一個針對可調視訊編碼中跨層編碼與位元流擷取之位元率-失真最佳化模型

Abstract

可調視訊編碼標準(SVC)使觀看裝置可以使用位元流擷取機制調整其視訊接收內容。正因可調視訊編碼提供了結合空間、時間與畫質上的可調性，為不同觀看裝置擷取適當的位元流時需要經過特別考慮，不適當的選擇經常會產生粗劣的觀賞品質。在本論文中，我們提出了一個針對可調視訊編碼位元流進行位元率-失真(R-D)最佳化擷取的方法。精確地說，我們針對可調視訊編碼壓縮時的量化參數與跨層編碼相依性之設定，發展一組可適應性規則，遵循此規則所產生的良適性可調視訊編碼位元流(Well-adapted SVC bitstream)可在連續增益步驟中所擷取之可調層產生明顯較好的位元率-失真平衡。我們亦正式定義最佳化與近似最佳化擷取路徑的概念，並設計了在運算量上相當有效率的擷取路徑搜尋策略。實驗的結果展示出我們的位元率-失真最佳化的適應性設定方法與擷取策略可在不同觀賞裝置的播放畫面品質達到重大的改善。特別的是，我們的可適應性規則可保證沿著所找出的最佳擷取路徑之位元率-失真曲線具有凸狀的特性，並使得貪婪探索式擷取策略(Greedy Heuristic)可用以找出最佳化或近似最佳化之路徑，而此最簡單之搜尋策略比起暴力搜尋法(Exhaustive Search)只需要大約一半的運算複雜度。

The Scalable Video Coding (SVC) standard enables viewing devices to adapt their video reception using bitstream extraction. Since SVC offers spatial, temporal, and quality combined scalability, extracting proper bitstreams for different viewing devices can be a non-trivial task, and naive choices usually produce poor playback quality. In this thesis, we propose an approach for performing rate-distortion (R-D) optimal extraction of SVC bitstreams. Specifically, we developed a set of adaptation rules for setting the quantization parameters and the inter-layer dependencies among the SVC encoding layers. A well-adapted SVC bitstream thus produced manifest good R-D trade-offs when its scalable layers are extracted in successive refinement steps. We also formalized the notion of optimal and near-optimal extraction paths and devised computationally efficient strategies to search for the extraction paths. Experimental results demonstrated that our R-D optimized adaptation schemes and extraction strategies offer significant improvement in playback picture quality on various viewing devices. In particular, our adaptation rules promise R-D convexity along optimal extraction paths and permit the greedy heuristic extraction strategy to be used for discovering the optimal/near-optimal paths. This simplest strategy performs only half of the computation necessary for an exhaustive search.