Low-complexity distributed multi-view video coding for wireless video sensor networks based on compressive sensing theory

Sparsity is an attractive feature of images. Images can be efficiently represented using a few significant coefficients and sparse reconstructed from a small set of random linear measurements by utilizing the sparse feature in compressive sensing theory. Storage and transmission of multi-view video sequences involve large volumes of redundant data. These data can be efficiently compressed with techniques which encode the signals independently and decode them jointly. By integrating the respective characteristics of compressive sensing and distributed source coding, we propose a novel multi-view video coding approach for use in resource limited devices such as wireless video sensor networks. The proposed approach can explore the sparsity of video images, allow for low complexity encoder and the exploitation of inter-camera correlation without communications among cameras. Simulation results show the proposed framework outperforms the baseline compressive sensing-based scheme of intra frame coding by 3–5 dB. Compared with conventional H.264 or DVC scheme, the proposed frameworks simple while the quality of reconstructed image and compressibility are kept.