eduzhai > Applied Sciences > Engineering >

No-Reference Video Quality Assessment Using Space-Time Chips

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 6 pages

Abstract: We propose a new prototype model for no-reference video quality assessment(VQA) based on the natural statistics of space-time chips of videos. Space-timechips (ST-chips) are a new, quality-aware feature space which we define asspace-time localized cuts of video data in directions that are determined bythe local motion flow. We use parametrized distribution fits to the bandpasshistograms of space-time chips to characterize quality, and show that theparameters from these models are affected by distortion and can hence be usedto objectively predict the quality of videos. Our prototype method, which wecall ChipQA-0, is agnostic to the types of distortion affecting the video, andis based on identifying and quantifying deviations from the expected statisticsof natural, undistorted ST-chips in order to predict video quality. We trainand test our resulting model on several large VQA databases and show that ourmodel achieves high correlation against human judgments of video quality and iscompetitive with state-of-the-art models.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...