Book ChapterDOI
Dynamic Texture Segmentation Using Texture Descriptors and Optical Flow Techniques
Pratik Soygaonkar,Shilpa Paygude,Vibha Vyas +2 more
- pp 281-288
Reads0
Chats0
TLDR
The segmentation problem of image sequences consisting of cluttered dynamic textures is addressed and two local texture descriptor based techniques and Lucas-Kanade optical flow technique are combined together to achieve accurate segmentation.Abstract:
The texture which is in motion is known as Dynamic texture. As the texture can change in shape and direction over time, Segmentation of Dynamic Texture is a challenging task. Furthermore, features of Dynamic texture like spatial (i.e., appearance) and temporal (i.e., motion) may differ from each other. However, studies are mostly limited to characterization of single dynamic textures in the current literature. In this paper, the segmentation problem of image sequences consisting of cluttered dynamic textures is addressed. For the segmentation of dynamic texture, two local texture descriptor based techniques and Lucas-Kanade optical flow technique are combined together to achieve accurate segmentation. Two texture descriptor based techniques are Local binary pattern and Weber local descriptor. These descriptors are used in spatial as well as in temporal domain and it helps to segment a frame of video into distinct regions based on the histogram of the region. Lucas-Kanade based optical flow technique is used in temporal domain, which determines direction of motion of dynamic texture in a sequence. These three features are computed for every section of individual frame and equivalent histograms are obtained. These histograms are concatenated and compared with suitable threshold to obtain segmentation of dynamic texture.read more
Citations
More filters
Book ChapterDOI
Dynamic Textures Segmentation and Tracking Using Optical Flow and Active Contours
Ikram Bida,Saliha Aouat +1 more
TL;DR: A large number of scenes composing the authors' visual world are perceived as dynamic textures, displaying motion patterns with a certain spatial and temporal regularity such as swaying trees, smoke, fire, human movements, flowing water and others.
Journal ArticleDOI
Evaluating dynamic texture descriptors to recognize human iris in video image sequence
TL;DR: A new methodology to evaluate the “dynamic texture” from iris image sequences (motion analysis) and measure the discriminant power of these features for biometric system applications is proposed and can extract dynamic textures faster than the LBP-TOP.
Posted Content
A Fully Bayesian Infinite Generative Model for Dynamic Texture Segmentation.
TL;DR: This work proposes a novel non-parametric fully Bayesian approach for DT segmentation, formulated on the basis of a joint DPM and GDTM construction, and derives the Variational Bayesian Expectation-Maximization (VBEM) inference for the proposed model.
References
More filters
Proceedings Article
An iterative image registration technique with an application to stereo vision
Bruce D. Lucas,Takeo Kanade +1 more
TL;DR: In this paper, the spatial intensity gradient of the images is used to find a good match using a type of Newton-Raphson iteration, which can be generalized to handle rotation, scaling and shearing.
Journal ArticleDOI
Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions
Guoying Zhao,Matti Pietikäinen +1 more
TL;DR: A novel approach for recognizing DTs is proposed and its simplifications and extensions to facial image analysis are also considered and both the VLBP and LBP-TOP clearly outperformed the earlier approaches.
Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm
TL;DR: It is essential to define the notion of similarity in a 2D neighborhood sense and the image velocity d is defined as being the vector that minimizes the residual function defined as follows.
Journal ArticleDOI
WLD: A Robust Local Image Descriptor
TL;DR: Experimental results on the Brodatz and KTH-TIPS2-a texture databases show that WLD impressively outperforms the other widely used descriptors (e.g., Gabor and SIFT), and experimental results on human face detection also show a promising performance comparable to the best known results onThe MIT+CMU frontal face test set, the AR face data set, and the CMU profile test set.
Journal ArticleDOI
Dynamic Textures
TL;DR: A characterization of dynamic textures that poses the problems of modeling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing and experimental evidence that, within the framework, even low-dimensional models can capture very complex visual phenomena is presented.