Fusion-based side information generation for multi-view distributed video code of wireless video sensor networks

Distributed video coding (DVC) is a new paradigm in video coding. DVC offers flexible partitioning of the complexity between the encoder and decoder, robustness to channel errors due to intrinsic joint source-channel coding, codec independent scalability, and multi-view coding without communications between the cameras. This makes it very interesting for a wide range of applications, in particular Multimedia WSN. Multi-view DVC has recently received attention from the scientific community. Among the many challenging topics related to DSC there is the generation of the Side Information, which is estimated by the decoder of the data being decoded. This paper presents a new method for spatial side information generation of uncalibrated video sensor network, which is based on Trifocal Tensor. Then the spatial side information is fused with temporal intra-view side information to get better side information. Simulation results show that Trifocal Tensor-based spatial side information produces 1 to 2 dB improvement, while fusion-based side information produces 0.2 to 0.4 dB improvement in the PSNR of the rate-distortion plots. Visual performance is also improved.