Neural network-based recognition of trade workers present on industrial sites

A non-transitory computer-readable medium, wherein the non- transitory computer-readable medium is provisioned with program instructions that, when executed by at least one processor, cause a computing platform to:

• receive, via one or more cameras positioned on a construction site, a plurality of images;
• detect, within the plurality of images, a plurality of objects being worn by respective workers on the construction site;
• select, from the plurality of images, a set of images depicting a particular worker, the set of images comprising a first object of the plurality of objects being worn by the particular worker and a second object of the plurality of objects being worn by the particular worker;
• and
• based on (i) the selected set of images depicting the particular worker and (ii) the first object and the second object that, when worn together, are indicative of a particular trade of a plurality of trades, determine a plurality of trade probabilities for the particular worker, each trade probability in the plurality of trade probabilities indicating a likelihood that the particular worker belongs to a respective trade from among the plurality of trades.

A method carried out by a computing platform, the method comprising:

• receiving, via one or more cameras positioned on a construction site, a plurality of images;
• detecting, within the plurality of images, a plurality of objects being worn by respective workers on the construction site;
• selecting, from the plurality of images, a set of images depicting a particular worker, the set of images comprising a first object of the plurality of objects being worn by the particular worker and a second object of the plurality of objects being worn by the particular worker;
• and
• based on (i) the selected set of images depicting the particular worker and (ii) the first object and the second object that, when worn together, are indicative of a particular trade of a plurality of trades, determining a plurality of trade probabilities for the particular worker, each trade probability in the plurality of trade probabilities indicating a likelihood that the particular worker belongs to a respective trade from among the plurality of trades.