Abstract: A system and method for scanning an environment and generating an annotated 2D map is provided. The method includes acquiring, via a 2D scanner, a plurality of 2D coordinates on object surfaces in the environment, the 2D scanner having a light source and an image sensor, the image sensor being arranged to receive light reflected from the object points. A first 360° image is acquired at a first position of the environment, via a 360° camera having a plurality of cameras and a controller, the controller being operable to merge the images acquired by the plurality of cameras to generate an image having a 360° view, the 360° camera being movable from the first to a second position. A 2D map is generated based at least in part on the plurality of two-dimensional coordinates of points. The first 360° image is integrated with the 2D map.

Abstract: Techniques are described to generate a 3D scene by mapping a point cloud with a 2D image, and colorize portions of the 3D scene synthetically. An input is received to select, from the 3D scene, a portion to be colorized synthetically. The colorizing includes generating a reflectance image based on an intensity image of the point cloud. The colorizing further includes generating an occlusion mask that identifies the selected portion in the reflectance image. The colorizing further includes estimating, using a trained machine learning model, a color for each of the one or more points in the selected portion based on the reflectance image, the occlusion mask, and the 2D image. The 3D scene is updated by using the estimated colors from the trained machine learning model to colorize the selected portion.

Abstract: An articulated arm coordinate measuring machine includes an arm having multiple segments and an end assembly. The end assembly has multiple accessory interfaces that allow multiple accessories to be coupled to the end assembly. The accessory interfaces are configured to allow the accessories to be repeatably interchanged between the accessory interfaces.

Abstract: According to one or more embodiments, a method includes capturing a first three-dimensional (3D) point cloud and a second 3D point cloud. Each of the 3D point clouds includes a plurality 3D coordinates corresponding to one or more objects scanned in a surrounding environment. The first 3D point cloud and the second 3D point cloud capturing at least one overlapping portion. Further, the method includes capturing a first ultrawide-angle image and a second ultrawide-angle image of the surrounding environment, the first ultrawide-angle image captures color information of the first 3D point cloud, and the second ultrawide-angle image captures color information of the second 3D point cloud. The method further includes registering the first 3D point cloud and the second 3D point cloud by mapping one or more features from the first ultrawide-angle image and the second ultrawide-angle image.

Abstract: A software camera lock is provided. A first image is displayed as a 3D image, wherein a semi-transparent second image overlays the first image. A software camera is inserted at a fixed location in the 3D image, wherein the software camera provides a field-of-view (FOV) displaying a portion of the 3D image, the FOV displaying a first reference in the FOV, the second image displaying a second reference that represents first reference and comprising an object. Software camera is locked in FOV using a lock software camera mode. A model is inserted in first image to match a location of the object in second image, wherein locking the software camera in the FOV causes the FOV of the first image to be maintained in place as the model is being moved in the first image to match the location of the object in second image.

Abstract: A system includes a first type of measurement device that captures first 2D images, a second type of measurement device that captures 3D scans. A 3D scan includes a point cloud and a second 2D image. The system also includes processors that register the first 2D images. The method includes accessing the 3D scan that records at least a portion of the surrounding environment that is also captured by a first 2D image. Further, 2D features in the second 2D image are detected, and 3D coordinates from the point cloud are associated to the 2D features. 2D features are also detected in the first 2D image, and matching 2D features from the first 2D image and the second 2D image are identified. A position and orientation of the first 2D image is calculated in a coordinate system of the 3D scan using the matching 2D features.

Abstract: 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.

Abstract: Examples described herein provide a method for performing a predictive collision analysis. The method includes initiating, on a processing system, the predictive collision analysis to be performed on the processing system. The further method includes defining a virtual mirror property for a virtual mirror for the predictive collision analysis. The method further includes performing, by the processing system, the predictive collision analysis. Performing the predictive collision analysis includes generating a virtual mirror graphical representation including the virtual mirror based on the virtual mirror property.

Abstract: A system and method for measuring coordinate values of an environment is provided. The system includes a coordinate measurement scanner that includes a light source that steers a beam of light to illuminate object points in the environment, and an image sensor arranged to receive light reflected from the object points to determine coordinates of the object points in the environment. The system also includes one or more processors for performing a method that includes receiving a previously generated map of the environment and causing the scanner to measure a plurality of coordinate values as the scanner is moved through the environment, the coordinate values forming a point cloud. The plurality of coordinate values are registered with the previously generated map into a single frame of reference. A current map of the environment is generated based at least in part on the previously generated map and the point cloud.

Abstract: A system and method for providing feedback on a quality of a 3D scan is provided. The system includes a coordinate scanner configured to optically measure and determine a plurality of three-dimensional coordinates to a plurality of locations on at least one surface in the environment, the coordinate scanner being configured to move through the environment while acquiring the plurality of three-dimensional coordinates. A display having a graphical user interface. One or more processors are provided that are configured to determine a quality attribute of a process of measuring the plurality of three-dimensional coordinates based at least in part on the movement of the coordinate scanner in the environment and display a graphical quality indicator on the graphical user interface based at least in part on the quality attribute, the quality indicator is a graphical element having at least one movable element.

Abstract: A system and method for detecting construction site defects and hazards using artificial intelligence (AI) is provided. The system includes a movable base unit, a coordinate measurement scanner, a vision based sensor, and one or more processors. The one or more processors perform operations that include generating a two-dimensional (2D) map of the environment based at least in part on output from the coordinate measurement scanner, applying image recognition to the video stream data to identify and label a defect or hazard in the video data stream, correlating a location of the defect or hazard in the video stream data with the location in the 2D map, and recording the location of the defect or hazard in the 2D map.

Abstract: Examples described herein provide a method for generating a three-dimensional (3D) model of an object of interest using panoramic images of an environment. The method includes detecting, using a trained machine learning model, the object of interest in a panoramic image of the environment. The method further includes determining 3D coordinates for the object of interest. The method further includes combining the 3D coordinates for the object of interest with an existing 3D model of the object of interest to create a revised 3D model of the object of interest.

Abstract: A system includes a pose manipulation system operationally that sets a pose of a position measurement system with respect to an object that is to be measured. The system further includes a pose tracking system configured to record a relative pose between a coordinate system associated with the position measurement system and a coordinate system of the object. The pose tracking system records a path along which the position measurement system is enabled to measure 3D coordinates of a surface of a type of an object, wherein recording the path comprises moving the pose manipulation system sequentially through a plurality of poses and recording, at each pose, the relative pose to measure the 3D coordinates. The pose manipulation system follows the path again, and the position measurement system measures the 3D coordinates by applying one or more of the recorded poses.

Abstract: A method includes providing a measuring device having a projector, a camera with a photosensitive array, and at least one processor, projecting with the projector a line of light onto an object, capturing with the camera an image of the projected line of light on the object within a window subregion of the photosensitive array, and calculating with the at least one processor three-dimensional (3D) coordinates of points on the object based at least in part on the projected line of light and on the captured image.

Abstract: A system includes a three-dimensional (3D) scanner that captures a 3D point cloud corresponding to one or more objects in a surrounding environment. The system further includes a camera that captures a control image by capturing a plurality of images of the surrounding environment, and an auxiliary camera configured to capture an ultrawide-angle image of the surrounding environment. One or more processors of the system colorize the 3D point cloud using the ultrawide-angle image by mapping the ultrawide-angle image to the 3D point cloud. The system performs a limited system calibration before colorizing each 3D point cloud, and a periodic full system calibration before/after a plurality of 3D point clouds are colorized.

Abstract: A system and method for measuring three-dimensional (3D) coordinate values of an environment is provided. The system includes a movable base unit a first scanner and a second scanner. One or more processors performing a method that includes causing the first scanner to determine first plurality of coordinate values in a first frame of reference based at least in part on a measurement by at least one sensor. The second scanner determines a second plurality of 3D coordinate values in a second frame of reference as the base unit is moved from a first position to a second position. The determining of the first coordinate values and the second plurality of 3D coordinate values being performed simultaneously. The second plurality of 3D coordinate values are registered in a common frame of reference based on the first plurality of coordinate values.

Abstract: Technical solutions are described to track a handheld three-dimensional (3D) scanner in an environment using natural features in the environment. In one or more examples, the natural features are detected using machine learning. Features are filtered by performing a stereo matching between respective pairs of stereo images captured by the scanner. The features are further filtered using time matching between images captured by the scanner at different timepoints.

Abstract: 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.

Abstract: A method for creating an augmented reality scene, the method comprising, by a computing device with a processor and a memory, receiving a first video image data and a second video image data; calculating an error value for a current pose between the two images by comparing the pixel colors in the first video image data and the second video image data; warping pixel coordinates into a second video image data through the use of the map of depth hypotheses for each pixel; varying the pose between the first video image data and the second video image data to find a warp that corresponds to a minimum error value; calculating, using the estimated poses, a new depth measurement for each pixel that is visible in both the first video image data and the second video image data.

Abstract: Examples described herein provide a method that includes performing cluster matching with one or more cluster sizes for each of a plurality of points of a measurement point cloud. The method further includes determining, based on results of the multi-radii cluster matching, whether an object is displaced or whether the object includes a defect.