低密度同位檢查碼在分散式視訊編碼中之效能評估與加速

Abstract

分散式視訊編碼是一種新興起的應用，它顛覆了傳統的壓縮方式，將原本必須在編碼端大量計算的複雜度移至解碼端來做，這樣的好處是在行動裝置上都可以使用這類的編碼，在客戶端進行簡單的編碼，再傳送至伺服器端進行高複雜度的解碼。而分散式視訊編碼目前採用的流量控制有三種，這些流量控制主要是在估計編碼端需傳送多少的位元給解碼端以幫助解碼端順利解碼。另外，還有兩種可調式低密度同位檢查碼被採用在分散式視訊編碼中，分別是累加式低密度同位檢查碼以及可調長度式低密度同位檢查碼，不過到目前為止，上述的三種流量控制以及兩種可調式低密度同位檢查碼皆還沒有被完整的評估過，因此，在本篇論文中，我們將針對這三種流量控制以及兩種可調式低密度同位檢查碼分別做比較以及評估其試用環境。 除此之外，在有回饋式通道的分散式視訊編碼中，解碼端的高複雜度一直是個有待解決的問題，這個高複雜度主要是因為解碼端不斷地送出檢查碼請求所導致的。因此，我們提出了兩種降低複雜度的方法，一種是在圖形處理器上將低密度同位檢查碼的遞迴計算平行化，另一種則是降低解碼端送出檢查碼請求的次數。而實驗結果也證明了，藉由這兩種加速的方法，可以在損失些微的比率失真下達到高速的運算。

Distributed video coding (DVC) is a new coding paradigm targeting applications with the need for low-complexity encoding at the cost of a higher decoding complexity, using different types of rate control which is responsible for estimating how many syndromes are required for WZ video decoding. On the other hand, two well known rate-compatible LDPC codes, 1) LDPC Accumulate (LDPCA) code and 2) rateless LDPC code, have been proposed and successfully integrated into DVC. So far, the different rate controls and the two rate-compatible LDPC codes have never been compared under a fair emulation. Thus, we evaluate and compare them in this thesis. Besides, in the DVC architecture based on a feedback channel, the high decoding complexity is mainly due to the request-decode operation with repetitively fixed step size (induced by Slepian–Wolf decoding). In this thesis, a parallel message-passing decoding algorithm for low density parity check (LDPC) syndrome is applied through Compute Unified Device Architecture (CUDA) based on General-Purpose Graphics Processing Unit (GPGPU). Furthermore, we propose an approach to reduce the number of requests dubbed as Ladder Request Step Size (LRSS) which leads to more speedup gain. Experimental results show that, through our work, significant speedup in decoding time is achieved with negligible loss in rate-distortion (RD) performance.