A video system for determining a region of interest in a video comprising a video source and a video processing system is provided. The video processing system is configured to receive the video from the video source and identify at least one object in the video which is in contact with the floor. The video processing system is further configured to determine a contact point between the object and the floor in a frame of the video and identify at least one polygon representing the floor in the frame, wherein the polygon includes the contact point. The video processing system is further configured to identify a three dimensional volume representing a space above the polygon extending to a designated height and select the region of interest by identifying a two dimensional area of the frame based on the three dimensional volume.