Automated visual testing using trifocal analysis in an uncalibrated sequence of images

Automated visual testing using multiple views has been recently developed to automatically detect discontinuities in manufactured objects. The principal idea of this strategy is that, unlike the noise that appears randomly in images, only the discontinuities remain stable in a sequence of images because they remain in their position relative to the movement of the object being analyzed. This sort of multiple view imaging has been successfully applied in sequences of calibrated images for which the 3D → 2D transference function for the projection of the views is known precisely. Nonetheless, its application in industrial environments is difficult because of the instabilities inherent in the system. This investigation proposes a new strategy, based on the detection of discontinuities in a uncalibrated sequence of images. The methodology consists in constructing a model and carrying out a trifocal analysis that allows the determination of the real position of a discontinuity using corresponding control points in the sequence. Experimental results obtained on radioscopic images of die castings illustrate the potential in the detection of discontinuities in uncalibrated images, detecting the totality of the discontinuities in the sequence.