Video processing using topological map

A videoconferencing system, comprising:

• a sensor configured to capture sequential frames of video image data during a videoconference;
• and
• a processing subsystem configured to:
• designate at least one group of pixels within a given frame of the sequential frames of video image data as an active area of interest, based on filtering individual pixels of the given frame to identify pixels of interest and applying a multidimensional filter to the pixels of interest to identify the at least one group of pixels;
• based upon one or more inclusion criteria, include the active area of interest within a stack, wherein the stack occupies a primary frame within a two-dimensional video space;
• update a topological map of the two-dimensional video space dependent upon the stack;
• identify a framing region within the topological map;
• and
• adjust framing of a primary imaging camera based on the framing region.

A computer-implemented method, comprising:

• receiving data indicative of an active area of interest detected within a video frame captured by a detection system;
• based upon one or more inclusion criteria, including the active area of interest within a stack of previously identified active areas of interest, wherein the stack occupies a primary frame within a two-dimensional video space;
• updating a topological map of the two-dimensional video space based upon the stack;
• and
• using the topological map, identifying a feature of interest within the two-dimensional video space.