Abstract: A geodetic surveying device, wherein the geodetic surveying device is configured for surveying retroreflective cooperative targets, the geodetic surveying device comprising a base, a telescope and a support. The geodetic surveying device further comprises a target recognition emitting unit, called ATR-illuminator, an target recognition sensor, called ATR-sensor, an angle encoder and a processing unit. The geodetic surveying device is configured to distinguish desired targets from undesired targets, wherein the geodetic surveying device further comprises a classification model, wherein the classification model is configured for classification of retroreflective targets generating spots, wherein the retroreflective targets are classified into desired targets and undesired targets, wherein the classification is carried out by applying the classification model on the spot.

Abstract: A method for scanning an area using a ground penetrating radar (GPR) by moving the GPR along at least one scanning trajectory. The method includes determining at least one landmark object image feature by applying object detection techniques to images of the area to be scanned, determining a position and/or type of at least one landmark object corresponding to the at least one landmark object image feature in a scanning-area coordinate frame, determining a candidate position or candidate type of at least one candidate underground asset in the area to be scanned by using the determined position or type of the at least one landmark object determining the at least one scanning trajectory using the candidate position and/or candidate type of the at least one candidate underground asset.

Abstract: A geodetic surveying device, wherein the geodetic surveying device is configured for surveying retroreflective cooperative targets, the geodetic surveying device comprising a base, a telescope and a support. The geodetic surveying device further comprises a target recognition emitting unit, called ATR-illuminator, an target recognition sensor, called ATR-sensor, an angle encoder and a processing unit. The geodetic surveying device is configured to distinguish desired targets from undesired targets, wherein the geodetic surveying device further comprises a classification model, wherein the classification model is configured for classification of retroreflective targets generating spots, wherein the retroreflective targets are classified into desired targets and undesired targets, wherein the classification is carried out by applying the classification model on the spot.

Abstract: A method and a system for tube bending by a tube bending machine, wherein values of input parameters of the tube bending machine defining processing steps of the tube bending machine are determined as a function of a mapping of bending parameters defining a target tube bending geometry to the input parameters. The mapping is determined by a data-driven approach, wherein a machine learning based mapping model is fitted to tube bending machine processing data of an ongoing or a previous bending process, thereby providing a machine learning dependency of the input parameters from target bending parameters. For the training of the mapping model, values of the bending parameters and corresponding values of the input parameters are used, as well as a comparison information between the values of the bending parameters and measured actual values of the bending parameters resulting from the tube bending process.

Abstract: A computer program product and to a method for compensating thermal errors in a mechanical process, the mechanical process in particular provided by a mechanical device such as a coordinate measuring machine, a tooling machine or an articulated robot arm. Thermal errors arise due to thermal disturbances affecting the mechanical process, wherein thermal disturbances may arise from environmental influences affecting the mechanical process or from internally generated changing temperature distributions.

Abstract: A method for scanning an area using a ground penetrating radar (GPR) by moving the GPR along at least one scanning trajectory. The method includes determining at least one landmark object image feature by applying object detection techniques to images of the area to be scanned, determining a position and/or type of at least one landmark object corresponding to the at least one landmark object image feature in a scanning-area coordinate frame, determining a candidate position or candidate type of at least one candidate underground asset in the area to be scanned by using the determined position or type of the at least one landmark object determining the at least one scanning trajectory using the candidate position and/or candidate type of the at least one candidate underground asset.

Abstract: A computer program product and to a method for compensating thermal errors in a mechanical process, the mechanical process in particular provided by a mechanical device such as a coordinate measuring machine, a tooling machine or an articulated robot arm. Thermal errors arise due to thermal disturbances affecting the mechanical process, wherein thermal disturbances may arise from environmental influences affecting the mechanical process or from internally generated changing temperature distributions.

Abstract: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.

Abstract: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.

Abstract: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.

Abstract: The present embodiments relate to denoising medical images. By way of introduction, the present embodiments described below include apparatuses and methods for machine learning sparse image representations with deep unfolding and deploying the machine learnt network to denoise medical images. Iterative thresholding is performed using a deep neural network by training each layer of the network as an iteration of an iterative shrinkage algorithm. The deep neural network is randomly initialized and trained independently with a patch-based approach to learn sparse image representations for denoising image data. The different layers of the deep neural network are unfolded into a feed-forward network trained end-to-end.