基于特征融合的粒子滤波在红外小目标跟踪中的应用

Application of Particle Filter Based on Feature Fusion in Small IR Target Tracking

针对红外图像序列中的小目标跟踪问题,在分析红外小目标特点的基础上,提出了一种基于特征融合的粒子滤波目标跟踪算法。该方法利用粒子滤波支持目标特征融合的优点,提出将灰度特征和分形特征相融合,并将融合后的信息用于粒子权值的计算,从而大大提高了跟踪算法的稳健性。实验结果表明,和传统的粒子滤波算法相比,该算法能够更加准确、有效地跟踪红外序列中的小目标。

For small target tracking in infrared （IR） image sequences, a particle filter algorithm based on feature fusion is presented with the analysis of the characters of small IR targets. Taking the advantage of particle filter of supporting target feature fusion method, this algorithm combines the gray feature with fractal feature, and then uses the fusion results to calculate the particle weights, which greatly improves the robustness of the tracking algorithm. The experimental results show that the presented method is more accurate and effective for small IR target tracking in infrared image sequences than the traditional particle filter method.