Viewpoint Switching Prediction Model for Multi-view Video Based on Viewing Logs

Transcription

1 2013 Short Paper Viewpoint Switching Prediction Model for Multi-view Video Based on Viewing Logs 207 Atsushi Asakura Takatsugu Hirayama Takafumi Marutani Jien Kato Kenji Mase Graduate School of Information Science Nagoya University hirayama/ R-GIRO Ritsumeikan Global Innovation Research Organization (R-GIRO), Ritsumeikan University Graduate School of Information Science Nagoya University jien/ mase/ keywords: multi-view video, video streaming, switching prediction, viewing logs. Summary Multi-view video consists of multiple views which are shot simultaneously by multiple cameras from different viewpoints. Users can watch the video while choosing a viewpoint from them freely. In the multi-view video streaming, we need to deal with a problem that the multi-view videos put an enormous burden on the network for delivering because of transmitting many videos at a same time. Hierarchical multi-view streaming(hmvs) has been proposed as one of the methods of reducing the transmission quantity of multi-view video. The prediction of switching viewpoints is necessary for bandwidth allocation in HMVS. In this paper, we propose a viewpoint switching prediction model based on viewing logs for HMVS. The proposed model divides the sequence of multi-view video into some scenes and learns the probability of switching viewpoints for each scene from viewing logs. Through the evaluation experiment, the proposed model achieved effective viewpoint switching predictions Multiview Video Coding MVC [Guo 06][Merkle 07][Ho 07] MVC MVC MVC [Lou 05][Kurutepe 07][Pan 11] Pan [Pan 11] Hierarchical Multiview Streaming HMVS

2 SP3-F 2014 [ 12] HMVS HMVS MVC HMVS HMVS 1 2 HMVS Web Peg-Scope Viewer W-PSV [Marutani 12] W-PSV 1 Microsoft Silverlight W-PSV HMVS Silverlight SmoothStreaming W-PSV 1 1 W-PSV [ 11] W-PSV 映像表示部 1 2. 視点選択部 Web Peg-Scope Viewer(W-PSV) C t S t C t t C t = {c c Z,1 c C max } C max S t t p(c t C t 1,S t 1 )= p(c t,c t 1,S t 1 ) p(c t 1,S t 1 ) t 1 C t 1 S t 1 t C t (1) C t = C t 1 2 p(c t C t 1,S t 1 )=1.0 (2) 1 C t C max,c t C t 1 (1) (1)

3 209 視点 視点遷移確率 p(ct Ct-1, St-1) Cmax Ct-1 St Ct? t-1 t 時刻 2. (1) 3 () B W-PSV (:15 :8 ) T ( ) T = 1,2,3,4,5,6,7,8,9,10,15,30,60

4 SP3-F タッチライン C=1 C=12 S=1 S=2 S=3 S=4 C=6 (C S D =4) D 4 D =4 D 1 15 (C t 1,S t 1 ) (1) C t C t 1 p(c t C t 1,S t 1 ) 3 3 leave-one-out (LOOCV) n t (C n,t,c n,t 1,S n,t 1 ) n t 1 S t 1 C t 1 t C t n p N n (C t C t 1,S t 1 ) (C n,t,c n,t 1,S n,t 1 ) p N n (C n,t C n,t 1,S n,t 1 ) n t,c t C t 1 p N n (C n,t C n,t 1,S n,t 1 ) n n (3) 3 4 T LOOCV 5(a) T (3) T = D LOOCV 5(b) D (3) D = Pan [Pan 11] 6 C t 1 = c p(c t = c 1 C t 1 )=p(c t = c +1 C t 1 )= 0.5,p(C t c 1 C t 1 )=p(c t c +1 C t 1 )= (= 1/(12 1))

5 211 (a) 6 5 (b) (a) T (b) D (2) leave-one-out ( ) % Z=

6 SP3-F 2014 W-PSV (SCOPE) [Guo 06] Guo, X., Lu, Y., Wu, F., Gao, W., and Li, S.: Distributed multi-view video coding, in Electronic Imaging 2006, pp T 60770TInternational Society for Optics and Photonics (2006) [Ho 07] Ho, Y.-S. and Oh, K.-J.: Overview of Multi-view Video Coding, in Systems, Signals and Image Processing, 2007 and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services. 14th International Workshop on, pp (2007) [Kurutepe 07] Kurutepe, E., Civanlar, M., and Tekalp, A.: Client- Driven Selective Streaming of Multiview Video for Interactive 3DTV, Circuits and Systems for Video Technology, IEEE Transactions on, Vol. 17, No. 11, pp (2007) [Lou 05] Lou, J.-G., Cai, H., and Li, J.: A real-time interactive multiview video system, in Proceedings of the 13th annual ACM international conference on Multimedia, MULTIMEDIA 05, pp , New York, NY, USA (2005), ACM [Marutani 12] Marutani, T., Mase, K., Fujii, T., and Kawamoto, T.: Multi-view video contents viewing system by synchronized multiview streaming architecture, in Proceedings of the 20th ACM international conference on Multimedia, MM 12, pp , Nara, Japan (2012) [ 12],,,,.IE,, Vol. 111, No. 478, pp (2012) [Merkle 07] Merkle, P., Smolic, A., Muller, K., and Wiegand, T.: Multi-View Video Plus Depth Representation and Coding, in Image Processing, ICIP IEEE International Conference on, Vol. 1, pp. I 201 I 204 (2007) [ 11],,,,,,,.EC,, Vol. 2011, No. 1, pp. 1 6 (2011) [Pan 11] Pan, Z., Ikuta, Y., Bandai, M., and Watanabe, T.: A User Dependent System for Multi-view Video Transmission, in Advanced Information Networking and Applications (AINA), 2011 IEEE International Conference on, pp (2011) ACM R-GIRO ( ) Oxford () IEEE Computer Society NTT MIT (ATR) , 2013