Interactive tools to identify and label objects in video frames

An apparatus, comprising:

• memory storing instructions;
• and
• at least one processor configured via the instructions to:
• receive first inputs from a user, the first inputs representative of first aspects of an object shown in a first frame of video image;
• infer, using an artificial neural network and based at least in part on the first inputs, second aspects of the object shown in a second frame of video image;
• present, via a user interface, the second aspects of the object inferred using the artificial neural network for the second frame of video image;
• receive, via the user interface, second inputs from the user, the second inputs representative of a correction to the second aspects inferred by the artificial neural network;
• and
• store user identified object labels indicative of the first inputs and separate inferred object labels indicative of at least one of the second aspects that is not corrected based on the second inputs, wherein the separate inferred object labels are not corrected or otherwise changed by the user.

A non-transitory computer readable storage medium storing instructions which, when executed by a microprocessor in a computing device, causes the computing device to perform a method, comprising:

• presenting a graphical user interface of an interactive tool;
• showing a first frame of a video clip in the graphical user interface;
• receiving, via the graphical user interface, first user inputs labeling first aspects of an object in the first frame;
• inferring, using an artificial neural network and based at least in part on the first user inputs, second aspects to be labeled for the object in a second frame of the video clip;
• presenting, in the graphical user interface, the second frame with the second aspects inferred using the artificial neural network for the second frame of the video clip;
• receiving, via the graphical user interface, second inputs to confirm or modify the second aspects inferred using the artificial neural network, wherein one of the second inputs comprises an input to delete an identification of an object that is not of interest in the second frame;
• and
• storing user identified object labels indicative of the first inputs and separate inferred object labels indicative of at least one of the second aspects that is not corrected based on the second inputs.