Abstract: A computer-implemented method for determining a set of target items to be annotated for training a machine learning application. The method comprises providing a training data set with a set of data samples and an auto-encoder with a classifier. The auto-encoder comprises an embedding model that maps the set of data samples to a set of compressed feature vectors. The set of compressed feature vectors define a compressed feature matrix. Further provided are: a definition of a graph associated to the compressed feature matrix, applying a clustering-algorithm to identify node clusters of the graph and applying a centrality algorithm to identify central nodes of the node clusters, retrieving from an annotator node labels for the central nodes, propagating the annotated node labels to other nodes of the graph and performing a training of the embedding model and the classifier with the annotated and the propagated node labels.

Abstract: A computer-implemented method, computer program product, and computer system are provided. The method comprises training a machine-learning model using an initial set of training data samples, receiving a new training data sample, and predicting a label for the new training data sample. The method also comprises, upon determining that a prediction quality value for the predicted label of the new training data sample is below a predefined quality value, adding the new training data sample to the initial set, thereby building an extended training data set. The method also comprises retraining the machine-learning model using the extended training data set.

Abstract: Computer-implemented methods and apparatus are provided for annotating digital images of line plots with ground truth labels. For each digital image, such a method includes supplying image data defining the image of a line plot to a machine-learning model trained to generate a set of control points defining a spline corresponding to the line plot. The method further comprises displaying the spline, and the set of control points, superimposed on the image in a graphical user interface and, in response to user manipulation via the graphical user interface of one or more control points, dynamically adjusting the displayed spline in accordance with manipulated control points whereby the displayed spline can be adjusted for conformity with the line plot. The set of control points for the adjusted spline is then stored as a ground truth label for the image.

Abstract: A computer-implemented method, computer program product, and computer system are provided. The method comprises training a machine-learning model using an initial set of training data samples, receiving a new training data sample, and predicting a label for the new training data sample. The method also comprises, upon determining that a prediction quality value for the predicted label of the new training data sample is below a predefined quality value, adding the new training data sample to the initial set, thereby building an extended training data set. The method also comprises retraining the machine-learning model using the extended training data set.

Abstract: Computer-implemented methods and apparatus are provided for annotating digital images of line plots with ground truth labels. For each digital image, such a method includes supplying image data defining the image of a line plot to a machine-learning model trained to generate a set of control points defining a spline corresponding to the line plot. The method further comprises displaying the spline, and the set of control points, superimposed on the image in a graphical user interface and, in response to user manipulation via the graphical user interface of one or more control points, dynamically adjusting the displayed spline in accordance with manipulated control points whereby the displayed spline can be adjusted for conformity with the line plot. The set of control points for the adjusted spline is then stored as a ground truth label for the image.

Abstract: A computer-implemented method for determining a set of target items to be annotated for training a machine learning application. The method comprises providing a training data set with a set of data samples and an auto-encoder with a classifier. The auto-encoder comprises an embedding model that maps the set of data samples to a set of compressed feature vectors. The set of compressed feature vectors define a compressed feature matrix. Further provided are: a definition of a graph associated to the compressed feature matrix, applying a clustering-algorithm to identify node clusters of the graph and applying a centrality algorithm to identify central nodes of the node clusters, retrieving from an annotator node labels for the central nodes, propagating the annotated node labels to other nodes of the graph and performing a training of the embedding model and the classifier with the annotated and the propagated node labels.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A method and system for surveying and/or metrology for assigning particular classes of interest within measurement data, wherein an assignment of at least one measurement object to a first class of interest within the measurement data based on a classification model, is processed by a feedback procedure providing feedback data for a training procedure which provides update information for the classification model, wherein the training procedure is based on a machine learning algorithm, e.g. relying on deep learning for supervised learning and/or unsupervised learning.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A method may include identifying features in images of a setting captured by cameras associated with a laser scanner at a first location. The features may correspond to elements in the setting. The method may include correlating the features with scan point data associated with the elements. The scan point data may be derived from a scan of the setting by a laser of the laser scanner at the first location. The method may include tracking the features within images captured by the cameras. The images may be captured during movement of the laser scanner away from the first location. The method may include estimating a position and/or an orientation of the laser scanner at a second location based on the tracking of the features and based on the correlating of the features with the scan point data.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A method for registering two or more three-dimensional (3D) point clouds. The method includes, with a surveying instrument, obtaining a first 3D point cloud of a first setting at a first position, initiating a first Simultaneous Localisation and Mapping (SLAM) process by capturing first initial image data at the first position with a camera unit comprised by the surveying instrument, wherein the first initial image data and the first 3D point cloud share a first overlap, finalising the first SLAM process at the second position by capturing first final image data with the camera unit, wherein the first final image data are comprised by the first image data, with the surveying instrument, obtaining a second 3D point cloud of a second setting at the second position, and based on the first SLAM process, registering the first 3D point cloud and the second 3D point cloud relative to each other.

Abstract: A method may include identifying features in images of a setting captured by cameras associated with a laser scanner at a first location. The features may correspond to elements in the setting. The method may include correlating the features with scan point data associated with the elements. The scan point data may be derived from a scan of the setting by a laser of the laser scanner at the first location. The method may include tracking the features within images captured by the cameras. The images may be captured during movement of the laser scanner away from the first location. The method may include estimating a position and/or an orientation of the laser scanner at a second location based on the tracking of the features and based on the correlating of the features with the scan point data.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.

Abstract: A system is disclosed that comprises a camera module and a control and evaluation unit. The camera module is designed to be attached to the surveying pole and comprises at least one camera for capturing images. The control and evaluation unit has stored a program with program code so as to control and execute a functionality in which a series of images of the surrounding is captured with the at least one camera; a SLAM-evaluation with a defined algorithm using the series of images is performed, wherein a reference point field is built up and poses for the captured images are determined; and, based on the determined poses, a point cloud comprising 3D-positions of points of the surrounding can be computed by forward intersection using the series of images, particularly by using dense matching algorithm.