Abstract
Nowadays, more and more families are willing to buy 3D TV to improve their watching experience. Stereo perception produced by watching 3D images or videos brings strong immersive watching experience to users. However, accumulated vision fatigue confuses users a lot after watching 3D TV for a long time. When watching 3D images, controlled by past recognition experience and visual attention mechanism, gaze point of two eyes is changing among different objects which have different depth of field. The eye movement in this changing process is called vergence. Vergence can be defined as movement of our eyes in opposite directions to locate the area of interest on the fovea and accommodation as alteration of the lens to obtain and maintain the area of interest focused on the fovea. So the more frequently the vergence process occurs, the more uncomfortable we feel. We expect to obtain several eye movement patterns, which can be considered as some typical visual attention patterns, by building a top-down recognition and visual attention model and then applying some clustering methods to find them. So we use an eye tracker to record eye movement data and then model it as a bayesian network model. The generative model is based on beta process and we build an Autoregression-HMM model to describe the relationship between latent eye movement patterns and eye movement data. To uncover parameters which represent different eye movement patterns in this model, we use MCMC method to calculate them with iterative computations. In this work, some different latent patterns existed in the sequential eye movement data can be revealed. After analyzing these patterns, we are able to find out some similarities and differences of visual attention models between different people watching the same image or between different images viewed by the same one. These conclusions can help to improve quality of 3D image thus lessening the users’ vision fatigue when watching 3D TV. This work also will contribute to understanding the relationship between visual attention, visual model and visual discomfort. A regression method can be applied to discover more specific conclusions in further research.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Ponce, C.R., Born, R.T.: Stereopsis. Curr. Biol. 18(18), R845–R850 (2008)
Yano, S., Emoto, M., Mitsuhashi, T.: Two factors in visual fatigue caused by stereoscopic HDTV images. Displays 25(4), 141–150 (2004)
Torralba, A., Oliva, A., Castelhano, M.S., Henderson, J.M.: Contextual guidance of eye movements and attention in real-world scenes: the role of global features in object search. Psychol. Rev. 113(4), 766–86 (2006)
Borji, A., Itti, L.: State-of-the-art in visual attention modeling. IEEE Trans. Patt. Anal. Mach. Intell. 35(1), 185–207 (2012)
Salah, A.A., Alpaydin, E., Akarun, L.: A selective attention-based method for visual pattern recognition with application to handwritten digit recognition and face recognition. IEEE Trans. Patt. Anal. Mach. Intell. 24(3), 420–425 (2002)
Liu, T., Yuan, Z., Sun, J., Wang, J., Zheng, N., Tang, X., Shum, H.Y.: Learning to detect a salient object. IEEE Trans. Patt. Anal. Mach. Intell. 33(2), 353–367 (2011)
Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems, pp. 545–552 (2007)
Avraham, T., Lindenbaum, M.: Esaliency (extended saliency): meaningful attention using stochastic image modeling. IEEE Trans. Patt. Anal. Mach. Intell. 32(4), 693 (2010)
Pang, D., Kimura, A., Takeuchi, T., Yamato, J., Kashino, K.: A stochastic model of selective visual attention with a dynamic Bayesian network. Technical report of IEICE PRMU 108:139–144 (2008)
Chikkerur, S., Serre, T., Tan, C., Poggio, T.: What and where: a Bayesian inference theory of attention. Vis. Res. 50(22), 2233–47 (2010)
Kienzle, W., Franz, M.O., SchLkopf, B., Wichmann, F.A.: Center-surround patterns emerge as optimal predictors for human saccade targets. J. Vis. 9(5:7), 1–15 (2009)
Peters, R.J., Itti, L.: Beyond bottom-up: incorporating task-dependent influences into a computational model of spatial attention. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Thibaux, R., Jordan, M.I.: Hierarchical Beta processes and the Indian buffet process. J. Mach. Learn. Res. 2(3), 564–571 (2007)
Ghahramani, Z., Griffiths, T.L., Sollich, P.: Bayesian nonparametric latent feature models. In: Bayesian Statistics, pp. 201–226 (2007)
Fox, E.B., Sudderth, E.B., Jordan, M.I., Willsky, A.S.: A sticky HDP-HMM with application to speaker diarization. Ann. Appl. Stat. 5(2A), 1020–1056 (2011)
Hughes, M.C., Fox, E.B., Sudderth, E.B.: Effective split-merge monte carlo methods for nonparametric models of sequential data. Adv. Neural Inf. Process. Syst. 25, 1295–1303 (2012)
ITU-R BT.1438: “Subjective Assessment of Stereoscopic Television Pictures” (2000)
Tobii®Technology: “Accuracy and Precision Test Method for Remote Eye Trackers,” 7 February 2011
Tobii®Technology: “Accuracy and Precision Test Report: Tobii X120 Eye Tracker,” June 2012
Ma, B., Zhou, J., Gu, X., Wang, M., Zhang, Y., Guo, X.: A new approach to create 3D fixation density maps for stereoscopic images. In: 3DTV-Conference: the True Vision - Capture, Transmission and Display of 3D Video, pp. 1–4 (2015)
Acknowledgments
Thanks for Micheal C Hughes’s open source project NPBayes toolbox on github. Our program’s realization is based on his work. The work for this paper was supported by NSFC under 61471234 and 61527804, and MOST under Contact 2015BAK05B03.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Zhang, C., Zhou, J., Zhu, S. (2018). The Statistic Modeling of Eye Movement Viewing S3D Images. In: Zhai, G., Zhou, J., Yang, X. (eds) Digital TV and Wireless Multimedia Communication. IFTC 2017. Communications in Computer and Information Science, vol 815. Springer, Singapore. https://doi.org/10.1007/978-981-10-8108-8_19
Download citation
DOI: https://doi.org/10.1007/978-981-10-8108-8_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-8107-1
Online ISBN: 978-981-10-8108-8
eBook Packages: Computer ScienceComputer Science (R0)