Dynamic Textures Dataset

Summary

Dataset can be accessed from these links coming soon.

• Dynamic textures dataset
• Homogeneous dynamic textures dataset
• Dynamic texture recognition dataset
• UCLA-50 version
• Dynamic texture segmentation dataset
• Dynamic shape and appearance models

Related publications include (Doretto & Soatto, 2006), (Doretto et al., 2004), (Doretto et al., 2003), (Doretto et al., 2003), (Saisan et al., 2001).

References

1. TPAMI

   Dynamic shape and appearance models Doretto, G., and Soatto, S. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006. abstract bibTeX pdf doi

   We propose a model of the joint variation of shape and appearance of portions of an image sequence. The model is conditionally linear, and can be thought of as an extension of active appearance models to exploit the temporal correlation of adjacent image frames. Inference of the model parameters can be performed efficiently using established numerical optimization techniques borrowed from finite-element analysis and system identification techniques.

   @article{dorettoS06IEEEtpami,
     abbr = {TPAMI},
     author = {Doretto, G. and Soatto, S.},
     title = {Dynamic shape and appearance models},
     journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
     year = {2006},
     volume = {28},
     pages = {2006--2019},
     number = {12},
     address = {Los Alamitos, CA, USA},
     bib2html_pubtype = {Journals},
     bib2html_rescat = {Dynamic Textures, Visual Motion Analysis, Shape and Appearance Modeling,
     	Image Based Rendering, Registration from Dynamic Textures},
     doi = {http://doi.ieeecomputersociety.org/10.1109/TPAMI.2006.243},
     file = {dorettoS06IEEEtpami.pdf:doretto\\journal\\dorettoS06IEEEtpami.pdf:PDF;dorettoS06IEEEtpami.pdf:doretto\\journal\\dorettoS06IEEEtpami.pdf:PDF},
     issn = {0162-8828},
     owner = {doretto},
     publisher = {IEEE Computer Society},
     timestamp = {2006.11.24}
   }
   

2. ECCV

   Spatially homogeneous dynamic textures Doretto, G., Jones, E., and Soatto, S. In Proceedings of European Conference on Computer Vision, 2004. Oral abstract bibTeX pdf

   We address the problem of modeling the spatial and temporal second-order statistics of video sequences that exhibit both spatial and temporal regularity, intended in a statistical sense. We model such sequences as dynamic multiscale autoregressive models, and introduce an efficient algorithm to learn the model parameters. We then show how the model can be used to synthesize novel sequences that extend the original ones in both space and time, and illustrate the power, and limitations, of the models we propose with a number of real image sequences.

   @inproceedings{dorettoJS04eccv,
     abbr = {ECCV},
     author = {Doretto, G. and Jones, E. and Soatto, S.},
     title = {Spatially homogeneous dynamic textures},
     booktitle = {Proceedings of European Conference on Computer Vision},
     year = {2004},
     volume = {2},
     pages = {591--602},
     address = {Prague, Czech Republic},
     month = may,
     bib2html_pubtype = {Conferences},
     bib2html_rescat = {Dynamic Textures, Visual Motion Analysis},
     file = {dorettoJS04eccv.pdf:doretto/conference/dorettoJS04eccv.pdf:PDF},
     owner = {doretto},
     timestamp = {2013.10.18},
     wwwnote = {Oral}
   }
   

3. IJCV

   Dynamic textures Doretto, G., Chiuso, A., Wu, Y. N., and Soatto, S. International Journal of Computer Vision, 2003. abstract bibTeX pdf

   Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind etc. We present a characterization of dynamic textures that poses the problems of modeling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing. We borrow tools from system identification to capture the “essence” of dynamic textures; we do so by learning (i.e. identifying) models that are optimal in the sense of maximum likelihood or minimum prediction error variance. For the special case of second-order stationary processes, we identify the model sub-optimally in closed-form. Once learned, a model has predictive power and can be used for extrapolating synthetic sequences to infinite length with negligible computational cost. We present experimental evidence that, within our framework, even low-dimensional models can capture very complex visual phenomena.

   @article{dorettoCWS03ijcv,
     abbr = {IJCV},
     author = {Doretto, G. and Chiuso, A. and Wu, Y. N. and Soatto, S.},
     title = {Dynamic textures},
     journal = {International Journal of Computer Vision},
     year = {2003},
     volume = {51},
     pages = {91--109},
     number = {2},
     bib2html_pubtype = {Journals},
     bib2html_rescat = {Dynamic Textures, Visual Motion Analysis, Visual Motion Recognition},
     file = {dorettoCWS03ijcv.pdf:doretto\\journal\\dorettoCWS03ijcv.pdf:PDF;dorettoCWS03ijcv.pdf:doretto\\journal\\dorettoCWS03ijcv.pdf:PDF}
   }
   

4. ICCV

   Dynamic texture segmentation Doretto, G., Cremers, D., Favaro, P., and Soatto, S. In Proceedings of IEEE International Conference on Computer Vision, 2003. abstract bibTeX pdf

   We address the problem of segmenting a sequence of images of natural scenes into disjoint regions that are characterized by constant spatio-temporal statistics. We model the spatio-temporal dynamics in each region by Gauss-Markov models, and infer the model parameters as well as the boundary of the regions in a variational optimization framework. Numerical results demonstrate that, in contrast to purely texture-based segmentation schemes, our method is effective in segmenting regions that differ in their dynamics even when spatial statistics are identical.

   @inproceedings{dorettoCFS03iccv,
     abbr = {ICCV},
     author = {Doretto, G. and Cremers, D. and Favaro, P. and Soatto, S.},
     title = {Dynamic texture segmentation},
     booktitle = {Proceedings of IEEE International Conference on Computer Vision},
     year = {2003},
     volume = {2},
     pages = {1236--1242},
     address = {Nice, France},
     month = oct,
     bib2html_pubtype = {Conferences},
     bib2html_rescat = {Dynamic Textures, Visual Motion Segmentation},
     file = {dorettoCFS03iccv.pdf:doretto\\conference\\dorettoCFS03iccv.pdf:PDF;dorettoCFS03iccv.pdf:doretto\\conference\\dorettoCFS03iccv.pdf:PDF},
     owner = {doretto}
   }
   

5. CVPR

   Dynamic texture recognition Saisan, P., Doretto, G., Wu, Y. N., and Soatto, S. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2001. abstract bibTeX pdf

   Dynamic textures are sequences of images that exhibit some form of temporal stationarity, such as waves, steam, and foliage. We pose the problem of recognizing and classifying dynamic textures in the space of dynamical systems where each dynamic texture is uniquely represented. Since the space is non-linear, a distance between models must be defined. We examine three different distances in the space of autoregressive models and assess their power.

   @inproceedings{saisanDWS01cvpr,
     abbr = {CVPR},
     author = {Saisan, P. and Doretto, G. and Wu, Y. N. and Soatto, S.},
     title = {Dynamic texture recognition},
     booktitle = {Proceedings of the IEEE Computer Society Conference on Computer Vision
     	and Pattern Recognition},
     year = {2001},
     volume = {2},
     pages = {58--63},
     address = {Kauai, Hawaii, USA},
     month = dec,
     bib2html_pubtype = {Conferences},
     bib2html_rescat = {Dynamic Textures, Visual Motion Recognition},
     file = {saisanDWS01cvpr.pdf:doretto\\conference\\saisanDWS01cvpr.pdf:PDF;saisanDWS01cvpr.pdf:doretto\\conference\\saisanDWS01cvpr.pdf:PDF},
     owner = {doretto}
   }