Abstract: A computer-based method includes receiving, at a computer-based system, an aerial image of a property that includes a first visual indicator on the aerial image that follows and identifies a boundary line for the property; using a building rooftop Deep Fully Convolutional Network (DFCN), configured and trained to predict the presence of building rooftops in aerial imagery, to predict whether any building rooftops are present within the boundary line of the property based on the aerial image; and applying a second visual indicator to the aerial image to identify and outline a building rooftop in the aerial image identified by the building rooftop deep fully convolutional network. In some implementations, other Convolutional Networks (ConvNets) are used to predict other property attributes and characteristics.

Abstract: A system for eye movement and pupil size change matching for user authentication includes an ocular sensor that is configured to sense eyes of a user and collect data indicative of the user's eye movement and pupil size changes. When a user's eyes are detected, the logic analyzes data collected by the ocular sensor in order to determine whether the sensed data match data extracted from a template defined by the eye movement and pupil size changes of an authorized user. If so, the user is authenticated and is permitted to access at least one restricted resource. As an example, the user may be permitted to access an application or sensitive data stored on a computer system or to access a restricted area, such as a room of a building.