无线传感器网络中基于移动智能体的目标追踪

Target tracking based on moving agent in wireless sensor network

就无线传感器网络中的目标追踪问题而言,减少传感器之间的冲突、提高追踪精度是两个重要问题．为此,采用移动智能体方法协同声音传感器追踪移动目标．当目标出现时,负责追踪的智能体产生,并随目标移动而移动．为减小在选举移动智能体的过程中出现的冲突,采用基于概率的选举策略,给出概率函数的设置方法．在目标关联过程中,时间窗口的大小对算法的追踪精度而言至关重要,经过分析,给出了设置时间窗口大小的基本原则．仿真结果表明设计恰当的随机函数和时间窗口可以有效地减小冲突、提高追踪的精度．

For target tracking in wireless sensor network, the reducing of the conflict between sensors and the improvement of the tracking accuracy are main concerns. A moving-agent method is developed to coordinate the acoustic sensors to track the moving target in this paper. When finding the moving target in the acoustic sensor network, a moving agent is generated to triangulate the target＇s position. While the target is moving, the agent is also moving to follow the target. An election strategy based on the probability is then used to select the moving agent and thus reduce the conflict between the sensors. Furthermore, the random function is designed for given random function distribution. Besides, it also indicates that the time window connected with the data association process is a very important parameter and the domain of the time window is analyzed. Finally, the simulation shows that choosing a right random function and a right value of the time window can reduce the conflict and improve the tracking accuracy.