A Novel Quality Metric Using Spatiotemporal Correlational Data of Human Eye Maneuver

Abstract

The popularly used subjective estimator-mean opinion score (MOS) is often biased by the testing environment, viewers mode, domain expertise, and many other factors that may actively influence on actual assessment. We therefore, devise a noreference subjective quality assessment metric by exploiting the nature of human eye browsing on videos. The participants' eyetracker recorded gaze-data indicate more concentrated eyetraversing approach for relatively better quality. We calculate the Length, Angle, Pupil-size, and Gaze-duration features from the recorded gaze trajectory. The content and resolution invariant operation is carried out prior to synthesizing them using an adaptive weighted function to develop a new quality metric using eye traversal (QMET). Tested results reveal that the quality evaluation carried out by QMET demonstrates a strong correlation with the most widely used peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and the MOS.

Uniform Color Space-Based High Dynamic Range Video Compression

“…Furthermore, the algorithm can also be further evaluated across other HDR video sequences especially those processed with the BT.2020 primaries [41] at higher bit-depths such as 12-and 14-bits/pixel/channel when optimized codec support becomes available. Finally, the objective and subjective evaluations can also be extended using two recently developed quality assessment metrics using eyetracking data such as the no-reference metric proposed in [42] and spatiotemporal correlation data using eye tracking as proposed in [43]. However, their suitability for HDR video content also needs to be verified before they can be used to evaluate the HDR video compression algorithms.…”