Abstract: The present approach relates to an automatic and efficient motion plan for a drone to collect and save a qualified dataset that may be used to improve reconstruction of 3D models using the acquired data. The present architecture provides an automatic image processing context, eliminating low quality images and providing improved image data for point cloud generation and texture mapping.

Abstract: A system and a method for capturing a movement pattern of a person. The method comprises capturing a plurality of images of the person executing a movement pattern by means of a non-contact sensor, the plurality of images representing the movements of the body elements of the person, generating at least one skeleton model having limb positions for at least some of the plurality of images, and calculating the movement pattern from the movements of the body elements of the person by comparing changes in the limb positions in the at least one skeleton model generated.

Abstract: The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.

Abstract: Methods and systems are provided for generating deep learning training data with an imaging system. In one embodiment, a method for an imaging system comprises performing a scan of a subject to acquire imaging data, training a deep neural network on the imaging data to obtain updates to the deep neural network, and transmitting the updates to a server for training a central deep neural network. In this way, imaging data may be leveraged for training and developing global deep learning models without transmitting the imaging data itself, thereby preserving patient privacy.

Abstract: The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.

Abstract: The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.

Abstract: Methods and systems are provided for capturing deep learning training data from imaging systems. In one embodiment, a method for an imaging system comprises performing a scan of a subject to acquire imaging data, inputting the imaging data to a deep neural network, displaying an output of the deep neural network and an image reconstructed from the imaging data, and transmitting an intermediate representation of the imaging data generated by the deep neural network to a server for training a central deep neural network. In this way, imaging data may be leveraged for training and developing global deep learning models without transmitting the imaging data itself, thereby preserving patient privacy.

Abstract: The present approach relates to an automatic and efficient motion plan for a drone to collect and save a qualified dataset that may be used to improve reconstruction of 3D models using the acquired data. The present architecture provides an automatic image processing context, eliminating low quality images and providing improved image data for point cloud generation and texture mapping.

Abstract: A robotic system includes a processing system comprising at least one processor. The processor generates a plan to monitor the asset. The plan comprises one or more tasks to be performed by the at least one robot. The processor receives sensor data from at least one sensor indicating one or more characteristics of the asset. The processor adjusts the plan to monitor the asset by adjusting or adding one or more tasks to the plan based on one or both of the quality of the acquired data or a potential defect of the asset. The adjusted plan causes the at least one robot to acquire additional data related to the asset when executed.

Abstract: The present approach relates to an automatic and efficient motion plan for a drone to collect and save a qualified dataset that may be used to improve reconstruction of 3D models using the acquired data. The present architecture provides an automatic image processing context, eliminating low quality images and providing improved image data for point cloud generation and texture mapping.

Abstract: Methods and systems are provided for generating deep learning training data with an imaging system. In one embodiment, a method for an imaging system comprises performing a scan of a subject to acquire imaging data, training a deep neural network on the imaging data to obtain updates to the deep neural network, and transmitting the updates to a server for training a central deep neural network. In this way, imaging data may be leveraged for training and developing global deep learning models without transmitting the imaging data itself, thereby preserving patient privacy.

Abstract: Methods and systems are provided for capturing deep learning training data from imaging systems. In one embodiment, a method for an imaging system comprises performing a scan of a subject to acquire imaging data, inputting the imaging data to a deep neural network, displaying an output of the deep neural network and an image reconstructed from the imaging data, and transmitting an intermediate representation of the imaging data generated by the deep neural network to a server for training a central deep neural network. In this way, imaging data may be leveraged for training and developing global deep learning models without transmitting the imaging data itself, thereby preserving patient privacy.

Abstract: The present approach relates to the use of a point cloud of an object to initialize or seed a space carving technique used to generate a 3D model of the object. In one implementation, feature matching is performed on 2D images, with matched features constituting the points of a point cloud model. The point cloud generated in this manner, is one input of a foreground/background segmentation algorithm, which generates a set of segmented 2D images used by a space carving routine to generate a 3D model of the object.

Abstract: The present approach relates to an automatic and efficient motion plan for a drone to collect and save a qualified dataset that may be used to improve reconstruction of 3D models using the acquired data. The present architecture provides an automatic image processing context, eliminating low quality images and providing improved image data for point cloud generation and texture mapping.

Abstract: A robotic system includes a processing system comprising at least one processor. The processor generates a plan to monitor the asset. The plan comprises one or more tasks to be performed by the at least one robot. The processor receives sensor data from at least one sensor indicating one or more characteristics of the asset. The processor adjusts the plan to monitor the asset by adjusting or adding one or more tasks to the plan based on one or both of the quality of the acquired data or a potential defect of the asset. The adjusted plan causes the at least one robot to acquire additional data related to the asset when executed.

Abstract: The present invention relates to a filler head (100) for a liquid tank in a motor vehicle with a housing (103), with a first molded housing part (103-1) having formed therein a tank vent pipe (105) for introducing air into the housing (103); and a second molded housing part (103-2) having formed therein a dip tube (107) for guiding a jet of liquid in the interior of the filler head (100), the dip tube (107) including a vent opening (111) for discharging from the filler head (100) the air that may be introduced through the tank vent pipe (105).

Abstract: The present invention relates to a method of operating an oxygen-consuming electrode as cathode for the electrolysis of alkali metal chlorides or hydrochloric acid, in an electrochemical cell, comprising feeding an oxygen-containing process gas to the electrode, wherein the oxygen-containing process gas is at least partly heated using a heat source from the electrolysis before contact with the oxygen-consuming electrode to a temperature which corresponds to not more than the temperature of the cathode space in the cell or is less than 50° C. below the temperature of the cathode space in the cell.

Abstract: Described is a process for preparing an aqueous polymer dispersion from ethylenically unsaturated, free-radically polymerizable monomers. In a first stage, a first polymer is prepared by free-radical emulsion polymerization. In a second stage, an aqueous polymer dispersion is prepared in the presence of the first polymer. The monomers of the first stage comprise monomers with acid groups. The polymerization of the first stage takes place at a low pH of less than 5. The acid groups of the first polymer are neutralized during the polymerization of the second stage to an extent such that the pH of the polymer dispersion at the end of the second stage is greater than 5. The aqueous polymer dispersions can be used as adhesives for producing composite films.

Abstract: The present invention relates to a filler head (100) for a liquid tank in a motor vehicle with a housing (103), with a first molded housing part (103-1) having formed therein a tank vent pipe (105) for introducing air into the housing (103); and a second molded housing part (103-2) having formed therein a dip tube (107) for guiding a jet of liquid in the interior of the filler head (100), the dip tube (107) including a vent opening (111) for discharging from the filler head (100) the air that may be introduced through the tank vent pipe (105).

Abstract: A photodiode includes a first doped layer and a second doped layer that share a common face. A deep isolation trench has a face contiguous with the first and second doped layers. A conducting layer is in contact with a free face of the second doped layer. A protective layer is provided at an interface with the first doped layer and second doped layer. This protective layer is capable of generating a layer of negative charge at the interface. The protective layer may further be positioned within the second doped layer to form an intermediate protective structure.