Systems and methods for automatically generating training image sets for an environment

A computing system for generating a training set of images and labels for a native environment, the computing system comprising at least one processor in communication with at least one memory device, wherein the at least one processor is configured to:

• receive a plurality of physical coordinate sets;
• retrieve, from the at least one memory device, environmental model data corresponding to a georeferenced model of the native environment, the environmental model data defining a plurality of environmental features, wherein the environmental model data links an internal coordinate system of the georeferenced model to a system of geographic coordinates;
• create a plurality of two-dimensional (2-D) rendered images from the environmental model data, each of the 2-D rendered images corresponding to a view from one of the physical coordinate sets, the plurality of 2-D rendered images including one or more of the environmental features;
• generate linking data associating each of the 2-D rendered images with (i) labels for the one or more included environmental features, and (ii) a corresponding native image;
• and
• store the training set including the 2-D rendered images, the labels, the corresponding native images, and the linking data.

A non-transitory computer-readable storage medium having computer-executable instructions embodied thereon for generating a training set of images and labels for a native environment, wherein when executed by at least one processor in communication with at least one memory device, the computer-executable instructions cause the at least one processor to:

• receive a plurality of physical coordinate sets;
• retrieve, from the at least one memory device, environmental model data corresponding to a georeferenced model of the native environment, the environmental model data defining a plurality of environmental features;
• create a plurality of two-dimensional (2-D) rendered images from the environmental model data, each of the 2-D rendered images corresponding to a view from one of the physical coordinate sets, the plurality of 2-D rendered images including one or more of the environmental features;
• calculate, for each 2-D rendered image, metadata based on the environmental model data, the metadata including a spatial relationship from the physical coordinate set to at least one of the one or more environmental features;
• generate linking data associating each of the 2-D rendered images with (i) labels for the one or more included environmental features, (ii) a corresponding native image, and (iii) the metadata;
• and
• store the training set including the 2-D rendered images, the labels, the corresponding native images, the metadata, and the linking data.