Three-dimensional wavelet transform (3D-DWT) encoders are good candidates for applications like professional video\r\nediting, video surveillance, multi-spectral satellite imaging, etc. where a frame must be reconstructed as quickly as\r\npossible. In this paper, we present a new 3D-DWT video encoder based on a fast run-length coding engine.\r\nFurthermore, we present several multicore optimizations to speed-up the 3D-DWT computation. An exhaustive\r\nevaluation of the proposed encoder (3D-GOP-RL) has been performed, and we have compared the evaluation results\r\nwith other video encoders in terms of rate/distortion (R/D), coding/decoding delay, and memory consumption.\r\nResults show that the proposed encoder obtains good R/D results for high-resolution video sequences with nearly\r\nin-place computation using only the memory needed to store a group of pictures. After applying the multicore\r\noptimization strategies over the 3D DWT, the proposed encoder is able to compress a full high-definition video\r\nsequence in real-time.
Loading....