Systems and methods for content analysis to support navigation and annotation in expository videos

A non-transitory computer-readable medium embodying a set of computer-executable instructions, which, when executed in a computerized system comprising a central processing unit, a display device and a memory in connection with a captured video of a content being added to a medium, cause the computerized system to perform a method comprising:

• a. using the central processing unit to analyze changes within a plurality of frames of the captured video to automatically detect scrolling, depicted in the captured video, of the medium to which the content is being added (a video boundary event);
• b. using the central processing unit to automatically segment the video into a plurality of video segments based on the detected video boundary event;
• c. using the central processing unit to generate an overview image using at least a portion of the video, wherein the overview image is a single image comprising content from the plurality of video segments;
• d. using the central processing unit to map a plurality of portions of the overview image to the plurality of video segments;
• e. generating a graphical user interface on the display device, the graphical user interface comprising a first graphical user interface portion displaying at least the mapped plurality of portions of an overview image;
• and
• f. in response to detection of a selection event of one of the mapped plurality of portions of the overview image by a user, playing the video segment associated with the selected mapped portion of the overview image, wherein the video segment is played in a second portion of the generated graphical user interface.

A computerized system comprising a central processing unit, a display device and a memory storing a set of instructions executable in connection with a captured video of a content being added to a medium, the set of instructions comprising instructions for:

• a. automatically analyzing changes within a plurality of frames of the captured video to automatically detect scrolling, depicted in the captured video, of the medium to which the content is being added (a video boundary event);
• b. automatically segmenting the video into a plurality of video segments based on the detected video boundary event;
• c. generating an overview image using at least a portion of the video, wherein the overview image is a single image comprising content from the plurality of video segments;
• d. mapping a plurality of portions of the overview image to the plurality of video segments;
• e. generating a graphical user interface comprising a first graphical user interface portion on the display device, the graphical user interface displaying at least the mapped plurality of portions of an overview image;
• and
• f. in response to detection of a selection event of one of the mapped plurality of portions of the overview image by a user, playing the video segment associated with the selected mapped portion of the overview image, wherein the video segment is played in a second portion of the generated graphical user interface.