Mimicking human visual system in detecting blockiness artifacts in compressed video streams
AssigneeMicrosoft Corporation
InventorsWalid S. I. Ali, Rony Ferzli
Life of this patent
Estimating the term…
Abstract
A low complexity block-based, no-reference objective blockiness metric is provided that may be combined with other artifact metrics to measure overall quality of received video stream in a video conferencing application such that measures can be taken at the transmitter or in post-processing to enhance video quality. Prior knowledge of the blockiness boundaries may be used to reduce number of computations in determining the blockiness of a particular video frame.
Claims20
A method to be executed at least in part in a computing device for providing a blockiness metric associated with received video quality in a video conference system, the method comprising:
- receiving a decoded video frame at a post-processing module;
- computing a blockiness metric for columns of the decoded video frame based on an autocorrelation value and a cross-correlation value of each column;
- computing a blockiness metric for rows of the decoded video frame based on an autocorrelation and a cross-correlation of each row;
- and
- combining the blockiness metric for the columns and the blockiness metric for the rows to obtain an overall blockiness metric for the decoded video frame.
A computing device capable of providing video conferencing services, the computing device comprising:
- a video capture device;
- a pre-processing module;
- an encoder;
- a decoder;
- a post-processing module configured to:
- receive a decoded video frame;
- compute a blockiness metric for columns of the decoded video frame based on averaging autocorrelation and cross-correlation values of each column;
- compute a blockiness metric for rows of the decoded video frame based on averaging autocorrelation and cross-correlation values of each row;
- combine the blockiness metrics for the columns and the rows to obtain an overall blockiness metric for the decoded video frame;
- and
- scale the overall blockiness metric by applying a non-linear logistic function to replicate a behavior of Human Visual System (HSV), wherein the scaled overall blockiness metric is used to adjust at least one operational parameter of the video conference system for automatically enhance received video;
- and
- a display device for displaying the enhanced video.
A computer-readable memory device having instructions stored thereon for providing video conferencing services, the instructions comprising:
- receiving a decoded video frame at a post-processing module;
- computing a blockiness metric for columns of the decoded video frame based on averaging a ratio of autocorrelation and cross-correlation values of each column;
- computing a blockiness metric for rows of the decoded video frame based on averaging a ratio of autocorrelation and cross-correlation values of each row;
- combining the blockiness metric for the columns and the blockiness metric for the rows to obtain overall blockiness metrics for Y, U, and V planes of the decoded video frame;
- combining the overall blockiness metrics for Y, U, and V planes of the decoded video frame in a weighted manner;
- scaling the overall blockiness metric by:
- determining a maximum overall blockiness metric among a predefined number of decoded video frames;
- determining an exponential model based on the determined maximum overall blockiness metric;
- and
- applying the exponential model to the overall blockiness metrics of the predefined number of decoded video frames such that the overall blockiness metrics have defined lower and upper limits.
Dependencies are inferred from the claim text.