Interleaving 3D model feature prediction and matching to support multi-sensor object recognition

The object recognition, system presented combines on-line feature prediction with an iterative multisensor matching algorithm. Matching begins with an initial object type and pose hypothesis. An iterative generate-and-test procedure then refines the pose as well as the sensor-to-sensor registration for separate range and electro optical sensors. During matching, object features predicted to be visible are updated to reflect changes in hypothesized object pose and sensor registration. The match found is locally optimal in terms of the complete space of possible matches and globally consistent in the sense of preserving the 3D constraints implied by sensor and object geometry. Results on real data are presented which demonstrate the algorithm correcting for up to 30/spl deg/ errors in initial orientation and 5 m errors in initial translation.

[1]  Allen R. Hanson,et al.  Model-based fusion of FLIR, color, and ladar , 1995, Other Conferences.

[2]  P. Wintz,et al.  An efficient three-dimensional aircraft recognition algorithm using normalized fourier descriptors , 1980 .

[3]  Jin-Long Chen,et al.  Determining Pose of 3D Objects With Curved Surfaces , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Precompiling a Geometrical Model into an Interpretation Tree for Object Recognition in Bin-picking Tasks , 1987 .

[5]  J. Ross Beveridge,et al.  Object to Multisensor Coregistration with Eight Degrees of Freedom , 1994 .

[6]  Mark R. Stevens,et al.  Optical Linear Feature Detection Based on Model Pose. , 1995 .

[7]  C. H. Liu,et al.  3-D curved object recognition from multiple 2-D camera views , 1990 .

[8]  J.L. Chen,et al.  Recovering and tracking pose of curved 3D objects from 2D images , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  W. Brent Seales,et al.  Modeling the rim appearance , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[10]  David J. Kriegman,et al.  On using CAD models to compute the pose of curved 3D objects , 1992, CVGIP Image Underst..

[11]  D. Marr,et al.  Analysis of occluding contour , 1977, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[12]  Charles R. Dyer,et al.  3-D multiview object representations for model-based object recognition , 1987, Pattern Recognit..

[13]  Mark R. Stevens,et al.  Toward Target Verification Through 3-D Model-Based Sensor Fusion , 1996 .

[14]  J. K. Aggarwal,et al.  SHAPE RECOGNITION FROM SINGLE SILHOUETTES. , 1987 .

[15]  Yuan-Fang Wang,et al.  Matching Three-Dimensional Objects Using Silhouettes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Michael E. Goss,et al.  Reduction of BRL / CAD Models and Their Use in Automatic Target Recognition Algorithms , 1995 .

[17]  G. Paltridge,et al.  Radiative processes in meteorology and climatology , 1976 .

[18]  Bruce A. Draper,et al.  Progress on Target and Terrain Recognition Research at Colorado State University. , 1995 .

[19]  Cheng-Hsiung Liu,et al.  3D Curved Object Recognition from Multiple 2D Camera Views , 1990, Comput. Vis. Graph. Image Process..

[20]  Geoffrey D. Sullivan,et al.  Visual Object Recognition Using Deformable Models of Vehicles , 1995 .

[21]  C. Dyer,et al.  The asp: a continuous, viewer-centered object representation for computer vision , 1988 .