摄像机节点动态选择问题是摄像机网络应用中的一个难点.提出了一种基于增强学习的节点动态选择方法.采用视觉信息评分作为单步回报设计了节点选择策略的Q-学习算法,为了加速算法收敛速度,利用摄像机空间拓扑关系初始化Q值表,并基于Gibbs分布进行非贪心尝试.从目标可见性、朝向、清晰度和切换次数设计视觉评价函数反映视频信息丰富程度和视觉舒适度.实验结果表明,该节点动态选择方法能够有效地反映视频中的目标状态信息,选择结果切换平滑,满足实际应用需要.

This paper addresses the problem of node dynamic selection in camera networks. A selection method based on reinforcement learning is proposed in which the node is selected to maximize the expected reward while minimizing the switching with Q-learning. To accelerate the convergence of Q-learning, the geometry of camera networks is considered for initial Q-values and a Gibbs distribution is used for exploitation. In order to evaluate visual information of the video, a function of the visibility, orientation, definition and switching is designed to assess the immediate reward in Q-learning. Experiments show that the proposed visual evaluation criteria can capture the motion state of the object effectively and the selection method is more accurate on reducing cameras switching compared with the state-of-the art methods.

国家自然科学基金(61272219, 61100110, 61321491, 41305138);教育部新世纪优秀人才资助计划(NCET-04-0460);江苏省科技计划(BE2010072, BE2011058, BY2012190, BY2013072-04);计算机软件新技术国家重点实验室创新基金(ZZKT2013A12)