Extracting video clips from videos for use in training a machine-learning model

A computer-implemented method comprising:

• training a model with a set of training data to identify an object and a corresponding spatial location of the object in each image frame in a video depicting performance of a wellsite activity;
• analyzing a plurality of consecutive image frames in the video using the trained model to identify a target image frame in which the object is present in a predefined spatial area thereof, wherein the predefined spatial area is associated with performance of the wellsite activity;
• and
• generating a video clip that includes only a subpart of the video based on the target image frame, the subpart including a series of consecutive image frames containing the target image frame.

A non-transitory computer-readable medium comprising program code that is executable by one or more processors for causing the one or more processors to:

• train a model with a set of training data to identify an object and a corresponding spatial location of the object in each image frame in a video depicting performance of a wellsite activity;
• analyze a plurality of consecutive image frames in the video using the trained model to identify a target image frame in which the object is present in a predefined spatial area thereof, wherein the predefined spatial area is associated with performance of the wellsite activity;
• and
• generate a video clip that includes only a subpart of the video based on the target image frame, the subpart including a series of consecutive image frames containing the target image frame.