首页> 外文会议>World Automation Congress >Adaptive sampling for Bayesian visual tracking
【24h】

Adaptive sampling for Bayesian visual tracking

机译:贝叶斯视觉跟踪的自适应采样

获取原文

摘要

We propose a statistical motion model for sequential Bayesian tracking and show an adaptive particle filter algorithm for the motion model. It predicts the current state with the help of optical flows, i.e., it explores the state space with information based on the current and previous images of an image sequence. In addition, we introduce a robust method for state estimation and an automatic method for adjusting the variance of the motion model, which parameter is manually determined in most particle filters. In experiments with a real image sequence, we compare the proposed motion model with a random walk model, which is a widely used model for tracking, and show the proposed model outperform the random walk model.
机译:我们提出了一种统计运动模型,用于顺序贝叶斯追踪,并显示运动模型的自适应粒子滤波器算法。它在光学流的帮助下预测当前状态,即,它具有基于图像序列的电流和先前图像的信息探索状态空间。此外,我们介绍了一种用于调整运动模型方差的状态估计和自动方法的鲁棒方法,该方法在大多数粒子过滤器中手动确定该参数。在具有真实图像序列的实验中,我们将所提出的运动模型与随机步道模型进行比较,这是一种广泛使用的跟踪模型,并显示所提出的模型优于随机步道模型。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号