Abstract: A method for performing thermal screening is described. The method includes capturing at least one non-thermal image of a scene having a person; capturing at least one thermal image of the scene having the person; determining a region of interest of the non-thermal image; determining, based on a body sub-region of the non-thermal image corresponding to the body of the person within the scene, a distance value representative of a physical distance of the person from the thermal camera; determining a region of interest of the thermal image corresponding to the region of interest of the non-thermal image; determining a raw temperature value for the person based on the region of interest of the thermal image; and normalizing the raw temperature value based on at least the distance value to determine a normalized temperature value. A corresponding system and non-transitory computer-readable medium are also provided.

Abstract: A system and method for performing distributed facial recognition divides processing steps between a user engagement device/robot, having lower processing power, and a remotely located server, having significantly more processing power. Images captured by the user engagement device/robot are processed at the device/robot by applying a first set of image processing steps that includes applying a first face detection. First processed images having at least one detected face is transmitted to the server, whereat a second set of image processing steps are applied to determine a stored user facial image matching the detected face of the first processed image. At least one user property associated to the given matching user facial image is then transmitted to the user engagement device/robot. An interactive action personalized to the user can further be performed at the user engagement device/robot.

Abstract: A system and method for performing distributed facial recognition divides processing steps between a user engagement device/robot, having lower processing power, and a remotely located server, having significantly more processing power. Images captured by the user engagement device/robot are processed at the device/robot by applying a first set of image processing steps that includes applying a first face detection. First processed images having at least one detected face is transmitted to the server, whereat a second set of image processing steps are applied to determine a stored user facial image matching the detected face of the first processed image. At least one user property associated to the given matching user facial image is then transmitted to the user engagement device/robot. An interactive action personalized to the user can further be performed at the user engagement device/robot.

Abstract: A system and method for performing distributed facial recognition divides processing steps between a user engagement device/robot, having lower processing power, and a remotely located server, having significantly more processing power. Images captured by the user engagement device/robot are processed at the device/robot by applying a first set of image processing steps that includes applying a first face detection. First processed images having at least one detected face is transmitted to the server, whereat a second set of image processing steps are applied to determine a stored user facial image matching the detected face of the first processed image. At least one user property associated to the given matching user facial image is then transmitted to the user engagement device/robot. An interactive action personalized to the user can further be performed at the user engagement device/robot.