Abstract:
The present disclosure includes a diorama space generation and construction module configured to construct an AR map by using a user camera image or image data received through a sensor, a diorama environment tracking and location optimization module configured to load the constructed AR map onto an AR device and track a location of the AR device in a diorama space in real time based on image data received in real time, and a multi-user association and event synchronization module including a user interaction module configured to perform user interaction processing, user event information processing and management, and AR content playback configured to perform interaction synchronization processing, content synchronization processing, and user information synchronization processing.
Abstract:
Provided are an apparatus and method for managing a feature point map. The method includes generating an initial travel path through which an environmental information collecting entity moves, determining the generated initial travel path as a travel path for detection and controlling the environmental information collecting entity along the determined travel path for detection, receiving environmental information from the environmental information collecting entity, extracting feature point information from the environmental information, generating a feature point map from the feature point information, and storing the feature point map.
Abstract:
An augmented reality device based on recognition of a spatial structure includes: a point cloud normal vector extracting unit extracting a normal vector for a point cloud from image data input from a camera; a plane object segmenting unit segmenting a plane in the image data by using the extracted normal vector; a representative plane selecting unit selecting a representative plane among the segmented planes; a spatial structure extracting unit recognizing a spatial structure by using the representative plane; and a virtual object matching unit matching a virtual object in the recognized spatial structure.
Abstract:
A method for deep metric learning per hierarchical step of multi-labels and few-shot inference using the same is provided, which includes sampling a plurality of N multiplets from a learning data set that is expressed by hierarchical multi-labels; configuring the N multiplets into triplets or quadruplets so as to correspond to the number of classes in each hierarchy; performing a metric learning per hierarchical step for a deep neural network model based on the configured triplets and quadruplets; and distributing, to an embedded device, the deep neural network model from which a loss function is removed as the metric learning is completed.
Abstract:
A providing apparatus for an augmented reality service includes: a parameter calculating unit calculating camera parameters of a plurality of respective cameras; a mesh information processing unit converting point cloud information based on images obtained from the plurality of respective cameras into mesh information for the plurality of respective cameras and converting the mesh information into a world coordinate for a target space photographed by the plurality of cameras by using the camera parameters; a map generating unit generating a whole map for the target space by considering an area where the converted mesh information for the plurality of respective cameras is duplicated; and an augmentation processing unit augmenting a virtual object to the whole map.
Abstract:
There are provided a device for displaying virtual reality overlapping the real world and a method thereof. A collimated display device for augmented reality includes a virtual image providing unit configured to modulate an image of the virtual object to light and project the result; and a collimation mirror made of a translucent material that reflects light of the image of the virtual object to a user's field of vision and provides the image of the virtual object overlapping the real world. Therefore, it is possible for the user to see an image of the virtual object that is an additional image matching the real world.