臺灣博碩士論文加值系統

隨著資訊科技的改變，多媒體檔案儲存、串流影音朝向雲端化發展；行動裝置的普及，人們都可透過手機觀看影片。然而，不論是雲端伺服器每月的數據使用量，或行動上網（3G、4G）的數據使用量，都有用量計價（Pay as You Go）的機制，或是頻寬限制，因而造成了許多不必要的成本及支出。
為此，本論文為解決上述問題，透過仔細的分析研究後，開發了一套「可以透過行動裝置偵測環境光，調整影像、影音串流的品質，進而達到節省用戶端、伺服器端的數據使用量」的系統。
最後，將本論文提出的方法，實作成伺服器應用程式與用戶端行動裝置應用程式，收集使用者的回饋，產生出對應該使用者當下環境光的品質的影片，讓使用者無法辨識出畫質的好壞，進而實現本論文的目的。

Technology advances have changed many things like multimedia storage and streaming video from local servers to cloud servers. After smart phones have become popular, people can use their phones to watch videoes. However, the network transfer service from the cloud is not unlimited, as it depends on how much you pay (Pay as You Go). Also, the mobile network transfer and speed are also limited. All of these make client users and service providers spend money to increase network transfer efficiency.
Thus, to solve the aforementioned problems, we did some study, and we proposed a system that can change video quality depending on luminance and decrease the network transfer usage accordingly.
Finally, we developed a system with the server application and the client application based on our proposed method. We collected user's feedback based on their current luminance, and generated a video with their feedback and the luminance. The users couldn't tell the difference between the original video and the adjusted one easily. As a result, we proved our methods, can help to reduce the amount of data transfer.

推薦書 ....................................................................... I
審定書 ....................................................................... II
中文摘要..................................................................... III
ABSTRACT................................................................ IV
誌 謝 ........................................................................ V
表目錄 .......................................................................VIII
圖目錄 ....................................................................... IX
第一章 緒論 ................................................................. 1
1.1 摘要 ............................................................................ 1
1.2 論文架構 ....................................................................... 1
第二章 相關文獻 ............................................................ 2
2.1 視覺顯著區塊偵測............................................................. 2
2.1.1 Saliency Detection: A Spectral Residual Approach . . . . . . . . 2
2.1.2 A Corner-based Saliency Model . . . . . . . . . . . . . . . . . . 3
2.2 影像品質的調整 ............................................................... 4
2.2.1 Non-Local Means Denoising . . . . . . . . . . . . . . . . . . . . 4
2.3 影像相似度的衡量............................................................. 6
2.3.1 Image Quality Assessment: From Error Visibility to Structural
Similarity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.4 影片片段的分隔 ............................................................... 7
2.4.1 A Shot Boundary Detection Method Based on Color Feature . . 7
2.4.2 視訊加密搜尋與檢索 . . . . . . . . . . . . . . . . . . . . . . . . 8
第三章 影像品質的調整...................................................... 10
3.1 產生視覺顯著區塊（Saliency Map） ......................................... 10
3.2 依照環境光取得前景與背景................................................... 10
3.3 將背景去雜訊 .................................................................. 11
3.4 產生新的影像 .................................................................. 12
3.5 整合後的方法 .................................................................. 13
第四章 系統流程 ............................................................ 14
4.1 伺服器端 - 影片前處理........................................................ 14
4.2 用戶端 - 如何選擇畫質........................................................ 14
4.3 伺服器端 - 如何產生適合該使用者畫質的影片 .............................. 15
第五章 系統實驗 ............................................................ 16
5.1 實驗一：針對影像做測試 ..................................................... 16
5.1.1 參數定義 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
5.1.2 使用Unity模擬環境光 . . . . . . . . . . . . . . . . . . . . . . . 17
5.1.3 計算SSIM目的 . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
5.1.4 流程說明 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
5.2 實驗二：使用者測試 .......................................................... 18
5.2.1 實驗環境 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
5.2.2 情境說明 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
5.3 結果比較 ....................................................................... 19
5.3.1 實驗一 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
5.3.2 實驗二 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
第六章 結論與未來展望...................................................... 21
參考文獻..................................................................... 22

Xiaodi Hou and Liqing Zhang.
Saliency Detection: A Spectral Residual Approach
IEEE Conference on Computer Vision and Pattern Recognition, 2007.

Wirawit Rueopas, Sangsan Leelhapantu, and Thanarat H Chalidabhongse.
A Corner-based Saliency Model
13th International Joint Conference on Computer Science and Software Engineering (JCSSE), 2016.

Xiaodi Hou and Liqing Zhang
A Non-Local Algorithm for Image Denoising
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005

H. Barlow.
Possible Principles Underlying the Transformation of Sensory Messages
IEEE Sensory Communication, 1961

Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, and Eero P. Simoncelli
Image Quality Assessment: From Error Visibility to Structural Similarity
IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600−612, Apr. 2004

Laurent Itti, Christof Koch
A saliency-based search mechanism for overt and covert shifts of visual attention
Vision Research 40 1489–1506, 2000

Herve Jegou, Matthijs Douze and Cordelia Schmid.
Hamming Embedding and Weak geometry consistency for large scale image search
Proceedings of the 10th European conference on Computer vision, October, 2008

Hua Zhang, Ruimin Hu and Lin Song.
A Shot Boundary Detection Method Based on Color Feature
Proceedings of International Conference on Computer Science and Network Technology, 2011

Hsing-Ching Chang, Chuan-Kai Yang.
視訊加密搜尋與檢索
Computer Graphics Workshop 2013, CGW 2013