Abstract: A device determines the positioning of objects in a scene by implementing a robust and deterministic method. The device obtains object detection data (ODD) which identifies the objects and locations of reference points of the objects in views of the scene. The obtained ODD is processed to identify a first image object of a first view as a mirror reflection of a real object. A virtual view associated with a virtual camera position is created, including the ODD associated with the first image object of the first view. The ODD associated with the first image object is removed from the first view. Based on the ODD associated with at least said virtual view and a further view of the one or more views, a position of said first image object is computed.

Abstract: A processing device is configured to obtain a sequence of images of a scene captured by an image sensor, determine an analysis area for an object in a respective image in the sequence of images, and process the respective image within the analysis area for detection of predefined features of the object. The processing device is further configured to receive pose prediction data, PPD, which represents predicted poses of the object as a function of time, and to determine the analysis area based on the PPD. The PPD may be given by three-dimensional poses of the object that have been determined in the system based on images from a plurality of image sensors in the system. The PPD facilitates detection of features of individual objects in the images even if the objects are occluded and/or crowded.

Abstract: A system for training a neural network for action recognition based on unlabeled action sequences includes a first neural network (NN1) and a second neural network (NN2). A first updating module is arranged to update parameters of NN1 to minimize a difference between representation data generated by NN1 and representation data generated by NN2. A second updating module is arranged to update parameters of NN2 as a function of the parameters of NN1. An augmentation module includes first and second sub-modules and is configured to include augmented versions of incoming action sequences in first and second input data. The first and second sub-modules are configured to apply at least partly different augmentation to the incoming action sequences. After NN1 and NN2 have been operated on one or more instances of the first and second input data, NN1 comprises a parameter definition of a pre-trained neural network.

Abstract: A method for extrinsic calibration of cameras in a monitoring system, performed by a calibration device, includes obtaining preliminary calibration data of the cameras, obtaining a preliminary pose for an object observed by the cameras, and determining calibration data that results in an optimization of an objective function using the preliminary calibration data and the preliminary pose as starting values for the optimization. The method further includes defining the objective function with calibration data and pose as unknown variables and including a first function yielding aggregated reprojection error, and a second function yielding pose quality based on relative orientation and relative distance between 3D points of the pose. The second function enables improved accuracy of the calibration data and may be configured to yield pose quality for individual poses or motion quality for a time sequence of poses.

Abstract: A method (100) is disclosed, the method (100) being performed by a server device, where the server device (400) is configured to communicate with a first electronic device (300) of a plurality of electronic devices (300, 300A-300I), the first electronic device being configured to operate using a processing scheme based on a machine-learning model. The method (100) comprises receiving (S102), from the first electronic device (300), an update request for updating the machine-learning model, the update request comprising sensor data indicative of a context surrounding the first electronic device (300); generating (S107) an updated machine-learning model based on the sensor data of the update request; and transmitting (S110) an update response comprising the updated machine-learning model to the first electronic device (300).

Abstract: A device determines the positioning of objects in a scene by implementing a robust and deterministic method. The device obtains object detection data (ODD) which identifies the objects and locations of reference points of the objects in views of the scene. The obtained ODD is processed to identify a first image object of a first view as a mirror reflection of a real object. A virtual view associated with a virtual camera position is created, including the ODD associated with the first image object of the first view. The ODD associated with the first image object is removed from the first view. Based on the ODD associated with at least said virtual view and a further view of the one or more views, a position of said first image object is computed.

Abstract: A method for extrinsic calibration of cameras in a monitoring system, performed by a calibration device, includes obtaining preliminary calibration data of the cameras, obtaining a preliminary pose for an object observed by the cameras, and determining calibration data that results in an optimization of an objective function using the preliminary calibration data and the preliminary pose as starting values for the optimization. The method further includes defining the objective function with calibration data and pose as unknown variables and including a first function yielding aggregated reprojection error, and a second function yielding pose quality based on relative orientation and relative distance between 3D points of the pose. The second function enables improved accuracy of the calibration data and may be configured to yield pose quality for individual poses or motion quality for a time sequence of poses.

Abstract: A device may determine touch position information representing a position where a touch surface is touched by an object, and may determine force information representing a force being applied by the object to the touch surface. Based on the force information, the device may determine that the force applied to the touch surface does not satisfy a force threshold. Afterwards, the device may determine that a particular duration has not elapsed. Finally, after determining that the particular duration has not elapsed, the device may provide the touch position information for further processing.

Abstract: Method for validating a trusted user of an electronic device, which electronic device comprises an input surface, e.g. on a key, dedicated for application of a user finger; a user input data sensor system, including a fingerprint sensor connected to the input surface for detecting user input fingerprint data, and a tremor sensor for detecting user input tremor data; data access to stored user input data corresponding to a trusted user; and a main processor system configured to match detected user input data with stored input data for validation of a trusted user. A triggering algorithm may run in a sub-sensor system, for sensing device handling and comparing sensed device handling with stored data. If the comparison reveals that user input is likely to occur based on the, a command is sent to the main processing system to trigger activation of tremor sensing and matching.

Abstract: Embodiments are directed to automatically unlocking a user device based on proximity to a previously paired accessory.

Abstract: An electronic device is operated based on whether it detects vibration indicative of natural human tremors while the device is not enclosed in a small space. Human tremors are detected by sampling a motion signal and performing a discrete Fourier transformation on a plurality of sets of samples. For each sample, a mean magnitude is calculated for a first range of frequencies indicative of human tremors. A mean magnitude is also calculated for a second range of frequencies greater than the first range. If the difference between the mean magnitude of the first range and the mean magnitude of the second range, then human tremors are detected for the set of samples. Human tremors are detected for the device if a threshold number of sets of samples within a predetermined time period produce an output indicating detection.

Abstract: A system and method are provided for controlling the own-voice experience of a user who talks while an earpiece is mounted to occlude an ear of the user. A vibration sensor is engaged with the user's head to sense vibrations formed by the user speaking and conducted by the user's head to the vibration sensor. A signal generator operates a speaker element, which is integrated with the earpiece, to generate sound waves in the ear canal of the user, based on the output signal of the vibration sensor. The signal generator generates the sound waves to at least partially cancel other sound waves that are generated by at least part of said vibrations entering the ear canal from surrounding bone and/or tissue. The system and method counteracts the occlusion effect and are applicable in connection with in-ear headsets, earphones, in-ear headphones, in-ear monitors, circumaural headphones, hearing aids, earplugs and earmuffs.

Abstract: The present invention relates to a touch screen device, a handheld device and a method for operating a touch screen device.

Abstract: A system and method are provided for controlling the own-voice experience of a user who talks while an earpiece is mounted to occlude an ear of the user. A vibration sensor is engaged with the user's head to sense vibrations formed by the user speaking and conducted by the user's head to the vibration sensor. A signal generator operates a speaker element, which is integrated with the earpiece, to generate sound waves in the ear canal of the user, based on the output signal of the vibration sensor. The signal generator generates the sound waves to at least partially cancel other sound waves that are generated by at least part of said vibrations entering the ear canal from surrounding bone and/or tissue. The system and method counteracts the occlusion effect and are applicable in connection with in-ear headsets, earphones, in-ear headphones, in-ear monitors, circumaural headphones, hearing aids, earplugs and earmuffs.

Abstract: An electronic device is operated based on whether it detects vibration indicative of natural human tremors while the device is not enclosed in a small space. Human tremors are detected by sampling a motion signal and performing a discrete Fourier transformation on a plurality of sets of samples. For each sample, a mean magnitude is calculated for a first range of frequencies indicative of human tremors. A mean magnitude is also calculated for a second range of frequencies greater than the first range. If the difference between the mean magnitude of the first range and the mean magnitude of the second range, then human tremors are detected for the set of samples. Human tremors are detected for the device if a threshold number of sets of samples within a predetermined time period produce an output indicating detection.

Abstract: A digital photograph is processed by receiving a communication related to the digital photograph from an application external to an image storage device that stores the digital photograph. Parameters related to the application are processed. The digital photograph is changed based on the parameters related to the application. Related methods, devices, and/or computer program products are described.

Abstract: Method for validating a trusted user of an electronic device, which electronic device comprises an input surface, e.g. on a key, dedicated for application of a user finger; a user input data sensor system, including a fingerprint sensor connected to the input surface for detecting user input fingerprint data, and a tremor sensor for detecting user input tremor data; data access to stored user input data corresponding to a trusted user; and a main processor system configured to match detected user input data with stored input data for validation of a trusted user. A triggering algorithm may run in a sub-sensor system, for sensing device handling and comparing sensed device handling with stored data. If the comparison reveals that user input is likely to occur based on the, a command is sent to the main processing system to trigger activation of tremor sensing and matching.

Abstract: A device for weighing a user includes a weight sensor that determines a weight of the user, and a bare feet image sensor that generates an image of the bare feet of the user. The device includes a processor that is responsive to the weight sensor and to the bare feet image sensor and executes computer program instructions to perform operations such as identifying a provisioned user out of one or more provisioned users based on the image of the bare feet of the user standing on the device. A database stores information associated with the image of the bare feet of one or more provisioned users of the device. The weight of the user associated with the identified provisioned is stored. Related devices and methods are provided.

Abstract: The present invention relates to a communication system, an audio server, and a method for operating a communication system.

Abstract: A device, having a touch screen display, performs a mutual capacitance scan of rows and columns of an array of capacitive touch sensors associated with the touch screen display. The device selects a subset of the rows, and a subset of the columns, of the array of capacitive touch sensors, and performs a self capacitance scan of the selected subset of the rows, and the selected subset of the columns, of the array of capacitive touch sensors based on results of the mutual capacitance scan. The device identifies an accidental or false touch input on the touch screen display based on results of the self capacitance scan.