A video quality assessment method may include frame-by-frame analysis of a test video sequence (often compressed) with its original (reference) counterpart, pre-conditioning elements of the test and reference frames, defining a region of interest in the pre-conditioned test frame and estimating relative errors within the region of interest between the test and reference frame, filtering the estimated errors of the region of interest temporally across adjacent frames within a perpetually relevant time window, aggregating the filtered errors within the time window, ranking the aggregated errors, selecting a subset of the ranked errors, aggregating across the selected subset of errors, and inputting said aggregated error to a quality assessment system to determine a quality classification along with an estimated quality assessment.