System and method for detecting a boundary in images using machine learning

A computer-implemented method for detecting a boundary in images, the method comprising:

• receiving or accessing a first image comprising a first polygon including image data indicative of a boundary of an area of a structure;
• generating, using a data model representing a neural network, a second image based on the first image by dividing the area enclosed by the boundary of the structure in the first image, wherein the second image comprises a first portion of the area within the boundary and a second portion of the area within the boundary partitioned by a line across the structure, wherein the dividing of the area enclosed by the boundary of the structure is based at least in part on a coordinate location which is offset from the line;
• and
• generating, based on the second image, a geo-image comprising corresponding spatial-reference information for one or more pixels in the geo-image, the geo-image comprising one of the first portion and the second portion in the second image.

A non-transitory computer-readable storage medium storing instructions which when executed adapt at least one computing device to:

• receive or access a first image comprising a first polygon including image data indicative of a boundary of an area of a structure;
• generate, using a data model representing a neural network, a second image based on the first image by dividing the area enclosed by the boundary of the structure in the first image, wherein the second image comprises a first portion of the area within the boundary and a second portion of the area within the boundary partitioned by a line across the structure, wherein the dividing of the area enclosed by the boundary of the structure is based at least in part on a coordinate location which is offset from the line;
• and
• generate, based on the second image, a geo-image comprising corresponding spatial-reference information for one or more pixels in the geo-image, the geo-image comprising one of the first portion and the second portion in the second image.