Full metadata record
DC FieldValueLanguage
dc.contributor.author郭明諭en_US
dc.contributor.authorKuo, Ming-Yuen_US
dc.contributor.author李鎮宜en_US
dc.contributor.authorLee, Chen-Yien_US
dc.date.accessioned2014-12-12T01:37:46Z-
dc.date.available2014-12-12T01:37:46Z-
dc.date.issued2010en_US
dc.identifier.urihttp://140.113.39.130/cdrfb3/record/nctu/#GT079711676en_US
dc.identifier.urihttp://hdl.handle.net/11536/44374-
dc.description.abstract此論文探討和分析了實作全文自適應二進位算術解碼器(CABAD)的策略。此外,我們提出了一個預測位元子(bin)趨勢的技術以改善數據之間的依賴性來提高產出,並且更進一步優化儲存系統以降低系統負擔於匯流排頻寬或內存空間。在我們的設計中,模擬數據結果顯示,該方法們可以得到90%以上的預測命中率和70%的使用空間減少率。而且在,我們的估計中,我們最小只需要17K的邏輯閘個數與3,360位元的SRAM就讓最高產出足以支援層級5.0主檔次(Main Profile)的H.264/AVC。我們提出的硬體架構運行在150兆赫(最大為232.5兆赫)且實現全高清視頻即時播放每秒30幀。因此,我們的設計可以在吞吐量和硬件成本之間得到一個很好的平衡。zh_TW
dc.description.abstractThis thesis discusses and analyzes the strategies of CABAD implementation. Furthermore, we proposed a bin-trend-predicted scheme to improve the data dependency and optimize the memory system to reduce the system overhead. In our design, simulation results show that the methods can get over 90% hit rate and 70% reduction rate. And, we require only 17k gate counts with 3,360 bits SRAM and can achieve Level 5.0 MP in our estimation. The proposed architecture operates on 150 MHz (Max. 232.5 MHz) for realizing full-HD video playback at 30 fps. Therefore, we take an excellent balance with throughput and hardware cost.en_US
dc.language.isoen_USen_US
dc.subjectH.264/AVCzh_TW
dc.subject二元算術編碼zh_TW
dc.subject算術編碼zh_TW
dc.subject解碼器zh_TW
dc.subject熵編解碼器zh_TW
dc.subjectH.264/AVCen_US
dc.subjectCABACen_US
dc.subjectArithmetic Codingen_US
dc.subjectCABAC Decoderen_US
dc.subjectEntropy Codingen_US
dc.title使用預測位元子即時對H.264/AVC之 全文自適應二進位算術解碼器zh_TW
dc.titleA Bin-predictable CABAC Decoder for real-time H.264/AVCen_US
dc.typeThesisen_US
dc.contributor.department電子研究所zh_TW
Appears in Collections:Thesis


Files in This Item:

  1. 167601.pdf
  2. 167602.pdf

If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.