A system and method of selecting an area of interest from a plurality of images captured by a plurality of cameras are described. The method includes receiving a request for an area of interest from a plurality of images, the area of interest containing an object of interest selected by a user, the object of interest being captured in one or more images captured by one or more of the plurality of cameras, the plurality of cameras having overlapping field of views; determining a camera within the plurality of cameras that wholly contains the area of interest; transforming the physical location of the object of interest into a pixel position such that the area of interest being essentially centered around the pixel position corresponding to the physical location of the object of interest; and extracting the area of interest.