Practical Pose Estimation Method for Industrial X-ray Radiography Based on Deep Learning and Local Template Matching

With the increasing integration of industrial products, critical components are often enclosed within shells, making it difficult to measure their actual positions during assembly using contact measurement techniques. This often results in substandard product quality. X-ray imaging offers a non-destructive solution for inspecting internal structures and accurately positioning internal components. However, traditional pose estimation methods based on X-ray imaging rely on projection optimization, which is time-consuming and cannot meet the timely feedback requirements of assembly processes. In this work, we propose a pose estimation method for industrial X-ray radiography that combines neural networks for initial pose estimation with local template matching for pose refinement. This approach achieves high accuracy and efficiency in positioning internal targets. We conducted real X-ray imaging experiments on several objects, including a terahertz anode tube model. The mean alignment error was approximately 0.2 mm, which is lower than the spatial resolution (about 0.25 mm) of the CT images constructed from the same X-ray projections. The running time for pose estimation of a single object was about 10 seconds, significantly faster than conventional methods that take several minutes, making it suitable for timely feedback in industrial assembly processes.