Abstract
See-and-avoid behaviors are an essential part of autonomous navigation for Unmanned Air Vehicles (UAVs). To be fully autonomous, a UAV must be able to navigate complex urban and near-earth environments and detect and avoid imminent collisions. While there have been significant research efforts in robotic navigation and obstacle avoidance during the past few years, this previous work has not focused on applications that use small autonomous UAVs. Specific UAV requirements such as non-invasive sensing, light payload, low image quality, high processing speed, long range detection, and low power consumption, etc., must be met in order to fully use this new technology. This paper presents single camera collision detection and avoidance algorithm. Whereas most algorithms attempt to extract the 3D information from a single optical flow value at each feature point, we propose to calculate a set of likely optical flow values and their associated probabilities—an optical flow probability distribution. Using this probability distribution, a more robust method for calculating object distance is developed. This method is developed for use on a UAV to detect obstacles, but it can be used on any vehicle where obstacle detection is needed.
Similar content being viewed by others
References
Koch, R.: 3D Surface Reconstruction from stereoscopic image sequences. In: Proceedings of the Fifth International Conference on Computer Vision, pp. 109–114. Cambridge, MA (1995)
Gonzalez, R.C., Cancelas, J.A., Alvarez, J.C., Fernandez, J.A., Enguita, J.M.: Fast stereo vision algorithm for robotic applications. In: Proceedings of IEEE International Conference on Emerging Technologies and Factory Automation (ETFA ‘99), vol.1, pp. 97–104. Barcelona, Spain (1999)
Gimel’farb, G.L.: Intensity-based bi- and trinocular stereo vision: Bayesian decisions and regularizing assumptions. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, Conference A: Computer Vision and Image Processing, vol.1, pp. 717–719. Jerusalem, Israel (1994)
Ruichek, Y., Issa, H., Postaire, J.-G.: Approach for obstacle detection using linear stereo vision. In: Proceedings of the IEEE Intelligent Vehicles Symposium 2000. Dearborn, MI (2000)
Goldberg D.E.: Genetic Algorithms in Search Optimization and Machine Learning. Addison-Wesley, Reading (1989)
Cantu-Paz E.: Efficient and Accurate Parallel Genetic Algorithms. Kluwer Academic Publishers, Boston (2000)
Chambers L.: The Practical Handbook of Genetic Algorithms: Applications. Chapman and Hall, Boca Raton (2001)
Woo, S., Dipanda, A.: Matching lines and points in an active stereo vision system using genetic algorithms. In: Proceedings International Conference on Image Processing, vol.3, pp. 332–335. Vancouver, BC (2000)
Olson C.F., Matthies L.H., Schoppers M., Maimone M.W.: Rover navigation using stereo ego-motion. Robot. Auton. Syst. 43(4), 215–229 (2003)
Gandhi, R.K.T., Devadiga, S., Camps, O.: Detection of obstacles on runway using egomotion compensation and tracking of significant features. In: Proceedings 3rd IEEE Workshop on Applications of Computer Vision, pp. 168–173. WACV 96 (1996)
Krishnan S., Raviv D.: 2D feature tracking algorithm for motion analysis. Pattern Recognit. 28, 1103– (1995)
Desouza G., Kak A.: Vision for mobile robot navigation: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 24, 237– (2002)
Illah C.T., Nourbakhsh R., Andre D., Genesereth M.R.: Mobile robot obstacle avoidance via depth from focus. Robot. Autonom. Syst. 22, 151–158 (1997)
Petland, Darrell, T., Turk, M., Huang, W.: A simple real-time range camera. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 256–261 (1989)
Darrell, T., Wohn, K.: Pyramid based depth from focus. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 504–509 (1988)
Rioux M., Blais F.: Compact three-dimensional cameras for robotic applications. J. Opt. Soc. Am. 3(9), 1518– (1986)
Guissin, R., Ullman, S.: Direct computation of the focus of expansion from velocity field measurements. In: Proceedings of the IEEE Workshop on Visual Motion, pp. 146–155, Oct 1991
Convertino B.G., Distante A.: Focus of expansion estimation with a neural network. IEEE Int. Conf. Neural Networks 3, 1693– (1996)
Rangarajan K., Shah M.: Interpretation of motion trajectories using focus of expansion. IEEE Trans. Pattern Anal. Mach. Intell. 14, 1205– (1992)
Burger, W., Bhanu, B.: On computing a “fuzzy” focus of expansion for autonomous navigation. In: Proceedings CVPR ‘89., IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 563–568, Jun 1989
Lonquet-Higgins H.C.: A computer algorithm for reconstructing a scene from two projections. Nature 293, 133– (1981)
Faugeras, O.D., Mourrain, B.: What can be seen in three dimensions with an uncalibrated stereo rig? Eur. Conf. Comput. Vis. (ECCV), pp. 563–576 (1992)
Hartley, R.I.: Estimation of relative camera positions for uncalibrated cameras. Eur. Conf. Comput. Vis. (ECCV), pp. 579–587 (1992)
Tomasi C., Kanade T.: Shape and motion from image streams under orthography: a factorization method. Int. J. Comput. Vis. 9, 137– (1992)
Jepson A., Heeger D.: Linear Subspace Methods for Recovering Translational Direction. Cambridge University Press, (1992)
Thomas I., Simoncelli E.: Linear Structure from Motion. Technical Report IRCS 94–26. University of Pennsylvania, (1994)
Oliensis J., Genc Y.: Fast algorithms for projective multi-frame structure from motion. Proc. IEEE Int. Conf. Comput. Vis. 1, 536– (1999)
Oliensis J.: Multi-frame structure-from-motion algorithm under perspective projection. Int. J. Comput. Vis. 34(2/3), 163– (1999)
Broida T.J., Chellappa R.: Estimating the kinematics and structure of a rigid object from a sequence of monocular images. IEEE Trans. Pattern Anal. Mach. Intell. 13, 497– (1991)
Oliensis J., Thomas J.I.: Incorporating motion error in multi-frame structure from motion. IEEE Trans. Pattern Anal. Mach. Intell. 21, 665– (1999)
Soatto S., Perona P.: Rucursive 3D visual-motion estimation using subspace constraints. Int. J. Comput. Vis. 22, 235– (1997)
Xiong Y., Shafer S.A.: Dense structure from a dense optical flow sequence. Comput. Vis. Image Underst. 69(2), 222– (1998)
Oliensis, J.: Direct Multi-Frame Structure from Motion for Hand-Held Cameras. Proc. Int. Conf. Pattern Recognit., pp. 889–895 (2000)
Oliensis, J.: Multiframe structure from motion in perspective. In: Proceedings IEEE Workshop on Representation of Visual Scenes, pp. 77–84 (1995)
Shum, H.Y., Ke, Q., Zhang, Z.: Efficient bundle adjustment with virtual key frames: a hierarchical approach to multi-frame structure from motion. Proc. Conf. Comput. Vis. Pattern Recognit., pp. 538–543 (1999)
Favaro, P., Jin, H., Soatto, S.: A semi-direct approach to structure from motion. Int. Conf. Image Anal. Proc., pp. 250–255 (2001)
Oliensis, J.: Direct multi-frame structure from motion for hand-held cameras. Proc. Int. Conf. Pattern Recognit., pp. 889–895 (2000)
Beardsley, P., Torr, P., Zisserman. A.: 3D Model acquisition from extended image sequences. Eur. Conf. Comput. Vis. (ECCV), pp. 683–695 (1996)
Forsyth, D., Ioffe, S., Haddon, J.: Bayesian structure from motion. Int. Conf. Comput. Vis. (ICCV), pp. 660–665 (1999)
Zhang Z.: Determining the epipolar geometry and its uncertainty—a review. Int. J. Comput. Vis. 27(2), 161– (1998)
Merrell, P.C.: Structure from motion using optical flow probability distributions. Master’s Thesis, Brigham Young University (2005)
Thomas, I., Simoncelli, E.: Linear Structure from Motion. Technical Report IRCS, pp. 94–26. University of Pennsylvania (1994)
Aanaes H., Fisker R., Astrom K., Carstensen J.M.: Robust Factorization. IEEE Trans. Pattern Anal. Mach. Intell. 24, 1215– (2002)
Gruber A., Weiss Y.: Multibody factorization with uncertainty and missing data using the EM algorithm. Proc. Conf. Comput. Vis. Pattern Recognit. 1, I:707– (2004)
Irani, M., Anandan, P.: Factorization with uncertainty. Proc. Eur. Conf. Comput. Vis., pp. 539–553 (2000)
Morris, D.D., Kanade, T.: A unified factorization algorithm for points, line segments, and planes with uncertainty models. Int. Conf. Comput. Vis., pp. 696–702 (1998)
Poelman C.J., Kanade T.: A paraperspective factorization method for shape and motion recovery. IEEE Trans. Pattern Anal. Mach. Intell. 19, 206– (1997)
Zucchelli M., Santos-Victor J., Christensen H.I.: Maximum likelihood structure from motion estimation integrated over time. Int. Conf. Pattern Recognit. 4, 260– (2002)
Dellaert F., Seitz S.M., Thrope C.E., Thrun S.: Structure from motion without correspondence. Proc. Conf. Comput. Vis. Pattern Recognit. 2, 557– (2000)
Soatto, S., Brocket, R.: Optimal structure from motion: local ambiguities and global estimates. Proc. Conf. Comput. Vis. Pattern Recognit., pp. 282–288 (1998)
Chiuso R.B., Soatto S.: Optimal structure from motion: local ambiguities and global estimates. Int. J. Comput. Vis. 39, 195– (2000)
Simoncelli, E.P., Adelson, E.H., Heeger, D.J.: Probability distributions of optical flow. Proc. Conf. Comput. Vis. Pattern Recognit., pp. 310–315 (1991)
Anandan P.: A computation framework and an algorithm for the measurement of visual motion. Int. J. Comput. Vis. 2, 283– (1989)
Szeliski R.: Bayesian modeling of uncertainty in low-level vision. Int. J. Comput. Vis. 5(3), 271– (1990)
Merrell, P.C., Lee, D.J., Beard, R.W.: Obstacle Avoidance for Unmanned Air Vehicles Using Optical Flow Probability Distributions. SPIE Optics East, Robotics Technologies and Architectures, Mobile Robots XVII, vol. 5609–04. Philadelphia (2004)
Merrell, P.C., Lee, D.J., Beard, R.W.: Statistical Analysis of Multiple Optical Flow Values for Estimation of Unmanned Air Vehicles Height Above Ground. SPIE Optics East, Robotics Technologies and Architectures, Intelligent Robots and Computer Vision XXII, vol. 5608–28. Philadelphia (2004)
Sun Z., Tekalp A.M., Ramesh V.: Error characterization of the factorization method. Comput. Vis. Image Underst. 82(2), 10– (2001)
Anderson, J.D., Lee, D.J., Edwards, B.B., Archibald, J.K., Greco, C.R.: Real-time Feature Tracking on an Embedded Vision Sensor for Small Vision-guided Unmanned Vehicles. In: The 7th IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA2007), pp. 55–60. Jacksonville June 20–23 (2007)
Wei, Z.Y., Lee, D.J., Nelson, B.E., Martineau, M.A.: A Fast and Accurate Tensor-based Optical Flow Algorithm Implemented in FPGA. In: IEEE Workshop on Applications of Computer Vision (WACV 2007), pp. 18–23. Austin Feb 21–22 (2007)
Wei Z.Y., Lee D.J., Nelson B.E.: FPGA-based Real-time Optical Flow Algorithm Design and Implementation. J. Multimed. 2(5), 38–45 (2007)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lee, DJ., Merrell, P., Wei, Z. et al. Two-frame structure from motion using optical flow probability distributions for unmanned air vehicle obstacle avoidance. Machine Vision and Applications 21, 229–240 (2010). https://doi.org/10.1007/s00138-008-0148-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-008-0148-9