Sparse representations-based super-resolution of key-frames extracted from frames-sequences generated by a visual sensor network.

摘要: Visual sensor networks (VSNs) usually generate a low-resolution (LR) frame-sequence due to energy and processing constraints. These LR-frames are not very appropriate for use in certain surveillance applications. It is important enhance the resolution of captured using enhancement schemes. In this paper, an effective framework super-resolution (SR) scheme proposed that enhances LR key-frames extracted from frame-sequences by visual-sensors. VSN, visual hub (VPH) collects huge amount data camera sensors. framework, at VPH, our recent key-frame extraction technique streamed base station (BS) after compression. A novel SR applied BS produce high-resolution (HR) output received key-frames. The uses optimized orthogonal matching pursuit (OOMP) sparse-representation recovery SR. OOMP does better terms detecting true sparsity than (OMP). This property helps HR image which closer original image. K-SVD dictionary learning procedure incorporated learning. Batch-OMP improves process removing limitation handling large set observed signals. Experimental results validate effectiveness show its superiority over other state-of-the-art