System and method for identifying an object in an image
Abstract:
A method for processing image data includes identifying a background scene in a background frame of an image. Each of a plurality of pixel locations in the background frame is set as a respective background pixel. For each of the pixel locations, a respective running mean and a respective running variance are determined based on a brightness component of the background frame at the pixel location. A subsequent frame is identified as a current frame. For each of the pixel locations in the current frame identified as a background pixel, the running mean is updated based on one of a plurality of mean weights and the running variance is updated based one of a plurality of variance weights. For each of the pixel locations in the current frame, an identification is made if the current pixel location is one of a background pixel and a foreground pixel based on a brightness component of the current pixel location in the current frame, the running mean of the current pixel location, and the running variance of the current pixel location.
Public/Granted literature
Information query
Patent Agency Ranking
0/0