Automatic Pan–Tilt Camera Control for Learning Dirichlet Process Gaussian Process (DPGP) Mixture Models of Multiple Moving Targets
Automatic Pan–Tilt Camera Control for Learning Dirichlet Process Gaussian Process (DPGP) Mixture Models of Multiple Moving Targets
复制标题
用于学习多移动目标的狄利克雷过程高斯过程 (DPGP) 混合模型的自动云台摄像机控制
DOI：
--
复制
发表时间：
2019
影响因子：
6.8
通讯作者：
S. Ferrari
中科院分区：
文献类型：
--
作者：
Hongchuan Wei;Pingping Zhu;Miao Liu;J. How;S. Ferrari
基于Kullback -Leibler（KL）差异的信息价值功能已被证明是通过贪婪策略来计划传感器测量的最有效的问题。在这里证明，本文是$ ext {np} $。差异与传感器视野的凸方法相结合，这些信息值函数可用于通过词汇方法获得实时传感器控制，并在行人数据上获得绩效保证。与现有算法相比，控制系统可显着改善目标建模和预测性能。
Information value functions based on the Kullback–Leibler (KL) divergence have been shown the most effective for planning sensor measurements by means of greedy strategies. The problem of optimizing information value over a finite time horizon to date has been considered computationally intractable and, as proven here, is $ ext{NP}$-hard. This paper presents new information value functions that are additive and can be optimized efficiently over time by deriving a lower bound of the KL divergence. Combined with a convex approximation of the sensor field of view, these information value functions can be used to obtain real-time sensor control by a lexicographic approach, and to derive performance guarantees. Numerical and experimental results on pedestrian data show that the lexicographic control system significantly improves target modeling and prediction performance when compared to existing algorithms.