Video enhancement using spatial and temporal super-resolution from a multi-camera system

Abstract

Super-Resolution (SR) covers a set of techniques whose objective is to improve the resolution of a video sequence or a single frame. In this scope, a fusion SR algorithm has been used, where High-Resolution (HR) images are constructed from several observed Low-Resolution (LR) images. In this paper, this approach is combined with a Multi-Camera (MC) system to take advantage of the spatial and temporal correlations between the recorded sequences, in order to improve the quality of the super-resolved HR sequence. The results show that the proposed combination outperforms the quality of typical SR applications, such as consumer electronics, surveillance video or remote sensing.