Visual-Based Manufacturing Platform Level Detection Method

This paper proposes a visual-based method for detecting the tilt angles of a platform using a single image. A particular circular reference object is used to provide information of the tilt angles via projective geometry. The image features of the reference object extracted by the basic rectangle and corner detection algorithm are used for ANFIS to estimate the tilt angles. The method is verified by simulation that it can detect the tilt angles very closely. Moreover, the method offers a very easy and low-cost approach for manufacturing applications.