论文部分内容阅读
针对多区域采样目标跟踪方法容易出现的区域多样性丧失、跟踪精度下降和跟踪不稳定等问题,本文引入区域优化权值及改进子区域重采样方法,提出基于优化权值的多区域采样目标跟踪算法.该方法利用区域优化权值优化各个子区域的区域置信度适当增加低置信度区域在重采样阶段所分配到的粒子数量,在保证粒子根据区域置信度大小有效分配的前提下,抑制了区域多样性丧失现象发生.本文算法在子区域内引入粒子权重优化权值并设定重采样阈值,缓解粒子贫化充分利用有效粒子信息.实验结果表明,本文方法能有效提高目标跟踪精度,改善目标跟踪稳定性.
Aiming at the problems such as the loss of regional diversity, the decrease of tracking accuracy and the instability of tracking which are prone to occur in the multi-region sampling target tracking method, this paper introduces the regional optimization weights and the improved sub-region resampling method, and proposes a multi-region sampling target tracking The method optimizes the regional confidence of each subregion by using the regional optimization weights, and increases the number of particles assigned to the low confidence region in the resampling stage appropriately. While ensuring the effective allocation of particles according to the confidence level of the region, The loss of regional diversity occurs.The algorithm proposed in this paper introduces particle weight optimization weights in the sub-region and sets the resampling threshold to alleviate the particle depletion and make full use of the effective particle information.The experimental results show that this method can effectively improve the target tracking accuracy and improve Target tracking stability.