Abstract: Disclosed are a terminal device for indoor positioning based on object recognition, a service server, and a method therefor. A terminal device according to one aspect of the present invention comprises: a storage unit for storing an indoor map in which preset coordinate values for each object are matched; a photographing unit; and a control unit for recognizing first and second objects from an image obtained through the photographing unit, estimating the respective virtual space positions of the first and second objects, estimating a virtual space distance between a user and each of the first and second objects by using a virtual space position of the user and the virtual space positions of the first and second objects, and estimating an indoor position of the user by using the virtual space distance.

Abstract: Disclosed are an image-based indoor positioning service system and method. A service server includes a communication unit configured to receive a captured image of a node set in an indoor map, and a location estimation model generation unit configured to learn the captured image of the node received through the communication unit, segment the learned captured image to obtain objects, and selectively activate the objects in the learned image to generate a location estimation model.

Abstract: An apparatus for building a map is disclosed. The apparatus for building a map according to the present invention includes a data collection unit configured to separately collect vector data and raster data, a vector data processing unit configured to generate ground-truth images of a previously set size by processing the vector data, a raster data processing unit configured to generate divided raster images of the set size by processing the raster data, and a polygon generation unit configured to generate predicted polygons through machine learning of the ground-truth images and the divided raster images and generate polygons which can be applied to map building based on the raster data on the basis of the predicted polygons and the ground-truth images.

Abstract: An apparatus for building a map is disclosed. The apparatus for building a map according to the present invention includes a data collection unit configured to separately collect vector data and raster data, a vector data processing unit configured to generate ground-truth images of a previously set size by processing the vector data, a raster data processing unit configured to generate divided raster images of the set size by processing the raster data, and a polygon generation unit configured to generate predicted polygons through machine learning of the ground-truth images and the divided raster images and generate polygons which can be applied to map building based on the raster data on the basis of the predicted polygons and the ground-truth images.

Abstract: An exemplary embodiment of the present invention provides a method for providing a tour plan service by a tour service providing apparatus. The tour service providing apparatus determines a tendency of a first user based on Internet using information of the first user. The tour service providing apparatus searches at least one first place content corresponding to the tendency of the first user. And the tour service providing apparatus provides a first tour plan created by using the first place content, to the first user.

Abstract: A user-based map manufacturing apparatus includes an open street map (OSM) database (DB) configured to store OSM data, a map item DB configured to store a map item, and a map manufacturer configured to convert the OSM data into an OSM layer in an image format, and generate the map item in the OMS layer to manufacture a map.