POLYOC: Photogrammetric Measurements of Buildings and Architectural Models via Multi-View Steoreovision

We present a new method to derive a reliable 3D description of buildings and architectural models based on stereo vision using multiple camera views. This multi-view stereo technique has been successfully applied to many objects and has proved to be more reliable and more accurate than the well known binocular and even trinocular stereo techniques. The method has the following attractive features: (-) Flexibility: Arbitrary positions of an arbitrary amount of different camera views are allowed. (-) Automatic Calibration of each camera view is obtained by a simple procedure. (-) Reliable Stereo Analysis: The matching of corresponding image features of different images relies on a basic paradigm of Hypothesis Prediction and Validation. (-) Knowledge Base: Heuristics can be applied to correct the object reconstruction. (-) CAD-lnterface: The 3D description of the reconstructed object can automatically transferred via DXF to a CAD-system. (-) Low Costs: No special and expensive technical equipment like a laser or an UV rangefinder is necessary. A camera, a PC with CAD-system and a digitizing device like a digitizing tablet with a pointing pen are sufficient.

[1]  Takeo Kanade,et al.  Stereo by Intra- and Inter-Scanline Search Using Dynamic Programming , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  N. Ayache,et al.  Trinocular Stereovision: Recent Results , 1987, IJCAI.

[3]  Charles Hansen,et al.  Rectification of images for binocular and trinocular stereovision , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[4]  S. Ullman,et al.  The interpretation of visual motion , 1977 .

[5]  W. Eric L. Grimson,et al.  Computational Experiments with a Feature Based Stereo Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  William B. Thompson,et al.  Disparity Analysis of Images , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  KING-CHiA HUNG,et al.  Polyhedron reconstruction using three-view analysis , 1989, Pattern Recognit..

[8]  Stefan Posch,et al.  Hierarchische linienbasierte Tiefenbestimmung in einem Stereobild , 1988, GWAI.