Video quality enhancement based on visual attention model and multi-level exposure correction

Due to unfavorable environmental conditions such as lack of lighting, poor visual quality in images and videos may make intelligent image/video systems unstable. This means that visual quality enhancement plays an important role in image/video processing, computer vision, and pattern recognition. In this paper, we propose a video quality enhancement scheme based on visual attention model and multi-level exposure correction. To this end, the proposed scheme is composed of four parts: pre-processing, visual attention model generation, multi-level exposure correction, and temporal filtering. To extract more visual cues for visual attention model generation, a pre-processing is used to modify each frame. After preprocessing, facial and non-facial cues are measured to generate visual attention maps of each frame. On the basis of visual attention maps, a multi-level exposure correction algorithm is utilized to adjust the exposure level of each frame and then create several intermediate results. After fusing intermediate results, a synthesized image with good visual quality can be obtained. To avoid flicker effect, a temporal filter is exploited to make the variance of the exposure level small in the temporal domain. To evaluate the performance of the proposed scheme, some images/videos captured by mobile phones and digital cameras are tested. The experimental results show that the proposed scheme can effectively deal with the images/videos with low and high exposure levels. The results also demonstrate that the proposed scheme outperforms some existing methods in terms of visual quality.