Dynamic texture

Dynamic texture ( sometimes referred to as temporal texture) is the texture with motion which can be found in videos of sea-waves, fire, smoke, wavy trees, etc.[1][2] Dynamic texture has a spatially repetitive pattern with time-varying visual pattern.[3] Modeling and analyzing dynamic texture is a topic of images processing and pattern recognition in computer vision.

Extracting features that describe the dynamic texture can be utilized for tasks of images sequences classification, segmentation, recognition and retrieval. Comparing with texture found within static images, analyzing dynamic texture is a challenging problem.[2] It is important that the extracted features from dynamic texture combine motion and appearance description, and also be invariance to some transformation such as rotation, translation and illumination.[2]

Analysis methods of dynamic texture

The methods of dynamic texture recognition can categorized as follows:[3]

  1. Methods based on optical flow: by applying optical flow to the dynamic texture, velocity with direction and magnitude can be detected and used to recognize the dynamic texture. Due to simplicity of its computation, it is currently the most popular method.
  2. Methods computing geometric properties: this methods track the surfaces of motion trajectories in spatiotemporal domain.[4]
  3. Methods based on local spatiotemporal filtering : this methods analyze the local spatiotemporal patterns and its orientation and energy and employ them as feature used for classification.[5]
  4. Methods based on global spatiotemporal transform: this method characterize the motion at different scale using wavelets that can decompose the motion into local and global.[6]
  5. Model-based methods : These methods aims at generating a model to describe the motion by a set of parameters.

Applications

- Segmenting the sequence images of natural scenes.[7] This helps on differentiate between streets and grass alongside these streets which could be used in the application of navigations.

- Motion detection : Dynamic texture features extracted from footage videos can be exploited to detect abnormal crowd activities.[8]

- Video classification: video of natural scenes or other scenes that exhibit dynamic textures.

- Video retrieval : Dynamic textures can be employed as a feature retrieve videos that contain, for example, sea-waves, smoke, clouds, wavy trees.

References
  1. "Temporal texture modeling - IEEE Conference Publication". doi:10.1109/ICIP.1996.560871. Cite journal requires |journal= (help)
  2. Zhao, G.; Pietikäinen, M. (2007). "Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions - IEEE Journals & Magazine". IEEE Transactions on Pattern Analysis and Machine Intelligence. 29 (6): 915–28. CiteSeerX 10.1.1.714.2104. doi:10.1109/TPAMI.2007.1110. PMID 17431293.
  3. Péteri, Renaud; Chetverikov, Dmitry (2005), "A Brief Survey of Dynamic Texture Description and Recognition", Computer Recognition Systems, Advances in Soft Computing, Springer, Berlin, Heidelberg, pp. 17–26, CiteSeerX 10.1.1.64.4707, doi:10.1007/3-540-32390-2_2, ISBN 9783540250548
  4. "Feature extraction of temporal texture based on spatiotemporal motion trajectory - IEEE Conference Publication". doi:10.1109/ICPR.1998.711871. Cite journal requires |journal= (help)
  5. Bergen, James R.; Wildes, Richard P. (2000-06-26). Qualitative Spatiotemporal Analysis Using an Oriented Energy Representation. Computer Vision — ECCV 2000. Lecture Notes in Computer Science. Springer, Berlin, Heidelberg. pp. 768–784. CiteSeerX 10.1.1.189.3015. doi:10.1007/3-540-45053-X_49. ISBN 9783540676867.
  6. "Video texture indexing using spatio-temporal wavelets - IEEE Conference Publication". doi:10.1109/ICIP.2002.1039981. Cite journal requires |journal= (help)
  7. Doretto; Cremers; Favaro; Soatto (October 2003). Dynamic texture segmentation. Proceedings Ninth IEEE International Conference on Computer Vision. pp. 1236–1242 vol.2. CiteSeerX 10.1.1.324.456. doi:10.1109/ICCV.2003.1238632. ISBN 978-0-7695-1950-0.
  8. Moore, Simon C.; Marshall, David; Rosin, Paul L.; Lloyd, Kaelon (2017-05-01). "Detecting violent and abnormal crowd activity using temporal analysis of grey level co-occurrence matrix (GLCM)-based texture measures". Machine Vision and Applications. 28 (3–4): 361–371. arXiv:1605.05106. doi:10.1007/s00138-017-0830-x. ISSN 1432-1769.
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.