Automatic Dynamic Texture Segmentation Using Local Descriptors and Optical Flow
作者： Jie Chen , Guoying Zhao , M. Salo , E. Rahtu , M. Pietikainen
关键词: Scale-space segmentation 、 Computer vision 、 Region growing 、 Pattern recognition 、 Optical flow 、 Image texture 、 Motion field 、 Segmentation 、 Texture Descriptor 、 Image segmentation 、 Histogram 、 Computer science 、 Artificial intelligence 、 Segmentation-based object categorization
摘要: A dynamic texture (DT) is an extension of the to temporal domain. How segment a DT challenging problem. In this paper, we address problem segmenting into disjoint regions. might be different from its spatial mode (i.e., appearance) and/or motion field). To end, develop framework based on appearance and modes. For mode, use new local descriptor describe DT; for optical flow represent variations DT. addition, flow, histogram oriented (HOOF) organize them. compute distance between two HOOFs, simple effective efficient measure Weber's law. Furthermore, also threshold selection by proposing method determining thresholds segmentation offline supervised statistical learning. The experimental results show that our provides very good compared state-of-the-art methods in regions differ their dynamics.
harvard.edu
acm.org
sci-hub.se 参考文章(35)
Tomer Amiaz, Sándor Fazekas, Dmitry Chetverikov, Nahum Kiryati, Detecting Regions of Dynamic Texture Lecture Notes in Computer Science. pp. 848- 859 ,(2007) , 10.1007/978-3-540-72823-8_73
Lee Cooper, Jun Liu, Kun Huang, Spatial Segmentation of Temporal Texture Using Mixture Linear Models Dynamical Vision. pp. 142- 150 ,(2006) , 10.1007/978-3-540-70932-9_11
Atiyeh Ghoreyshi, René Vidal, Segmenting Dynamic Textures with Ising Descriptors, ARX Models and Level Sets Dynamical Vision. pp. 127- 141 ,(2006) , 10.1007/978-3-540-70932-9_10
Dmitry Chetverikov, Renaud Péteri, A Brief Survey of Dynamic Texture Description and Recognition computer recognition systems. pp. 17- 26 ,(2005) , 10.1007/3-540-32390-2_2
Thomas Brox, Andrés Bruhn, Nils Papenberg, Joachim Weickert, None, High Accuracy Optical Flow Estimation Based on a Theory for Warping european conference on computer vision. pp. 25- 36 ,(2004) , 10.1007/978-3-540-24673-2_3
Jianbo Shi, J. Malik, Motion segmentation and tracking using normalized cuts international conference on computer vision. pp. 1154- 1160 ,(1998) , 10.1109/ICCV.1998.710861
CE Shennon, Warren Weaver, A mathematical theory of communication Bell System Technical Journal. ,vol. 27, pp. 379- 423 ,(1948) , 10.1002/J.1538-7305.1948.TB01338.X
David W. Murray, Bernard F. Buxton, Scene Segmentation from Visual Motion Using Global Optimization IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-9, pp. 220- 228 ,(1987) , 10.1109/TPAMI.1987.4767896
Jie Chen, Guoying Zhao, Matti Pietikainen, An improved local descriptor and threshold learning for unsupervised dynamic texture segmentation international conference on computer vision. pp. 460- 467 ,(2009) , 10.1109/ICCVW.2009.5457664
Sándor Fazekas, Tomer Amiaz, Dmitry Chetverikov, Nahum Kiryati, Dynamic Texture Detection Based on Motion Analysis International Journal of Computer Vision. ,vol. 82, pp. 48- 63 ,(2009) , 10.1007/S11263-008-0184-Y