Extending knowledge data in machine vision

A system comprising:

• one or more processors;
• and
• one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, configure a machine-vision system to perform operations comprising:
• obtaining a trained-synthetic dataset associated with a virtual-sporting event, features of the trained-synthetic dataset including at least two of:
• a tagged part of a representation of a player;
• a silhouette of the representation of the player;
• a center-heat map associated with the representation of the player;
• and
• a bounding box associated with the representation of the player;
• performing one or more iterations of extending the trained-synthetic dataset using a real-life dataset associated with an actual sporting event including recognized results, the extending including:
• identifying a portion of the recognized results from the real-life dataset;
• selecting the portion of the recognized results from the real-life dataset for annotation;
• annotating the portion of the recognized results from the real-life dataset to generate an annotated portion;
• adding the annotated portion to the trained-synthetic dataset to obtain an extended-trained dataset;
• storing the extended-trained dataset;
• determining whether learned data from the extended-trained dataset represents improved detection of the features compared to the trained-synthetic dataset;
• based on improvement of detection of the features and availability of another portion of the recognized results, repeating the extending using a part of the extended-trained dataset as the trained-synthetic dataset in a next iteration;
• and
• providing the extended-trained dataset to the machine-vision system.

A computer-implemented method comprising:

• detecting a first feature associated with a virtual-sporting event as a first detected feature;
• detecting a second feature associated with the virtual-sporting event as a second detected feature;
• providing the first detected feature and the second detected feature as input to a machine-vision system to identify at least a first portion of a representation of the virtual-sporting event;
• and
• combining the first detected feature and the second detected feature to validate the first portion of the representation of the virtual-sporting event.