【摘要】 红外图像具有对比度低、信噪比低等特点,传统算法难以获得高精度的目标跟踪结果,根据多种特征之间的信息互补性,为了提高红外目标跟踪的精度,提出一种特征融合和加权的红外目标跟踪算法。首先对传统算法的不足进行分析,分别提取红外目标的纹理和颜色特征,然后根据纹理和颜色特征对跟踪结果重要程度得到权值,最后根据权值实现红外目标跟踪,仿真测试实验结果表明,本文算法具有较强的鲁棒性,加快了红外目标跟踪的速度,并且跟踪效果要优于当前流行的红外目标跟踪算法。更多还原

【Abstract】 Infrared image has the characteristics of low contrast and low signal-noise ratio,using the traditional algorithms is difficult to obtain high accuracy of target tracking results,according to the complementary information of the various characteristics,in order to improve the accuracy of infrared target tracking,a feature fusion and weighted infrared target tracking algorithm is proposed in this paper.The existing problems of the traditional algorithms are analyzed,and the texture features and color features of the infrared target are extracted respectively,and then the texture features and color features are estimated to be weighted by the importance of tracking results,finally,the results of infrared target tracking are realized according to the weights,the simulation results show the algorithm in this paper has strong robustness and speed up the infrared target tracking speed,and the tracking effect is better than the current popular infrared target tracking algorithm.更多还原