基于粒子群算法和卡尔曼滤波的运动目标跟踪算法

Tracking Algorithm of Moving Object Based on Particle Swarm Optimization and Kalman Filter

针对目前一些常用的运动目标跟踪算法存在跟踪精度不高、实时性低、对遮挡问题处理不佳等问题,提出一种粒子群算法与卡尔曼滤波相结合的新的运动目标跟踪方法。利用卡尔曼滤波预测目标中心在下一帧图像中的位置,从而极大减少了搜索范围,并以该位置为中心建立目标搜索区域。然后以目标的灰度统计特征对目标模板和候选区域进行匹配,确保跟踪准确性。为了有效减少搜索匹配次数、提高实时性,利用粒子群算法在搜索区域找到和目标模板最相似的区域,从而找到最优中心位置,并以该位置作为卡尔曼滤波的观测值,进行下一帧跟踪。仿真实验结果表明新算法显著提高了跟踪的实时性、精确性,并对部分遮挡能较好地处理。

Aiming at the inaccuracy,low real-time and poor treatment of commonly used tracking algorithm of moving object,a new tracking algorithm of moving object based on particle swarm optimization（PSO） and Kalman filter is proposed.The possible position of moving target center in the next frame image is predicted by Kalman filter,which reduced the search scope greatly and set search region of target which is generated around the center position.Then matching the target template and the candidate regions with the gray statistical characteristics to ensure the tracking accuracy.In order to reduce the search for matching and improve real-time performance,PSO is utilized to search the best area which is most similar to the target template in the search region,as a result,the optimal center is found and the best position is used as an observed value of Kalman filter for next prediction.The experimental results show that the new method is effective and robust and can handle partial occlusion better.