An Adaptive Target Tracking Algorithm Based on Multi-Feature Fusion

Although widely used in practice for real time ability, the mean shift algorithm was weak at target model description and was robust for infrared image sequences form motion platform. In order to enhance the adaptability and target description ability of the mean shift algorithm, meanwhile to make up the shortcomings of the nuclear density estimation based on gradation feature, an adaptive Kalman-mean shift algorithm based on multi-feature fusion was proposed. A target description mode based on gradation-edge feature fusion was applied, while a scale updating item of tracking window was used in the mean shift algorithm based on the relation between mutual information and the object scale. Experimental results demonstrate that the adaptability of mean shift algorithm is enhanced by the improved algorithm, which is effectively applied in the tracking problem for the object of scale variance in long time tracking process.