The performance of a video fingerprinting system, which is usually measured in terms of pairwise independence and robustness, is directly related to the fingerprint that the system uses. This paper has proposed a novel fingerprinting methods base on the gradient orientations of the luminance centroid, which is not only pairwisely independent but also robust against common video processing steps including lossy compression, resizing, frame rate change, global change in brightness, color, gamma, etc.