Hilbert transform based workload estimation for low power surveillance video compression

In this paper, a workload estimation scheme is proposed for surveillance video encoding by using difference detection and Hilbert transform-based workload estimation model. Difference detection distributes the input video data according to their content similarity features and retrieves the encoding workload for the coded frames. Workload estimation model predicts the encoding workload for the following time slot using Hilbert transform and error control. Experimental results indicate that the proposed workload estimation model can provide accurate estimation results without performance hit to maintain the video encoding performance under a given performance constraint during power reduction.