Skip to Main content Skip to Navigation

Bruits temporels de compression et perception de la qualité vidéo : mesure et correction

Abstract : Home video has gone through three major transitions within the past years: from the MPEG2 videocompression norm to the h.264 one, from cathode ray tube screens to liquid crystal display screens andfrom standard definition (576x720) to High-Definition (1280x720 or 1920x1080). Those changes havemodified the importance of each type of compression artifacts for quality assessment, relatively to oneanother. The two main compression artifacts are currently blur and temporal defects, including under thisterm temporal variations of spatial defects and artifacts specifically temporal such as mosquito noise.We first focused on filtering mosquito noise and presented the TVIF, a corrector adapted to this noise:small amplitude compared to the nearest edge, proximity to edges and variation through time. We firsttried to use objective quality metrics to assess the performance of our corrector. As it proved to beinconclusive, we set up a subjective experiment which showed that observers perceived our corrector asan enhancement and that they preferred the spatio-temporal correction to the spatial one. Going backover objective evaluations with the subjective ones showed that the metrics we used correctly assessneither the correction nor the gain in quality of the spatio-temporal correction over the spatial one.We then set up an experiment combining quality evaluation (both global and temporal) and recordings ofeye movements. The aim of this experiment is to specify some key points for designing an objectivetemporal quality metric. One example is that observers found that temporal variations of blocking effectare the most annoying defect global quality and, as such, should be the main focus of a temporal qualitymetric. Analysis of eye-movements of observers during free task, global quality task and temporal qualitytask shows, among other things, that quality has no visible influence on the places observers watch buthighly influences the duration of fixations. The evolutions over time of all the oculomotor parameters(saccades speed, fixation locations and durations) are similar for the three tasks during the first 1 or 2seconds of the videos and that the differences between tasks appear later on. It seems that the task toassess video quality plays a role afterwards on the deployment of visual attention.
Document type :
Complete list of metadata

Cited literature [100 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Tuesday, March 20, 2012 - 10:42:34 AM
Last modification on : Friday, March 25, 2022 - 9:41:00 AM
Long-term archiving on: : Thursday, June 21, 2012 - 2:36:41 AM


Version validated by the jury (STAR)


  • HAL Id : tel-00680787, version 1



Claire Mantel. Bruits temporels de compression et perception de la qualité vidéo : mesure et correction. Autre. Université de Grenoble, 2011. Français. ⟨NNT : 2011GRENT023⟩. ⟨tel-00680787⟩



Record views


Files downloads