Abstract: The distributed characteristics of video surveillance systems are evident, and the complexity of the sampling side can be reduced by adopting an appropriate distributed video sampling scheme. Since compressive sensing also exhibits distributed characteristics, it is considered to have great application potential in distributed video sampling schemes. In order to facilitate the application of compressive sensing in distributed surveillance video systems, adaptive rate compressive sensing is investigated. Based on statistical characteristics estimation, the mean and variance of unknown original video subblocks are estimated from the measurements obtained through compressive sensing, and subblocks are rapidly clustered. The sparsity of subblocks in each cluster is then estimated, and the sampling rate is allocated accordingly. The video adaptive rate compressive sensing is implemented, and the consumption of sampling rate is reduced without causing degradation in video reconstruction quality or significantly increasing sampling complexity. Simulation results demonstrate that the proposed method effectively allocates the sampling rate, and the computational complexity of sampling meets the requirements of actual sampling equipment.

Key words: surveillance video, compressive sensing , adaptive rate sampling , statistical characteristics estimation , subblock clustering ,  sparse representation