Dynamic few-view X-ray imaging for inspection of CAD-based objects. (15th October 2021)

• Record Type: Journal Article
• Authors: Presenti, Alice; Sijbers, Jan; De Beenhouwer, Jan
• Is Part Of: Expert systems with applications. Volume 180(2021)
• Publication Date: 2021-10-15
• Subjects: Few-view inspection -- CAD -- Dynamic acquisition -- Visibility angles -- Pose estimation; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2021.115012
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Projection-based 3D inspection is possible if task-specific projections are acquired. Radiographs are dynamically acquired close to a pre-defined set of optimal projections. 2D/3D pose estimation reaches subpixel accuracy. Abstract: X-ray 3D Computed Tomography (3DCT) has great potential for inspection of industrial products. Unfortunately, conventional CT-based workflows to inspect objects created from a CAD model involve a time-consuming acquisition process, computationally expensive image reconstruction, and multiple postprocessing steps, preventing them from inline usage. In this paper, we propose DynaPose, a fast and yet accurate workflow for 3D X-ray inspection of objects created from a CAD model. By exploiting prior knowledge of the CAD model, and relying on only very few radiographs, inspection can be performed in real-time. The DynaPose method allows automated 3D pose estimation of the object to be inspected while dynamically acquiring radiographs that are optimal for the detection task. Through simulation and real experiments, we show that our approach paves the way for inline inspection of manufactured objects.