Automatic orientation and recognition in highly structured scenes

Abstract The paper discusses the impact of scene and assessment models for videometry. The role of geometric and semantic scene knowledge for 3D-modeling is discussed as well as the impact on the 3D-reconstruction process and the accuracy of results. Three issues are covered: the automation of orientation and calibration procedures, the recognition for 3D-mensuration and automatic 3D-reconstruction. Full automation of calibration and orientation procedures appears to be necessary for enlarging the field of applications also for non-specialists. Explicit geometric information and semantic knowledge about the scene are needed to achieve reliable 3D-descriptions. The focus of achieving highest possible accuracy needs to be embedded into a broader context of scene analysis. Models must be able to reflect the different aggregation layers of composite objects to automatically identify object parts in the image data. Examples are given on the role of projective geometry for automatic calibration, the role of scene knowledge for automatic orientation and on traffic light program for automatic evaluation. They demonstrate the feasibility of tools from computer vision for image metrology.

[1]  Steffen Abraham,et al.  Towards autonomous high-precision calibration of digital cameras , 1997, Optics & Photonics.

[2]  Andrew Zisserman,et al.  Geometric invariance in computer vision , 1992 .

[3]  Andrew W. Fitzgibbon,et al.  An Experimental Comparison of Range Image Segmentation Algorithms , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Wolfgang Förstner,et al.  A Framework for Low Level Feature Extraction , 1994, ECCV.

[5]  W. Baarda,et al.  A testing procedure for use in geodetic networks. , 1968 .

[6]  Olivier D. Faugeras,et al.  What can be seen in three dimensions with an uncalibrated stereo rig , 1992, ECCV.

[7]  Wolfgang Förstner,et al.  Semantic Modeling for the Acquisition of Topographic Information from Images and Maps: Smati 97 , 1997 .

[8]  Sabry F. El-Hakim,et al.  Configuration design for sensor integration , 1995, Other Conferences.

[9]  Wolfgang Förstner,et al.  Object Location Based on Uncertain Models , 1989, DAGM-Symposium.

[10]  Herbert Süße,et al.  Invariant Fitting of Planar Objects by Primitives , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  W. Baarda,et al.  Statistical concepts in geodesy. , 1967 .

[12]  M. Isabel Ribeiro,et al.  3D scene modeling from multiple range views , 1995, Other Conferences.

[13]  Richard I. Hartley,et al.  A linear method for reconstruction from lines and points , 1995, Proceedings of IEEE International Conference on Computer Vision.

[14]  Amnon Shashua,et al.  Trilinearity in Visual Recognition by Alignment , 1994, ECCV.

[15]  Peter J. Rousseeuw,et al.  Robust regression and outlier detection , 1987 .

[16]  Paul F. Whelan,et al.  Machine vision systems: proverbs, principles, prejudices, and priorities , 1994, Other Conferences.

[17]  Robert M. Haralick,et al.  Performance Characterization in Computer Vision , 1993, BMVC.

[18]  Paul A. Beardsley,et al.  3D Model Acquisition from Extended Image Sequences , 1996, ECCV.

[19]  Richard I. Hartley,et al.  Estimation of Relative Camera Positions for Uncalibrated Cameras , 1992, ECCV.

[20]  Amnon Krupnik.  Multiple-patch matching in the object space for aerotriangulation / , 1994 .

[21]  Katsushi Ikeuchi,et al.  Modeling sensor detectability and reliability in the configuration space for model-based vision , 1987 .

[22]  Jake K. Aggarwal,et al.  Model-based object recognition in dense-range images—a review , 1993, CSUR.

[23]  Stephen T. Barnard,et al.  Interpreting Perspective Image , 1983, Artif. Intell..

[24]  W. Föstner.  Reliability analysis of parameter estimation in linear models with application to mensuration problems in computer vision , 1987 .

[25]  Jake K. Aggarwal,et al.  Determining vanishing points from perspective images , 1984, Comput. Vis. Graph. Image Process..