A CAD driven multiscale approach to automated inspection

Abstract

In this paper we develop a general multiscale stochastic object detection algorithm for use in an automated inspection application. Information from a CAD model is used to initialize the object model and guide the training phase of the algorithm. An object is represented as a stochastic tree, where each node of the tree is associated with one of the various object components used to locate and identify the part. During the training phase a number of model paramete~s are estimated from a set of training images, some of which are generated from the CAD model. The algorithm then uses a fast multiscale search strategy to locate and identify the subassemblies making up the object tree. We demonstrate the performance of the algorithm on a typical mechanical assembly.

A multiscale stochastic image model for automated inspection

“…In this paper, which builds on the work presented in [20], [21], and [22], we develop a model-based inspection algorithm designed to detect assembly errors in a rigid object from a single monochrome image of the object. Since the algorithm is designed specifically for automated inspection, we can take advantage of the highly structured viewing conditions typically found in a factory environment.…”