Aspects of the embodiments described herein are related to systems, methods, and computer products for performing video redaction. When performing video redaction, a video is received and converted into a plurality of frames. For each of the frames, it is detected if one or more people are present in at least one of the plurality of frames. Bounding regions are determined for the detected people in each frame. The bounding regions are tagged with an identifier identifying the person associated with each bounding region. An icon identifying the detected person is determined and displayed on an interface as a selectable input, wherein each selectable input is selectable to redact or keep the detected person in the video. Once a selection to redact a person is received, the bounding regions of the selected person are filled with replacement pixels. The plurality of frames are then converted into a new video.