Brand penetration determination system using image semantic content

A computing system comprising:

• a geographic sub-region determination system configured to partition a geographic area into two or more sub-regions;
• a camera configured to obtain a collection of images associated with the two or more sub-regions;
• an image content analysis engine configured to determine, based at least in part on a machine-learned image content analysis model trained to detect one or more of text and logos associated with the brand within each image of the collection of images associated with the two or more sub-regions, a number of detections of a brand within each respective sub-region;
• a brand penetration index generation system configured to generate a brand penetration index for each sub-region, wherein the brand penetration index is based on the number of detections of the brand in the respective sub-region;
• wherein the geographic sub-region determination system is configured to determine, in splitting the geographic area into two or more sub-regions, the number of sub-regions and one or more boundaries of each sub-region so as to ensure that the population within each sub-region is above a threshold;
• and
• one or more tangible, computer-readable media configured to store the brand penetration index for each sub-region in association with an indicator of the respective sub-region.

One or more tangible, non-transitory, computer-readable media storing computer executable instructions that when executed by one or more processors cause the one or more processors to perform a method, the method comprising:

• splitting a geographic area into two or more sub-regions;
• obtaining a collection of images associated with the two or more sub-regions;
• determining, based at least in part on output from a machine-learned image content analysis model trained to detect one or more of text and logos associated with the brand within each image of the collection of images associated with the two or more sub-regions, a number of detections of a brand within each respective sub-region;
• generating a brand penetration index for each sub-region, wherein the brand penetration index is based on the number of detections of the brand in the respective sub-region;
• and
• storing the brand penetration index for each sub-region in memory in association with an indicator of the respective sub-region.