Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Anti-occlusion object tracking algorithm based on fused texture feature Mean-shift

CAO Jie,FU De-qiang(College of Electrical and Information Engineering,Lanzhou Univ.of Tech.,Lanzhou 730050,China)  
In traditional Mean-shift algorithm only the color features of object was used.When the scene contained a object with color similar to the tracked object color,an error tracking would happen.When the object was occluded,the object could not be tracked effectively.An anti-occlusion object tracking method with fused texture features of the object was proposed.Meantime,the template was updated,and the Kalman filter was used for object estimation and prediction when the object was occluded.An object-occlusion factor was also proposed as object occlusion criterion.When the object was occluded seriously,the object location would be predicted with extrapolation of object state.Experimental result showed that this method exhibited a stronger anti-interference and could be used to track correctly the object in complete occlusion.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved