AUTOMATED KNOWLEDGE-BASED SYSTEM FOR STEREO VIDEO METROLOGY

A knowledge-based system has been developed to help inexperienced user s make measurements from stereo video images. The purpose of the syste m is to automate much of the routine functions and decision making in photogrammetric measurements on a personal computer (PC). The system c an perform the following functions: (1) Check the validity of the inpu t data; (2) warn of weak geometric conditions; (3) provide guidance, d iagnostics, and counseling during success and failure modes; (4) condu ct robust blunder detection; and (5) perform accuracy analysis through error propagation. The result was the development of a user-friendly vision system that can be used productively without in-depth knowledge of photogrammetry. Experimental results showed that the PC-based visi on system achieved a potential accuracy of about one pixel on the imag e plane for planar coordinates. Lower measurement accuracy in the rang e of 4-5 pixels was obtained for the depth direction because of the in tersection geometry and accuracy limitations in manual image matching. The statistical analysis scheme, based on random error propagation of the image coordinates, was a realistic accuracy estimator. Calculated three-dimensional (3D) measurement errors consistently fell within th ree times the estimated standard errors (3 sigma). Comparison with act ual survey measurements showed that distances could be measured with a n accuracy of better than 2 pixels, while volume and surface area were measured to within 3%. Image scale, base/object distance ratio; numbe r and distribution of control points, and accuracy limitation in manua l matching had a significant impact on the measurement accuracy.