一种受人脑三阶段记忆机制启发的鲁棒运动目标跟踪方法

摘要

目前大多数运动目标跟踪算法在目标姿态发生突变或目标被严重遮挡后会产生目标丢失现象,为解决此类问题,受人脑三阶段记忆信息处理机制的启发,本文提出一种三层旋转圆记忆模型(Spinning Tri-Layer-CircleMemoryModeling,STLC-MM)用于在目标跟踪过程中对目标模板进行更新.模型定义了三个旋转圆记忆空间用于存储和处理跟踪过程中用过的目标模板.三个圆记忆空间旋转时,记忆空间中的模板也随之以相同的速度旋转,同时模型通过模拟一些人类的认知行为,如,记忆、提取、遗忘等对模板进行更新.最后,为了验证所提方法有效性,本文将STLC-MM嵌入到粒子滤波目标跟踪框架进行目标跟踪实验.实验结果表明所提方法在目标姿态突变以及严重遮挡等方面具有较强的鲁棒性.%Most of the current object tracking algorithms will fail when sudden appearance changes and serious occlusions occur.Inspired by the mechanism of human brain three-stage memory model,this paper develops a spinning tri-layercircle memory model(STLC-MM) and applies it for template updating during object tracking.Three memory spaces are defined to store and process the object templates used during tracking.With three circle memory spaces spinning,templates in the three memory spaces are updated by imitating the cognitive process of memorization,recall,and forgetting.Finally,in order to verify the effect of the proposed model,STLC-MM is incorporated into a particle filter (PF) framework.Experimental results show that the proposed method is more robust to sudden appearance changes and serious occlusions.