Systems and methods for creating a story board with forensic video analysis on a video repository

A method comprising:

• processing one or more video streams to identify, locate and track one or more persons and/or one or more objects captured in the one or more video streams;
• identifying a navigation pattern for at least some of the identified, located and tracked persons and/or objects captured in the one or more video streams;
• based on the identified navigation patterns, identifying one or more interactions between at least some of the identified, located and tracked persons and/or objects captured in one or more video streams;
• identifying one or more relationships between at least some of the identified, located and tracked persons and/or objects captured in one or more video streams;
• generating metadata that is representative of the identified, located and tracked persons and/or objects, the identified interactions and the identified one or more relationships;
• and
• presenting a story of a selected one of the identified, located and tracked persons and/or objects based at least in part on the metadata, the story represents at least one of the one or more identified interactions involving the selected one of the identified, located and tracked persons and/or objects, wherein the story includes a logical or chronological view of at least part of two or more of the plurality of video data streams summarizing the at least one of the one or more identified interactions.

A non-transitory computer readable medium storing instructions thereon that when executed by one or more processors causes the one or more processors to:

• process one or more video streams to identify, locate and track one or more persons and/or one or more objects captured in the one or more video streams;
• identify a navigation pattern for at least some of the identified, located and tracked persons and/or objects captured in the one or more video streams;
• receive a user input via a user interface identifying an initial person and/or initial object depicted in a video stream of a plurality of video streams;
• based on the identified navigation patterns, identify one or more interactions between the initial person and/or initial object identified by the user input and one or more other persons and/or other objects captured in at least one of the one or more video streams;
• and
• generate a storyboard that summarizes one or more of the interactions between the initial person and/or initial object and one or more of the other persons and/or other objects, wherein storyboard includes a logical or chronological view of at least part of two or more of the plurality of video data streams summarizing the one or more of the interactions.