注意力模型指导下的视频质量评价方法

Video Quality Assessment Method with Attention Model Guided

在视频质量评价方法中,常常需要对人眼视觉系统做出合理的假设,其中注意力模型就是一个很重要的因素。提出了一种在注意力模型指导下的视频质量评价方法,在图像帧的质量评价中加入了显著性区域信息,使之更能符合人眼视觉特性,并兼顾了视频中的运动信息,在一定程度上提高了客观质量评价方法的性能。

Among video quality assessment methods,assumptions about human visual system are made frequently,in order to accord with human psycho visual features and attention model plays an important role. In this paper, a video quality assessment method with attention model guided is proposed,in- corporating local image frame quality assessment with saliency information,also considering motion information in the video. It is testified that the pro- posed method enhances the performance of objective quality assessment.