摘要
动态纹理的处理、描述与识别是纹理分析的热门领域。动态纹理是对普通纹理在时间域方面的扩展,包括动态特征和静态特征。基于LBP算法的扩展提出的VLBP算法较好的描述了动态纹理特征,但是计算量过大,模板过多。本文提出了一种由VLBP算法改进的基于局部二进制运动模式的特征提取方法用以动态纹理的描述和识别,它包括提取动态特征和提取静态特征两部分。将LBP算子做为块匹配准则提取局部二进制运动模式柱状图做为动态特征的描述,提取LBP柱状图做为静态特征的描述,并将二者连接得出描述动态纹理特征的联合的局部二进制运动模式柱状图。通过对DynTex集实验的结果表明,本文提出的方法在性能和识别率方面均要优于VLBP。
The processing, description and recognition of Dynamic Texture（DT） are new exciting areas of texture analysis.DT is an extension of still texture to temporal domain, which contains motion features and appearance features.The Volume Local Binary Pattern（VLBP） method shows a high performance for DT characterization, however, it contains too many templates, of which the calculation work is huge.This paper proposes a new advanced method of which is based on the Local Binary Motion Patterns（LBMP） for extracting features of DT description and recognition by characterizing the motion and appearance features.The proposed revealing method uses the Concatenated-LBMP histogram as the identifier of DT, which is concatenated by the LBMP histogram derived from motion features based on the Local Binary Pattern（LBP） block-matching criterion and the LBP histogram from appearance features.Experimental results based on the DynTex database show that the proposed method achieves a higher recognition performance than VLBP.
出处
《微计算机信息》
2010年第9期174-176,共3页
Control & Automation
关键词
动态纹理
局部二进制模式
块匹配
动态特征
静态特征
Dynamic Texture
local binary patterns
block-matching
motion features
appearance features
