A method and system are provided. In one embodiment, a video image is preprocessed from a video camera to separate objects to be tracked from the rest of the video image. Statistics for the tracked objects and the rest of the video image are computed. Further, a quality measure based on the statistics for the tracked objects and the rest of the video image are generated. The quality measure indicates the suitability of the video image for use by an object tracking system. The generating of the quality measure maximizes saturation of each of the tracked objects. Further, the video camera is tuned to increase the quality measure beyond a threshold.