2010)
Nath, N., Braganza, D., Dawson, D.M., Burg, T.: Range identification for perspective vision systems: a position based approach. Int. J. Robot. Autom. 206. doi:10.2316/Journal.206.2011.2.206-3409
Abdursal, R., Inaba, H., Ghosh, B.: Nonlinear observers for perspective time-invariant linear systems. Automatica 40(3), 481–490 (2004)
Soatto, S., Frezza, R., Perona, P.: Motion Estimation via Dynamic Vision. IEEE Trans. Autom. Control 41(41), 393–412 (1996)
Tsai, R. Y., Huang, T. S.: Estimating three-dimensional motion parameters of a rigid planar patch. IEEE Trans. Acoust. Speech Signal Process. 29(6), 1147–1152 (1981)
Dahl, O., Nyberg, F., Heyden, A.: Nonlinear and Adaptive Observers for Perspective Dynamic Systems. In: Proceedings of American Control Conference (ACC), pp. 1966–1971, New York (2007)
Chen, X., Kano, H.: State observer for a class of nonlinear systems and its application to machine vision. IEEE Trans. Autom. Control 49(11), 2085–2091 (2004)
Chitrakaran, V.K., Dawson, D.M., Dixon, W.E., Chen, J.: Identification of a moving objects velocity with a fixed camera. Automatica 41(3), 553–562 (2005)
Dani, A., Fischer, N., Dixon, W.E.: Single camera structure motion. IEEE Trans. Autom. Control 57(1), 238–243 (2012)
Matthies, L., Kanade, T., Szeliski, R.: Kalman filter based algorithms for estimating depth from image sequences. Int. J. Comput. Vis. 3(3), 209–236 (1989)
Sridhar, B., Soursa, R., Hussein, B.: Passive range estimation for rotorcraft low-altitude flight. Mach. Vis. Appl. 6(1), 10–24 (1993)
Chaumette, F., Boukir, S., Bouthemy, P., Juvin, D.: Structure from controlled motion. IEEE Trans. Pattern Anal. Mach. Intell. 18(5), 492–504 (1996)
Chiuso, A., Favaro, P., Jin, H., Soatto, S.: Structure from motion causally integrated over time. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 523–535 (2002)
Durrant-Whyte, H., Bailey, T.: Simultaneous localization and mapping (slam): Part II. IEEE Robot. Autom. Mag. 13(3), 108–117 (2006)
Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: Monoslam: Real-time single camera slam. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)
Ayache, N., Faugeras, O.: Maintaining representations of the environment of a mobile robot. IEEE Trans. Robot. Autom. 6(5), 804–819 (1989)
Broida, T.J., Chellappa, R.: Estimation of object motion parameters from noisy images. IEEE Trans. Pattern Anal. Mach. Intell. 8(1), 90–99 (1986)
Dickmanns, E.D., Graefe, V.: Dynamic monocular machine vision. Mach. Vis. Appl. 1, 223–240 (1988)
Faugeras, O.D., Ayache, N., Faverjon, B.: Building Visual Maps by Combining Noisy Stereo Measurements. In: Proceedings of IEEE Conference on Robotics and Automation (ICRA), San Francisco (1986)
Young, G.S., Chellappa, R.: 3D motion estimation using a sequence of noisy stereo images: models, estimation and uniqueness. IEEE Trans. Pattern Anal. Mach. Intell. 12(8), 735–759 (1990)
Reif, K., Sonnemann, F., Unbehauen, R.: An EKF-based nonlinear observer with a prescribed degree of stability. Automatica 34(9), 1119–1123 (1998)
Gurfil, P., Rotstein, H.: Partial aircraft state estimation from visual motion using the subspace constraints approach. J. Guid. Control. Dyn. 25(5), 1016–1028 (2001)
Keshavan, J., Escobar-Alvarez, H., Dimble, K. D., Humbert, J. S., Goerzen, C. L., Whalley, M. S.: Application of a nonlinear recursive visual-depth observer using UH60 flight data. J. Guid. Control. Dyn. 39(7), 1501–1512 (2016)
Ghosh, B. K., Inaba, H., Takahashi, S.: Identification of Riccati dynamics under perspective and orthographic observations. IEEE Trans. Autom. Control 45(7), 1267–1278 (2000)
Khalil, H. K.: Nonlinear Systems. Prentice Hall. Upper Saddle River, New Jersey (2002)
Conroy, J., Humbert, S. J.: Structure from Motion in Computationally Constrained Systems. In: Proceedings of SPIE 8725 (2013), doi:10.1117/12.2015296
Levant, A.: Robust exact differentiation via sliding mode technique. Automatica 34(3), 379–384 (1998)
Chawda, V., Celik, O., O’Malley, M. K.: Application of Levant’s Differentiator for Velocity Estimation and Increased Z-Width in Haptic Interfaces. In: IEEE World Haptics Conference, pp. 403–408, Istanbul (2011)
Lucas, B. D., Kanade, T.: An Iterative Image Registration Technique with an Application to Stereo Vision. In: Proceedings of the International Joint Conference on Artificial Intelligence, pp. 674–679 (1981)
Birchfield, S.: KLT: An implementation of the Kanade-Lucas-Tomasi feature tracker http://www.ces.clemson.edu/stb/klt/ (2007)
Shi, J., Tomasi, C.: Good Features to Track. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 593–600, Seattle (1994)
Bouguet, J.: Camera calibration toolbox for MATLAB http://www.vision.caltech.edu/bouguetj (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Keshavan, J., Humbert, J.S. An Optical Flow-Based Solution to the Problem of Range Identification in Perspective Vision Systems. J Intell Robot Syst 85, 651–662 (2017). https://doi.org/10.1007/s10846-016-0404-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-016-0404-6