计算机科学 ›› 2022, Vol. 49 ›› Issue (1): 194-203.doi: 10.11896/jsjkx.201100107
陈乐1, 高岭1,2, 任杰3, 党鑫1, 王祎昊1, 曹瑞1, 郑杰1, 王海1
CHEN Le1, GAO Ling1,2, REN Jie3, DANG Xin1, WANG Yi-hao1, CAO Rui1, ZHENG Jie1, WANG Hai1
摘要: 随着移动增强现实(Mobile Augmented Reality,MAR)技术的飞速发展,MAR应用的种类及功能也越来越丰富多样,与此同时用户对MAR应用的视频质量及响应时间也提出了更高的要求。通常来说,MAR应用会将计算密集型任务(目标识别及渲染)卸载到云端或边缘服务器进行处理,并将渲染后的图像下载到移动端。但由于移动网络状态的不稳定性及网络带宽的限制,海量数据的传输将延长MAR应用响应时间,进而增加移动设备的传输能耗开销,严重影响用户使用体验。由此,文中提出了一种基于梯度提升回归(Gradient Boosting Regression,GBR)的自适应码率控制模型。该模型通过感知当前网络环境及拍摄内容,预测用户观感需求并对非关注点部分进行低码率压缩,从而在不影响用户体验的情况下尽可能地降低传输数据量,缩短响应时间。具体来说,通过分析200个热门视频的视频特征,构建视频特征同用户观感需求的内在联系,从而针对不同的用户需求提供合适的视频码率配置,由此达到维持体验、减少时延、节约能耗的目标。实验结果显示,同直接下载渲染后的1080p视频相比,提出的自适应码率控制模型在尽可能维持用户观感体验的前提下,每帧的下载时间平均减少了58%(19.13 ms)。
中图分类号:
[1]CHEN H X,DAI Y T,MENG H,et al.Understanding the cha-racteristics of mobile augmented reality applications[C]//2018 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).Piscataway NJ:IEEE,2018:128-138. [2]ZHOU Y Q,SUN B L,QI Y L,et al.Mobile AR/VR in 5Gbased on csonvergence of communication and computing[J].Telecommunications Science,2018,34(8):19-33. [3]LIU G Q.Research on offloading strategy based on mobile edge computing[D].Harbin:Harbin Institute of Technology,2018. [4]SHAUKAT N.Minimization of energy consumption for mobile edge computing-based augmented reality application[D].Beijing:Beijing University of Post and Telecommunication,2019. [5]GALIH S,IANSYAH S,YUDISTIRA H.Location and orientation based augmented reality mobile application for enhancing heritage landmark history and information[J].Universal Journal of Electrical and Electronic Engineering,2019,6(2A):39-45. [6]KICO I,LIAROKAPIS F.Investigating the learning process of folk dances using mobile augmented reality[J].Applied Sciences,2020,10(2):599. [7]CHEN Y H,RAVINDRANATH L,DENG S,et al.Glimpse:Continuous,real-time object recognition on mobile devices[C]//Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems(Sensys).New York NY:ACM,2015:155-168. [8]REN J,GAO L,YU J L,et al.Energy-efficient Deep Learning Task Scheduling Strategy for Edge Device[J].Chinese Journal of Computers,2020,43(3):440-452. [9]LIU L Y,LI H Y,GRUTESER M.Edge assisted real-time object detection for mobile augmented reality[C]//Proc of the the 25th Annual International Conference on Mobile Computing and Networking(MobiCom'19).New York NY:ACM,2019:1-16. [10]ZHANG W X,LIN S K,BIJARBOONEH F H.CloudAR:A Cloud-based Framework for Mobile Augmented Reality[C]//Proceedings of the on Thematic Workshops of ACM Multimedia(Workshops '17).2017:194-200. [11]QIAN F,HAN B,XIAO Q Y.Flare:practical viewport-adaptive 360-degree video streaming for mobile devices[C]//:Proc of the 24th Annual International Conference on Mobile Computing and Networking(MobiCom'18).New York NY:ACM,India,2018:99-114. [12]LENG Y,CHEN C C,SUN Q Y,et al.Energy-efficient videoprocessing for virtual reality[C]//Proceedings of the 46th International Symposium on Computer Architecture (ISCA).New York NY:ACM,2019:91-103. [13]RUAN X K,CHEN H L,ZHU X D,et al.Deep decision:a mobile deep learning framework for edge video analytics[C]//INFOCOM,IEEE Conference on Computer Communications (INFOCOM).Piscataway NJ:IEEE,2018:1421-1429. [14]ZHAO H,SHI J,QI X,et al.Pyramid scene parsing network[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2017:2881-2890. [15]LI Y,SHI J,LIN D.Low-latency video semantic segmentation[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2018:5997-6005. [16]GADDE R,JAMPANI V,GEHLER P V.Semantic video cnns through representation warping[C]//The IEEE Interational Conference on Computer Vision (ICCV).Piscataway NJ:IEEE,2017:4453-4462. [17]ZHU X,XIONG Y,DAI J,et al.Deep feature flow for video re-cognition[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2017:2349-2358. [18]LIU N,HAN J.Deep hierarchical saliency network for salient object detection[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2016:678-686. [19]WANG L,LU H,RUAN X,et al.Deep networks for saliencydetection via local estimation and global search[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2015:3183-3192. [20]ZHAO R,OUYANG W,LI H,et al.Saliency detection by multi-context deep learning[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2015:1265-1274. [21]DONOSER M,URSCHLER M,HIRZER M,et al.Saliencydriven total variation segmentation[C]//The IEEE Interational Conference on Computer Vision(ICCV).Piscataway NJ:IEEE,2009:817-824. [22]BAI X,WANG W,LIANG J.An active contour model based on region saliency for image segmentation[J].Journal of Computer Research and Development,2012:49(12):2686-2695. [23]BORJI A,FRINTROP S,SIHITE D L,et al.Adaptive objecttracking by learning background context[C]//2012 IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition Workshops.Piscataway NJ:IEEE,2012:23-30. [24]GAO Y,WANG M,TAO D,et al.3-D object retrieval and re-cognition with hypergraph analysis[J].IEEE Transactions on Image Processing,2012,21(9):4290-4303. [25]REN J,WANG X,FANG J.Proteus:network-aware web browsing on heterogeneous mobile systems[C]//Proc of the 14th International Conference on Emerging Networking Experiments and Technologies.New York NY:ACM,2018:379-392. [26]REN J,YUAN L,NURMI P,et al.Camel:smart,adaptive energy optimization for mobile web interactions[C]//IEEE Confe-rence on Computer Communications (INFOCOM).Piscataway NJ:IEEE,2020:119-128. [27]QIN Q,REN J,GAO L,et al.To compress,or not to compress:Characterizing deep learning model compression for embedded inference[C]//2018 IEEE Intl Symp on Parallel and Distributed Processing with Applications(ISPA).Piscataway NJ:IEEE,2019:729-736 [28]MARK B,ADRIAN C,GUN L.A survey of augmented reality[M].Boston,Amercia:Now Publishers Foundations and Trends,2015:126-146 [29]HOU Q I,CHEN M M,HU X,et al.Deeply supervised salient object detection with short connections [C]//The IEEEConfe-rence on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2017:3203-3212 [30]WAN S,YANG Z F.A new generation of efficient video coding H.265/HEVC:principle,standard and implementation[M].Beijing Publishing House of Electronics Industry,2014:2-15. [31]BT R I.Methodology for the subjective assessment of videoquality in multimedia applications[S].Geneva:The InternationalTelecommunication Union (ITU),2007. [32]SEVCIK L,BEHAN L,FRNDA J,et al.Prediction of subjective video quality based on objective assessment[C]//2018 26th Te-lecommunications Forum (TELFOR).Piscataway NJ:IEEE,2018:1-4. [33]JEROME H F.Greedy Function approximation:a gradient boosting machine[J].Annals of Statistics,2001,29(5):1189-1232. [34]LEO B.Bagging predictors[J].Machine Learning,1996(24):123-140 [35]FREUND Y,SCHAPIRE R E.A decision-theoretic generalization of on-line learning and an application to boosting[J].Journal of Computer and System Sciences,1997,55(1):119-139. [36]BREIMAN L,FRIEDMAN J H,OLSHEN R A,et al.Classification and regression trees[J].International Biometric Society,1984,40(3):874-874. [37]BLAU Y,MICHAELI T.The perception-distortion Tradeoff[C]//The IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Piscataway NJ:IEEE,2018:6228-6237. [38]ANISH M,RAJIV S,ALAN B.Making a “Completely Blind” Image Quality Analyzer[J].IEEE Signal Processing Letters,2013,20(3):209-212. [39]MA C,YANG C,YANG X.Learning a No-Reference Quality Metric for Single-Image Super-Resolution[J].Computer Vision and Image Understanding,2016,158:1-16. |
[1] | 赵磊, 周金和. 基于复杂网络内容场的ICN能效优化策略 ICN Energy Efficiency Optimization Strategy Based on Content Field of Complex Networks 计算机科学, 2019, 46(9): 137-142. https://doi.org/10.11896/j.issn.1002-137X.2019.09.019 |
[2] | 朱维军, 王鑫, 钟英辉, 樊永文, 陈永华. 一种基于梯度提升回归树的系外行星宜居性预测方法 Habitability Prediction of Exoplanets Based on GBRT Algorithm 计算机科学, 2019, 46(6A): 71-73. |
[3] | 沈夏炯, 张俊涛, 韩道军. 基于梯度提升回归树的短时交通流预测模型 Short-term Traffic Flow Prediction Model Based on Gradient Boosting Regression Tree 计算机科学, 2018, 45(6): 222-227. https://doi.org/10.11896/j.issn.1002-137X.2018.06.040 |
[4] | 邢文凯,高雪霞,侯小毛,翟萍. 云计算环境下的模糊解耦能效优化算法研究 Research on Fuzzy Decoupling Energy Efficiency Optimization Algorithm in Cloud Computing Environment 计算机科学, 2017, 44(12): 75-79. https://doi.org/10.11896/j.issn.1002-137X.2017.12.015 |
|