抗遮挡自适应的粒子滤波算法

An Anti-occlusion Adaptive Particle Filtering Algorithm

针对局部遮挡对粒子滤波跟踪算法的影响,提出了抗遮挡自适应的粒子滤波算法。该算法采用矩形作为跟踪窗,在重要性重采样之后,引入K均值聚类(KM聚类)算法,将空间特征与权重分布近似的粒子进行聚类,得到粒子子群,并通过粒子子群估计目标的最终状态。当目标外形变化超过5%时,说明存在遮挡或同色干扰现象,则跟踪窗保持上一帧尺寸不变,否则跟踪窗随着运动目标尺度变化而自适应变化。实验结果表明该算法对局部遮挡和运动目标尺度变化具有较强的鲁棒性。

Considering the influence of local occlusion on particle filter tracking algorithm, an anti occlusion adaptive particle filtering algorithm is proposed. It adopts a rectangle as the tracking window, and uses the K mean clustering algorithm to complete particle clustering in resampling, and then obtains the particle subgroup. It estimates the final state according to particles subgroups, and modifies the tracking window. When the area changes more than 5%, the tracking window maintains the same as the one in last frame. Otherwise, the tracking window will change according to the size of moving object, which is a self-adaptation process. At the same time it solves the degeneration problem of particle filter. This algorithm strengthens the robustness of tracking algorithm in case of local occlusion and moving object scale changing. The method performs better than the traditional particle filter tracking algorithm.