Abstract: A method for displaying images similar to a selected image includes receiving, from a user, a selection of an anchor image, generating, using a machine learning model, an anchor embeddings set for the anchor image and respective candidate embeddings sets for a plurality of candidate images. The method also includes calculating a distance between the anchor embeddings set and each of the plurality of candidate embeddings sets and displaying at least one of the plurality of candidate images based on the calculated distance.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, initial burst of eye pictures in short time by restricting the image area of a sensor, purpose of enabling an increased frame rate. Subsequent eye pictures are captured at le rate. The first gaze point value is computed memorylessly based on the initial burst res and no additional imagery, while subsequent values may be computed recursively to account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the different sensor. From the gaze point values, the system may derive a control signal to a computer device with a visual display.

Abstract: A graphics presentation apparatus including a display unit, an eye-tracking module, and a data output module. The eye-tracking module registers image data representing at least one eye of a user of the apparatus. Furthermore, the eye-tracking module determines, based on the registered image data, an orientation of the at least one eye relative to the display unit. Finally, in response thereto, the eye-tracking module generates a control signal controlling the data output module to produce visual content with such orientation on the display unit that a misalignment between the orientation of said at least one part and the orientation of the at least one eye of the user is minimized.

Abstract: The present invention relates to systems and methods for assisting a user when interacting with a graphical user interface by combining eye based input with input for e.g. selection and activation of objects and object parts and execution of contextual actions related to the objects and object parts. The present invention also relates to such systems and methods in which the user can configure and customize specific combinations of eye data input and input that should result in a specific contextual action.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, initial burst of eye pictures in short time by restricting the image area of a sensor, purpose of enabling an increased frame rate. Subsequent eye pictures are captured at le rate. The first gaze point value is computed memorylessly based on the initial burst res and no additional imagery, while subsequent values may be computed recursively to account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the different sensor. From the gaze point values, the system may derive a control signal to a computer device with a visual display.

Abstract: A graphics presentation apparatus including a display unit, an eye-tracking module, and a data output module. The eye-tracking module registers image data representing at least one eye of a user of the apparatus. Furthermore, the eye-tracking module determines, based on the registered image data, an orientation of the at least one eye relative to the display unit. Finally, in response thereto, the eye-tracking module generates a control signal controlling the data output module to produce visual content with such orientation on the display unit that a misalignment between the orientation of said at least one part and the orientation of the at least one eye of the user is minimized.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, initial burst of eye pictures in short time by restricting the image area of a sensor, purpose of enabling an increased frame rate. Subsequent eye pictures are captured at le rate. The first gaze point value is computed memorylessly based on the initial burst res and no additional imagery, while subsequent values may be computed recursively to account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the different sensor. From the gaze point values, the system may derive a control signal to a computer device with a visual display.

Abstract: The present invention relates to systems and methods for assisting a user when interacting with a graphical user interface by combining eye based input with input for e.g. selection and activation of objects and object parts and execution of contextual actions related to the objects and object parts. The present invention also relates to such systems and methods in which the user can configure and customize specific combinations of eye data input and input that should result in a specific contextual action.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, captures an initial burst of eye pictures in short time by restricting the image area of a sensor, with the purpose of enabling an increased frame rate. Subsequent eye pictures are captured at normal frame rate. The first gaze point value is computed memorylessly based on the initial burst of eye pictures and no additional imagery, while subsequent values may be computed recursively by taking into account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the same or a different sensor. From the gaze point values, the system may derive a control signal to be supplied to a computer device with a visual display.

Abstract: A graphics presentation apparatus including a display unit, an eye-tracking module, and a data output module. The eye-tracking module registers image data representing at least one eye of a user of the apparatus. Furthermore, the eye-tracking module determines, based on the registered image data, an orientation of the at least one eye relative to the display unit. Finally, in response thereto, the eye-tracking module generates a control signal controlling the data output module to produce visual content with such orientation on the display unit that a misalignment between the orientation of said at least one part and the orientation of the at least one eye of the user is minimized.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, captures an initial burst of eye pictures in short time by restricting the image area of a sensor, with the purpose of enabling an increased frame rate. Subsequent eye pictures are captured at normal frame rate. The first gaze point value is computed memorylessly based on the initial burst of eye pictures and no additional imagery, while subsequent values may be computed recursively by taking into account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the same or a different sensor. From the gaze point values, the system may derive a control signal to be supplied to a computer device with a visual display.

Abstract: A graphics presentation apparatus including a display unit, an eye-tracking module, and a data output module. The eye-tracking module registers image data representing at least one eye of a user of the apparatus. Furthermore, the eye-tracking module determines, based on the registered image data, an orientation of the at least one eye relative to the display unit. Finally, in response thereto, the eye-tracking module generates a control signal controlling the data output module to produce visual content with such orientation on the display unit that a misalignment between the orientation of said at least one part and the orientation of the at least one eye of the user is minimized.

Abstract: A gaze tracking system, leaving a low power mode in response to an activation signal, captures an initial burst of eye pictures in short time by restricting the image area of a sensor, with the purpose of enabling an increased frame rate. Subsequent eye pictures are captured at normal frame rate. The first gaze point value is computed memorylessly based on the initial burst of eye pictures and no additional imagery, while subsequent values may be computed recursively by taking into account previous gaze point values or information from previous eye pictures. The restriction of the image area may be guided by a preliminary overview picture captured using the same or a different sensor. From the gaze point values, the system may derive a control signal to be supplied to a computer device with a visual display.

Abstract: A graphics presentation apparatus including a display unit, an eye-tracking module, and a data output module. The eye-tracking module registers image data representing at least one eye of a user of the apparatus. Furthermore, the eye-tracking module determines, based on the registered image data, an orientation of the at least one eye relative to the display unit. Finally, in response thereto, the eye-tracking module generates a control signal controlling the data output module to produce visual content with such orientation on the display unit that a misalignment between the orientation of said at least one part and the orientation of the at least one eye of the user is minimized.

Abstract: A method and system for determining a position of a UE includes a first network node receiving a request for positioning information about the UE. The first network node requests a first positioning procedure at a first location node. The first location node determines using the first positioning procedure that involvement by a second location node is needed. The first location node initiates a trigger for positioning information about the UE to be sent to the second location node. The second location node, upon receiving the trigger for positioning information and determining the presence of an environment measurement parameter, determines the position information of the UE by performing a second positioning procedure based on the environment measurement parameter, and sends a position calculation response with the positioning information.

Abstract: The present invention relates to systems and methods for assisting a user when interacting with a graphical user interface by combining eye based input with input for e.g. selection and activation of objects and object parts and execution of contextual actions related to the objects and object parts. The present invention also relates to such systems and methods in which the user can configure and customize specific combinations of eye data input and input that should result in a specific contextual action.

Abstract: The present invention relates to systems and methods for assisting a user when interacting with a graphical user interface by combining eye based input with input for e.g. selection and activation of objects and object parts and execution of contextual actions related to the objects and object parts. The present invention also relates to such systems and methods in which the user can configure and customize specific combinations of eye data input and input that should result in a specific contextual action.

Abstract: Presented are methods and apparatus for generating an inaccuracy characteristic for a fingerprinting positioning algorithm calculation associated with a user equipment location. Fingerprinting positioning measurements are compared to high-accuracy positioning measurements and an error value is determined. The error values are accumulated and the inaccuracy characteristic is generated based on an inaccuracy calculation. For areas where insufficient data is available, an inaccuracy characteristic value can be interpolated or extrapolated from adjacent areas containing sufficient data.

Abstract: Presented are methods and apparatus for generating an inaccuracy characteristic for a fingerprinting positioning algorithm calculation associated with a user equipment location. Fingerprinting positioning measurements are compared to high-accuracy positioning measurements and an error value is determined. The error values are accumulated and the inaccuracy characteristic is generated based on an inaccuracy calculation. For areas where insufficient data is available, an inaccuracy characteristic value can be interpolated or extrapolated from adjacent areas containing sufficient data.

Abstract: The present invention relates to a method and a positioning server in a radio access network for collecting radio fingerprint positioning data records from different nodes. The data records comprise geographical positions and radio network communication parameters and are stored and grouped in clusters in the positioning server. A geometrical shape representing a geographical area based on the network communication parameters in the collected positioning data records in the cluster is computed. When a notification about changed network configuration parameters for a radio cell is received, known positioning servers simply erase all positioning data records related to that radio cell. This results in the unavailability of still valid positioning data. The present invention overcomes this problem by selectively erase positioning data records in the positioning server only when the configuration parameters have changed beyond a predefined value range.