Faro Technologies, Inc.

Georgios Balatzis

Ariane Stiebeiner

Matthias Wolke

Michael Müller

Francesco Bonarrigo

Andrea Riccardi

Stefan Wagner

Festim Xhohaj

Antonin Klopp-tosser

Tharesh Sharma

Examples described herein provide a method that includes aligning, by a processing device, a measured point cloud for an object with reference data for the object. The method further includes comparing, by the processing device, the measurement point cloud to the reference data to determine a displacement value between each point in the measurement point cloud and a corresponding point in the reference data. The method further includes generating, by the processing device, a deviation histogram of the displacement values between each point in the measurement point cloud and the corresponding point in the reference data. The method further includes identifying, by the processing device, a region of interest of the deviation histogram. The method further includes determining, by the processing device, whether a deviation associated with the object exists based at least in part on the region of interest.

Cloud-to-cloud comparison using artificial intelligence-based analysis

Examples described herein provide a method that includes performing a first scan of an object to generate first scan data. The method further includes detecting a defect on a surface of the object by analyzing the first scan data to identify a region of interest containing the defect by comparing the first scan data to reference scan data. The method further includes performing a second scan of the region of interest containing the defect to generate second scan data, the second scan data being higher resolution scan data than the first scan data. The method further includes combining the first scan data and the second scan data to generate a point cloud of the object.

Defect detection in a point cloud

Examples described herein provide a method that includes performing, by a processing device, using a neural network, pattern recognition on an image to recognize a feature in the image. The method further includes performing, by the processing device, upscaling of the image to increase a resolution of the image while maintaining the feature to generate an upscaled image.

Upscaling triangulation scanner images to reduce noise

Examples described herein provide a method that includes obtaining, by a processing device, three-dimensional (3D) voxel data. The method further includes performing, by the processing device, gray value thresholding based at least in part on the 3D voxel data and assigning a classification value to at least one voxel of the 3D voxel data. The method further includes defining, by the processing device, segments based on the classification value. The method further includes filtering, by the processing device, the segments based on the classification value. The method further includes evaluating, by the processing device, the segments to identify a surface voxel per segment. The method further includes determining, by the processing device, a position of a surface point within the surface voxel.

Surface determination using three-dimensional voxel data

An example method for training a machine learning model is provided. The method includes receiving training data collected by a three-dimensional (3D) imager, the training data comprising a plurality of training sets. The method further includes generating, using the training data, a machine learning model from which a disparity map can be inferred from a pair of images that capture a scene where a light pattern is projected onto an object.

Three-dimiensional point cloud generation using machine learning

Provided are embodiments of a method for performing automatic analysis of cross-sections of micro-channels. Embodiments includes receiving tomography scan data, aligning the tomography scan data, and extracting channels from a slice of the tomography scan data to create an isolated slice of the extracted channel. Embodiments also include determining surface voxels for the extracted channels, and determining an area defined within the surface voxels for each of the extracted channels. Embodiments include determining a contribution of the surface voxels for each of the extracted channels to the cross-section of the extracted channels, and outputting cross-section information based on the contribution of the surface voxels. Also provided are embodiments of a system for performing automatic analysis of cross-sections of micro-channels.

Growing community of inventors

Fellbach, Germany

Georgios Balatzis