Biologically plausible visual homing methods based on optical flow techniques

Insects are able to return to important places in their environment by storing an image of the surroundings while at the goal, and later computing a home direction from a matching between this 'snapshot' image and the currently perceived image. Very similar ideas are pursued for the visual navigation of mobile robots. A wide range of different solutions for the matching between the two images have been suggested. This paper explores the application of optical flow techniques for visual homing. The performance of five different flow techniques and a reference method is analysed based on image collections from three different indoor environments. We show that block matching, two simple variants of block matching and two even simpler differential techniques produce robust homing behaviour, despite the simplicity of the matched features. Our analysis reveals that visual homing can succeed even in the presence of many incorrect feature correspondences, and that low-frequency features are sufficient for homing. In particular, the successful application of differential methods opens new vistas on the visual homing problem, both as plausible and parsimonious models of visual insect navigation, and as a starting point for novel robot navigation methods.

[1]  R. Cassinis,et al.  Using colour information in an omnidirectional perception system for autonomous robot localization , 1996, Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96).

[2]  R Möller,et al.  Do insects use templates or parameters for landmark navigation? , 2001, Journal of theoretical biology.

[3]  Ralf Möller.  Visual homing without image matching , 2002 .

[4]  Thomas S. Collett,et al.  Memory use in insect visual navigation , 2002, Nature Reviews Neuroscience.

[5]  Ales Leonardis,et al.  Panoramic Eigenimages for Spatial Localisation , 1999, CAIP.

[6]  H G Krapp,et al.  Neuronal matched filters for optic flow processing in flying insects. , 2000, International review of neurobiology.

[7]  David Kortenkamp,et al.  Cognitive maps for mobile robots: A representation for mapping and navigation , 1993 .

[8]  T. S. Collett,et al.  Landmark maps for honeybees , 1987, Biological Cybernetics.

[9]  Dimitrios Lambrinos,et al.  Inse t Strategies of Visual Homing in Mobile , 1998 .

[10]  Ralf Möller,et al.  Insects could exploit UV-green contrast for Landmark navigation. , 2002, Journal of theoretical biology.

[11]  S. Al-Moghrabi,et al.  Inorganic carbon uptake for photosynthesis by the symbiotic coral-dinoflagellate association II. Mechanisms for bicarbonate uptake , 1996 .

[12]  Dimitrios Lambrinos,et al.  Insect Strategies of Visual Homing in Mobile Robots , 1998 .

[13]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[14]  Luc Van Gool,et al.  Vision Based Intelligent Wheel Chair Control: The Role of Vision and Inertial Sensing in Topological Navigation , 2004, J. Field Robotics.

[15]  Andrew Vardy,et al.  A Scale Invariant Local Image Descriptor for Visual Homing , 2005, Biomimetic Neural Learning for Intelligent Robots.

[16]  Andrew Vardy,et al.  Anatomy and Physiology of an Artificial Vision Matrix , 2004, BioADIT.

[17]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[18]  M. Land.  Visual acuity in insects. , 1997, Annual review of entomology.

[19]  Verena V. Hafner.  Adaptive navigation strategies in biorobotics: visual homing and cognitive mapping in animals and machines , 2004 .

[20]  R. Pfeifer,et al.  A mobile robot employing insect strategies for navigation , 2000, Robotics Auton. Syst..

[21]  Benjamin J. Kuipers,et al.  A Robust, Qualitative Approach To A Spatial Learning Mobile Robot , 1989, Optics East.

[22]  Giovanni M. Bianco,et al.  The turn-back-and-look behaviour: bee versus robot , 2000, Biological Cybernetics.

[23]  Svetha Venkatesh,et al.  Insect-Inspired Robotic Homing , 1999, Adapt. Behav..

[24]  R. Hengstenberg,et al.  Estimation of self-motion by optic flow processing in single visual interneurons , 1996, Nature.

[25]  Holk Cruse,et al.  A recurrent network for landmark-based navigation , 2003, Biological Cybernetics.

[26]  Hobart R. Everett,et al.  Where am I?" sensors and methods for mobile robot positioning , 1996 .

[27]  Emanuele Trucco,et al.  Introductory techniques for 3-D computer vision , 1998 .

[28]  David J. Fleet,et al.  Performance of optical flow techniques , 1994, International Journal of Computer Vision.

[29]  T. S. Collett,et al.  Landmark learning in bees , 1983, Journal of comparative physiology.

[30]  Michael F. Land,et al.  Variations in the Structure and Design of Compound Eyes , 1989 .

[31]  Carme Torras,et al.  Detecting salient cues through illumination-invariant color ratios , 2004, Robotics Auton. Syst..

[32]  T. Collett,et al.  Insect navigation en route to the goal: multiple strategies for the use of landmarks , 1996, The Journal of experimental biology.

[33]  S. Gourichon,et al.  Estimating ego-motion using a panoramic sensor: Comparison between a bio-inspired and a camera-calibrated method , 2003 .

[34]  R. Wehner,et al.  Visual navigation in insects: coupling of egocentric and geocentric information , 1996, The Journal of experimental biology.

[35]  Luc Van Gool,et al.  Vision Based Intelligent Wheel Chair Control: The Role of Vision and Inertial Sensing in Topological Navigation , 2004 .

[36]  Ralf Möller,et al.  A Biorobotics Approach to the Study of Insect Visual Homing Strategies , 2002 .

[37]  Bernhard Schölkopf,et al.  Learning view graphs for robot navigation , 1997, AGENTS '97.

[38]  J. Stewart.  Calculus: Early Transcendentals , 1988 .

[39]  Holger G. Krapp,et al.  Wide-field, motion-sensitive neurons and matched filters for optic flow fields , 2000, Biological Cybernetics.

[40]  J. Aloimonos,et al.  Finding motion parameters from spherical motion fields (or the advantages of having eyes in the back of your head) , 1988, Biological Cybernetics.

[41]  W. Ribi,et al.  The Structural Basis of Information Processing in the Visual System of the Bee , 1987 .

[42]  Edward M. Riseman,et al.  Image-based homing , 1991, IEEE Control Systems.

[43]  Hanspeter A. Mallot,et al.  Vision-Based Homing with a Panoramic Stereo Sensor , 2002, Biologically Motivated Computer Vision.

[44]  Anil K. Jain,et al.  Displacement Measurement and Its Application in Interframe Image Coding , 1981, IEEE Trans. Commun..

[45]  Jochen Zeil,et al.  Catchment areas of panoramic snapshots in outdoor scenes. , 2003, Journal of the Optical Society of America. A, Optics, image science, and vision.

[46]  H. Hertel,et al.  Processing of Visual Information in the Honeybee Brain , 1987 .

[47]  R. C. Nelson.  Visual homing using an associative memory , 2004, Biological Cybernetics.

[48]  Edward M. Riseman,et al.  Image-based homing , 1992 .

[49]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[50]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[51]  Jean-Arcady Meyer,et al.  Using Coloured Snapshots For Short-Range Guidance In Mobile Robots , 2002 .

[52]  B. Webb,et al.  Can robots make good models of biological behaviour? , 2001, Behavioral and Brain Sciences.

[53]  T. S. Collett,et al.  Biological compasses and the coordinate frame of landmark memories in honeybees , 1994, Nature.

[54]  P. Gaussiera,et al.  The visual homing problem : An example of robotics / biology cross fertilization , 1999 .

[55]  Alessandro Rizzi,et al.  A novel visual landmark matching for a biologically inspired homing , 2001, Pattern Recognit. Lett..

[56]  N. Strausfeld.  Atlas of an Insect Brain , 1976, Springer Berlin Heidelberg.

[57]  William Bialek,et al.  Statistics of Natural Images: Scaling in the Woods , 1993, NIPS.

[58]  Ralf Möller,et al.  Insect visual homing strategies in a robot with analog processing , 2000, Biological Cybernetics.

[59]  Andrew Vardy,et al.  Low-Level Visual Homing , 2003, ECAL.

[60]  Bernhard Schölkopf,et al.  Where did I take that snapshot? Scene-based homing by image matching , 1998, Biological Cybernetics.

[61]  Hanspeter A. Mallot,et al.  Biomimetic robot navigation , 2000, Robotics Auton. Syst..

[62]  J. H. van Hateren,et al.  Modelling the Power Spectra of Natural Images: Statistics and Information , 1996, Vision Research.

[63]  Thomas Röfer,et al.  Controlling a Wheelchair with Image-based Homing , 1997 .

[64]  Andrew Vardy,et al.  Biologically plausible methods for robot visual homing , 2005 .

[65]  Shree K. Nayar,et al.  Ego-motion and omnidirectional cameras , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[66]  Verena V. Hafner,et al.  Adaptive Homing—Robotic Exploration Tours , 2001, Adapt. Behav..

[67]  Panos E. Trahanias,et al.  A framework for visual landmark identification based on projective and point-permutation invariant vectors , 2001, Robotics Auton. Syst..

[68]  Alun M. Anderson.  A model for landmark learning in the honey-bee , 2004, Journal of comparative physiology.

[69]  James J. Little,et al.  Mobile Robot Localization and Mapping with Uncertainty using Scale-Invariant Visual Landmarks , 2002, Int. J. Robotics Res..