Apparatus for building map using machine learning and image processing
OwnerJu Hum Parkinventor
Life of this patent
Estimating the term…
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.
Claims15
A method for building a map using machine learning and image processing comprising:
- separately collecting vector data and raster data;
- generating ground-truth images of a previously set size by processing the vector data;
- generating divided raster images of the set size by processing the raster data;
- and
- generating predicted polygons through machine learning of the ground-truth images and the divided raster images and generating polygons which can be applied to raster data-based map building based on the predicted polygons and the ground-truth images;
- wherein the predicted polygons are generated through machine learning of the ground-truth images and the divided raster images;
- and
- predicted vector data is generated by converting the predicted polygons into vector data;
- and
- an accuracy of the predicted vector data is verified by comparing the ground-truth images and the predicted vector data and the predicted polygons are determined as polygons which can be applied to map building based on the raster data according to a verification result.
Dependencies are inferred from the claim text.