An Improved Meanshift Tracking Algorithm Based on Multi-feature Fusion and Back Projection
SHEN Mengzhou
LI Ning
XU Bin
CAO Caimin
GU Xiaorong
Abstract：The traditional MeanShift tracking algorithm is easy to fail due to its single colorfeature,also since its tracking win-dow size is fixed,it is unable to track size changed object successfully. Thus,a modified scale-adaptive MeanShift tracking algo-rithm based on multi-feature fusion and back projection is proposed. First,texture feature is fused with the original color feature to describe the object. Then,in order to reduce the interference of the background,background-weighted algorithm is introduced to our method. Finally,adaptive tracking window is realized by back projection and similarity comparison. The experimental results show that the improved algorithm achieves better tracking results than the traditional algorithm.
Keywords：object trackingadaptive tracking windowtexture featureback projection
Publication Date：2017-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 1533-1538 )