Distributed Compressive Video Sensing with Adaptive Reconstruction Based on Temporal Correlation

Aiming at enhance reconstruction quality, this paper proposes an adaptive reconstruction scheme with no feedback channel for distributed compressive video sensing, effectively exploiting temporal correlation. Specifically, the proposed scheme divides each block of non-key frames into different classifications based on temporal correlation in the encoding side and selects corresponding reconstruction mode which adaptively utilizes side information in the decoding side. The simulation results show that the proposed scheme achieves superior performance over existing methods in terms of reconstruction quality and computation cost.