An objective measurement tool for MPEG video quality
Signal Processing - Special issue on image and video quality metrics
Causal saliency effects during natural vision
Proceedings of the 2006 symposium on Eye tracking research & applications
A Coherent Computational Approach to Model Bottom-Up Visual Attention
IEEE Transactions on Pattern Analysis and Machine Intelligence
An introduction to ROC analysis
Pattern Recognition Letters - Special issue: ROC analysis in pattern recognition
SSIAI '08 Proceedings of the 2008 IEEE Southwest Symposium on Image Analysis and Interpretation
Do video coding impairments disturb the visual attention deployment?
Image Communication
Image quality assessment: from error visibility to structural similarity
IEEE Transactions on Image Processing
Image information and visual quality
IEEE Transactions on Image Processing
VSNR: A Wavelet-Based Visual Signal-to-Noise Ratio for Natural Images
IEEE Transactions on Image Processing
Hi-index | 0.00 |
The aim of this study is to understand how people watch a video sequence during free-viewing and quality assessment tasks. To this end, two eye tracking experiments were carried out. The video dataset is composed of 10 original video sequences and 50 impaired video sequences (five levels of impairments obtained by a H.264 video compression). A first experiment consisted in recording eye movements in a free-viewing task. The 10 original video sequences were used. The second experiment concerned an eye tracking experiment in a context of a subjective quality assessment. Eye movements were recorded while observers judged on the quality of the 50 impaired video sequences. The comparison between gaze allocations indicates the quality task has a moderate impact on the visual attention deployment. This impact increases with the presentation number of impaired video sequences. The locations of regions of interest remain highly similar after several presentations of the same video sequence, suggesting that eye movements are still driven by the low level visual features after several viewings. In addition, the level of distortion does not significantly alter the oculomotor behavior. Finally, we modified the pooling of an objective full-reference video quality metric by adjusting the weight applied on the distortions. This adjustment depends on the visual importance (the visual importance is deduced from the eye tracking experiment realized on the impaired video sequences). We observe that a saliency-based distortion pooling does not significantly improve the performances of the video quality metric.