Abstract: A system and method for tracing polygons in a drawing source file. The method includes extracting vector imagery from the source file, creating a planar representation of the vector imagery as a plurality of lines, filtering the plurality of lines to create simplified line art, morphologically dilating the simplified line art to generate a polygonal approximation, calculating geometric difference between the source file canvas bounds and the polygonal approximation to identify contracted polygons, morphologically dilating the contracted polygons to create visual polygons, and filtering the visual polygons according to one or more geometric parameters to identify salient polygons.

Abstract: Systems and methods for creating electronic indoor maps from computer-assisted-design (CAD) files are disclosed. The methods involve receiving a set of CAD files relating to a facility, classifying each CAD file of the set as a site plan or a floor plan, defining one or more layers of at least one electronic map for the facility based on the set, generating an electronic map for each CAD file of the set. The electronic map includes one or more layers and each layer include at least one object. The method also involves aligning objects in the electronic map for the facility, based on the layer of the object; assigning text data in each CAD file of the set to an object in the electronic map file of that CAD file; and storing the at least one electronic map for the facility on at least one storage component.

Abstract: Systems and methods for semantic segmentation of a source geometry are provided. The method includes providing a vector image of a location; generating a raster image from the vector image, the raster image including at least one partition, the at least one partition including a plurality of pixels; assigning a pixel class label to each of the plurality of pixels, the pixel class label including a usage type; and assigning a partition class label to the at least one partition based on the pixel class labels assigned to the plurality of pixels, wherein the partition class label includes a usage type for the partition.

Abstract: Computer-implemented systems and methods for geometry simplification and filtering are provided. The systems and methods may provide for automated simplification and filtering of visually complex architectural diagrams to their most important features, as may be desirable for creating maps that are true to real world instantiations. The method may use a conditional generative adversarial network (cGAN) that may be particularly well suited to identifying geometry in feature-poor architectural drawings.

Abstract: Systems and methods for semantic segmentation of a source geometry are provided. The method includes providing a vector image of a location; generating a raster image from the vector image, the raster image including at least one partition, the at least one partition including a plurality of pixels; assigning a pixel class label to each of the plurality of pixels, the pixel class label including a usage type; and assigning a partition class label to the at least one partition based on the pixel class labels assigned to the plurality of pixels, wherein the partition class label includes a usage type for the partition.

Abstract: A system and method for tracing polygons in a drawing source file. The method includes extracting vector imagery from the source file, creating a planar representation of the vector imagery as a plurality of lines, filtering the plurality of lines to create simplified line art, morphologically dilating the simplified line art to generate a polygonal approximation, calculating geometric difference between the source file canvas bounds and the polygonal approximation to identify contracted polygons, morphologically dilating the contracted polygons to create visual polygons, and filtering the visual polygons according to one or more geometric parameters to identify salient polygons.

Abstract: Systems and methods for creating electronic indoor maps from computer-assisted-design (CAD) files are disclosed. The methods involve receiving a set of CAD files relating to a facility, classifying each CAD file of the set as a site plan or a floor plan, defining one or more layers of at least one electronic map for the facility based on the set, generating an electronic map for each CAD file of the set. The electronic map includes one or more layers and each layer include at least one object. The method also involves aligning objects in the electronic map for the facility, based on the layer of the object; assigning text data in each CAD file of the set to an object in the electronic map file of that CAD file; and storing the at least one electronic map for the facility on at least one storage component.