Data-Driven Learning for Calibrating Galvanometric Laser Scanners

Abstract

State-of-the-art calibration very often constructs models motivated by a real-world device. Recently, artificial neural networks (ANNs) have been proposed as a more universal, accurate, and practical black-box approach. For a galvanometric triangulation device based on two mirrors, we embrace this proposal and set it into context with other supervised data-driven approaches: 1) ridge regression; 2) support vector regression; and 3) Gaussian processes. We show that they outperform available model-based approaches and yield similar performance compared with a memorizing lookup table calibration. The results demonstrate that an off-the-shelf usage of ANNs may run into generalization problems. Restricting the space of functions using kernel-based learning has proven to be advantageous. Finally, all approaches and distinct properties are discussed in a broader context, since each application entails differently relevant requirements for its calibration. This also holds for any calibration other than the considered triangulation device.

Modeling and Calibration of the Galvanometric Laser Scanning Three-Dimensional Measurement System

“…Manakov [10] introduced a method to calibrate the two-mirror galvanometric laser scanner but it's hard to deal with the optimization of the system's mathematical model. Wissel [11] proposed a datadriven learning calibration method which needs to collect a large number of data. Wagner [12] used statistical learning methods such as artificial neural networks (ANNS) and linear regression to calibrate the system, but this approach is easy to cause over-fitting problem and often has a high computational cost.…”

Effective Data-Driven Calibration for a Galvanometric Laser Scanning System Using Binocular Stereo Vision

“…If the other nonlinear methods (like the Support Vector Machine (SVM), the Gaussian Processes (GPs)) are used to solve this problem, it will lead to explosive time growth for GLS system calibration. As mentioned by Wissel et al [ 20 ], the training time by SVM is 8.91 min, and the time by GPs is more than 20 h. Moreover, the number of the training sample in their experiments (7193 points) is less than one tenth of ours (90,000 points). As we all know, the training time of the model is proportional to the number of the training sample.…”

“…So, it is applicable to both forward and backward applications. However, the calibrated mapping of the data-driven triangulation method [ 20 ] contains the 2D image coordinates of the laser spot in its 4D input, leading to the inapplicability for the backward applications.…”

“…In the real 3D Reconstruction experiment, we choose the surface of an engine blade as reconstructed object since it is a free-form surface. In addition, 3D reconstruction of the engine blade by the date-driven triangulation method [ 20 ] is also implemented for comparison. To evaluate the reconstruction accuracy, we use the commercial ATOS system (GOM, Brunswick, Germany) to measure the surface in advance.…”

“…The large amount of variables in the universal models are irrespective of specific physical meaning and are usually determined by means of supervised learning from a training data set, so they are also called data-driven methods. Along this line, Wissel et al [ 20 ] calibrated a galvanometric triangulation device, in which a GLS system and a camera constitute a fixed triangulation structure. However, their calibration result is only applicable for the specific triangulation setup to measure the shape of 3D objects, not applicable for the backward applications mentioned above.…”