Title :
Dynamic texture recognition based on fluid motion vector calculation
Author_Institution :
Inst. of Software Eng., East China Normal Univ., Shanghai, China
Abstract :
Dynamic texture is a part of the natural scene. Dynamic texture segmentation issue is research hotspot in the field of computer vision and even robot research area. This paper studies the method of dynamic texture recognition. We study the strategy based on fluid vector calculation. There three steps in the strategy. Firstly, we calculate the motion vector of fluid flow. Then remove noise using multi-resolution sampling method. At last we obtain the dynamic texture recognition results. Much more experimental results show that it is very efficient and can effectively achieve the dynamic texture recognition.
Keywords :
computer vision; image resolution; image sampling; image segmentation; image texture; natural scenes; vectors; computer vision; dynamic texture recognition; dynamic texture segmentation; fluid flow; fluid motion vector calculation; multiresolution sampling; natural scene; robot research area; Computer vision; Dynamics; Fluids; Heuristic algorithms; Histograms; Level set; Noise; dynamic texture; fluid flow; motion vector; recognition;
Conference_Titel :
Multimedia Technology (ICMT), 2011 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-1-61284-771-9
DOI :
10.1109/ICMT.2011.6002180