A moving target tracking algorithm based on adaptive multiple cues fusion

作者：Yin Hong Peng^*; Chai Yi; Kuan Jin Jun; Yang Xiao Yan

来源：Journal of Optoelectronics - Laser, 2010, 21(6): 917-923.

• Adaptive models
• Complex background
• Discriminability
• Fusion targets
• Kernel-based tracking
• Moving target tracking
• Target and background
• Tracking algorithm
• Variance ratio
• Vision theory

A novel tracking algorithm based on adaptive multiple-cure fusion is proposed for moving target tracking under complex background. According to the discriminability between target and background, that is measured by two-class variance ratio, the multiple cues are combined by linear weighting to represent target and realize kernel-based tracking. In addition, an adaptive model updating mechanism is addressed to alleviate the mode drifts by the likelihood of the cues between two successive frames. According to biology vision theory, color, edge and texture cue are employed to implement the scheme. Experimental results show the effectiveness of the proposed method.

• 出版日期2010