Research On Video Spatial - Temporal Resolution Adjustment

With the development of digital video processing and the boom of wireless network, digital video has become an important media to transport information via cellphones, tablets and other portable devices. In recent years, the increasing demands of high-quality video can only be met by videos of higher temporal resolutions and more flexible spatial resolutions.This paper focuses on the adjustment of video spatial-temporal resolutions, which is made up of two parts. The first part introduces a low complexity image interpolation algorithm to improve video temporal resolution and the second part presents a video retargeting method with higher spatial-temporal coherence.Image interpolation, the problem of producing a sequence of intermediate frames between two input images, is of significant interest. In this paper, we achieve an improved path-based interpolation method based on the original path-based framework, by introducing two innovative improvements. On one hand, we use optical flow to decide the direction of path, to constraint the path length and to maintain the global path coherency, which improves the efficiency significantly. On the other hand, we introduce the pixel interlacing model to obtain more accurate optical flows so that the accuracy of path selection will be improved a lot. Our improved path-based method performs as well as the original method in various interpolation applications in image quality and surpass the original method by a large scale in efficiency.Image retargeting makes it possible for images to display on the screens with different resolutions or arbitrary aspect ratios. When it comes to video retargeting, a removal, or carving of non-salient regions may cause some degree of distortion or discontinuousness of video content, which would lead to artifacts both temporally and spatially. The artifacts should be reduced by considering the salient content in the target video and enforcing spatial and temporal coherence at the same time. In this paper, we propose a new algorithm for video retargeting based on the discontinuous seam carving approaches and we enhance those approaches with several novel ideas. We have included the optical flow to achieve the temporal coherence and designed a new scheme to select the initial seam to maintain the spatial coherence. Experimental results show that the performance of vide retargeting can be improved significantly after including our proposed technique.