Systems and methods for automatic redaction of sensitive information from video streams

A method for automatic redaction of sensitive information from video streams, comprising:

• receiving, by an image processing computer program executed by an electronic device, a video stream of an office, a conference room, or a workspace;
• accessing, by the image processing computer program, a database comprising known locations of known fixed objects within the office, the conference room, or the workspace that are capable of having sensitive information thereon, wherein the known fixed objects consist of a whiteboard, a blackboard, a display, a desk, or a table;
• identifying, by the image processing computer program and using a deep neural network model, an object capable of having sensitive information thereon in the video stream of the office, the conference room, or the workspace, wherein the sensitive information comprises text or image data;
• matching, by the image processing computer program, a location of the object to one of the known locations of the known fixed objects within the office, the conference room, or the workspace;
• and
• redacting or obscuring, by the image processing computer program, the object in the video stream in response to the location of the object matching one of the known locations.