none｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	徐漢驊 Han-Hua Hsu
論文名稱：	Utility-Based Volumetric Media Streaming under Error-Prone FoV Prediction
指導教授：	黃志煒 Chih-Wei Huang
口試委員:
學位類別：	碩士 Master
系所名稱：	資訊電機學院 - 通訊工程學系 Department of Communication Engineering
論文出版年：	2022
畢業學年度：	110
語文別：	英文
論文頁數：	39
中文關鍵詞：	積體影像串流、點雲、資源分配、機器學習、邊緣運算、六自由度
外文關鍵詞：	volumetric streaming, ressource allocation, confidence score, QoE
相關次數：	點閱：14 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

隨著行動多媒體服務迅速的發展，尤其是超高畫質影像串流和虛擬實境的出現，前瞻多媒體應用，如元宇宙 (Metaverse) 等，逐漸成為行動服務的主流方向，議題的討論也越來越多。隨之而來的挑戰是，串流影像的同時嚴格維持超高畫質影像品質。也就是說，無線網路必須提共更低的延遲並擁有更高傳輸率的服務，這也是下一代行動技術持續討論的議題。為此，第三代夥伴計畫 (3rd Federation Partnership Project，3GPP) 的 5G 標準中定義了許多的功能和選項給更強大且更有彈性的無線網路環境，新的規格可以讓系統在流量、延遲以及可靠性三方面有更好的表現，但是同時也讓無線資源管理的複雜度直線上升。由於複雜度的上升，現有的傳統資源管理方法效果有限，所以我們希望透過增強式學習方法來解決 5G/6G 標準下無線網路資源管理的問題，並實現示範應用場域。。

With the rapid development of mobile multimedia services, especially the emergence of ultra-high-definition video streaming and virtual reality, forward-looking multimedia applications, such as Metaverse, have gradually become the mainstream direction of mobile services, and the discussion of the topic has become more and more more and more. The challenge that comes with it is to strictly maintain ultra-high-definition image quality while streaming. That is to say, wireless networks must provide services with lower latency and higher transmission rates, which are also ongoing discussions on next-generation mobile technologies. To this end, the 5G standard of the 3rd Generation Partnership Project (3GPP) defines many functions and options for a more powerful and resilient wireless network environment. The three aspects of delay and reliability have better performance, but at the same time, the complexity of wireless resource management has skyrocketed. Due to the increase in complexity, the existing traditional resource management methods have limited effect, so we hope to solve the problem of wireless network resource management under the 5G/6G standard through the reinforcement learning method, and realize the demonstration application field.

Introduction...........................................1
1 Volumetric Media Streaming...........................1
2 Motivation...........................................2
3 Contribution.........................................3
4 Framework............................................3
Related Works..........................................5
1 Point Cloud Streaming................................5
2 Prediction of User FoV in Volumaetric Streaming......6
3 User’s QoE Evaluation................................7
System Model and Problem Formulation...................8
1 Point Cloud Streaming Simulation Framework...........8
2 Design of Prediction Models..........................9
3 Tile-based Utility Calculation.......................10
Likelihood Map Generation and Resource Allocation......12
1 Likelihood Map Generation............................12
2 Resource Allocation of Tiles.........................13
Experimental Results...................................16
1 Output of Prediction Models..........................16
2 Utility Improvement of Likelihood Map................17
3 User Experience Improvement..........................18
Conclusions............................................21
1 Conclusion...........................................21
2 Future Work..........................................21
Bibliography.............................................22
                                

[1] Yassin Alkhalili, Tobias Meuser, and Ralf Steinmetz. A survey of volumetric content streaming approaches. In 2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), pages 191–199, 2020.
[2] Eman Ramadan, Arvind Narayanan, Udhaya Kumar Dayalan, Rostand A. K. Fezeu, Feng Qian, and Zhi-Li Zhang. Case for 5g-aware video streaming applications. In Proceedings of the 1st Workshop on 5G Measurements, Modeling, and Use Cases, 5G-MeMU ’21, page 27–34, New York, NY, USA, 2021. Association for Computing Machinery.
[3] Serhan Gul, Sebastian Bosse, Dimitri Podborski, Thomas Schierl, and Cornelius Hellge. Kalman filter-based head motion prediction for cloud-based mixed reality. In Proceedings of the 28th ACM International Conference on Multimedia, MM ’20, page 3632–3641, New York, NY, USA, 2020. Association for Computing Machinery.
[4] Serhan Gul, Dimitri Podborski, Thomas Buchholz, Thomas Schierl, and Cornelius Hellge. Low-latency cloud-based volumetric video streaming using head motion prediction. In Proceedings of the 30th ACM Workshop on Network and Operating Systems Support for Digital Audio and Video, NOSSDAV ’20, page 27–33, New York, NY, USA, 2020. Association for Computing Machinery.
[5] D. Graziosi, O. Nakagami, S. Kuma, A. Zaghetto, T. Suzuki, and A. Tabatabai. An overview of ongoing point cloud compression standardization activities: videobased (v-pcc) and geometry-based (g-pcc). APSIPA Transactions on Signal and Information Processing, 9:e13, 2020.
[6] Jounsup Park, Philip A. Chou, and Jenq-Neng Hwang. Rate-utility optimized streaming of volumetric media for augmented reality. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(1):149–162, 2019.
[7] Jounsup Park, Philip A. Chou, and Jenq-Neng Hwang. Volumetric media streaming for augmented reality. In 2018 IEEE Global Communications Conference (GLOBECOM), pages 1–6, 2018.
[8] Feng Qian, Bo Han, Jarrell Pair, and Vijay Gopalakrishnan. Toward practical volumetric video streaming on commodity smartphones. In Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications, pages 135–140, 2019.
[9] Jeroen van der Hooft, Maria Torres Vega, Tim Wauters, Christian Timmerer, Ali C. Begen, Filip De Turck, and Raimund Schatz. From capturing to rendering: Volumetric media delivery with six degrees of freedom. IEEE Communications Magazine, 58(10):49–55, 2020.
[10] Jeroen van der Hooft, Tim Wauters, Filip De Turck, Christian Timmerer, and Hermann Hellwagner. Towards 6dof http adaptive streaming through point cloud compression. In Proceedings of the 27th ACM International Conference on Multimedia, MM ’19, page 2405–2413, New York, NY, USA, 2019. Association for Computing Machinery.
[11] Jie Li, Cong Zhang, Zhi Liu, Wei Sun, and Qiyue Li. Joint communication and computational resource allocation for qoe-driven point cloud video streaming. In ICC 2020 - 2020 IEEE International Conference on Communications (ICC), pages 1–6, 2020.
[12] Yiqun Xu, Wei Hu, Shanshe Wang, Xinfeng Zhang, Shiqi Wang, Siwei Ma, and Wen Gao. Cluster-based point cloud coding with normal weighted graph fourier transform. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 1753–1757, 2018.
[13] Mohammad Hosseini and Christian Timmerer. Dynamic adaptive point cloud streaming. In Proceedings of the 23rd Packet Video Workshop, pages 25–30, 2018.
[14] Sebastian Schwarz, Marius Preda, Vittorio Baroncini, Madhukar Budagavi, PabloCesar, Philip A Chou, Robert A Cohen, Maja Krivokuca, S ´ ebastien Lasserre, Zhu ´Li, et al. Emerging mpeg standards for point cloud compression. IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 9(1):133–148, 2018.
[15] Shishir Subramanyam, Irene Viola, Alan Hanjalic, and Pablo Cesar. User centered adaptive streaming of dynamic point clouds with low complexity tiling. In Proceedings of the 28th ACM International Conference on Multimedia, MM ’20, page 3669–3677, New York, NY, USA, 2020. Association for Computing Machinery.
[16] Xinwei Chen, Ali Taleb Zadeh Kasgari, and Walid Saad. Deep learning for contentbased personalized viewport prediction of 360-degree vr videos. IEEE Networking Letters, 2(2):81–84, 2020.
[17] Dario DR Morais, Lucas S Althoff, Ravi Prakash, Marcelo M Carvalho, and Mylene CQ Farias. A content-based viewport prediction model. ` Electronic Imaging, 2021(9):255–1, 2021.
[18] Eugene d’Eon, Bob Harrison, Taos Myers, and Philip A. Chou. 8i voxelized full bodies, version 2 – a voxelized point cloud dataset. ISO/IEC JTC1/SC29 Joint WG11/WG1 (MPEG/JPEG) input document m40059/M74006, January 2017.
[19] Charles Corbiere, Nicolas Thome, Antoine Saporta, Tuan-Hung Vu, Matthieu Cord, and Patrick Perez. Confidence estimation via auxiliary models. IEEE Transactions on Pattern Analysis and Machine Intelligence, pages 1–1, 2021.
[20] Shaoang Li, Changyang She, Yonghui Li, and Branka Vucetic. Constrained deep reinforcement learning for low-latency wireless vr video streaming. In 2021 IEEE Global Communications Conference (GLOBECOM), pages 01–06, 2021.

簡易檢索 / 詳目顯示

相關論文