Abstract: In the application of Intelligent Transport System，sensors are often used to locate traffic targets at real-time． However，the target is uncertainty and the raw data usually have a lot of interferences caused by the abnormal data and some other noises． This leads to a great influence to the accuracy of data fusion． Aiming at this problem，wavelet transforming multi-scale decomposition and reconstruction combined with thresholding denoising are used to reduce the orginal noise， which can well maintain the transient characteristics of the original signal． In addition，the logical method is used to track target’s tracking of the processed data． Finally，the simulation test is carried out and the results show that the proposed method can eliminate the noise well; meanwhile，it can reduce the number of false tracks． Even if several targets have cross-track phenomena，the proposed method can achieve target’s identification and track．

Key words: wavelet, logical method, multi-target, data processing, track tracking

摘要： 智能交通系统( ITS) ，常常要采用传感器对交通目标进行实时定位监控，但被跟踪目标的不确定性以及原始 数据通常存在大量噪声的干扰，这对数据融合的精度产生很大的影响。针对这一问题，采用小波变换多尺度分解 与重构结合阈值消噪的方法对原始数据进行降噪处理，它能很好的保持原始信号的瞬变特征，并对处理后的数据 采用逻辑法进行目标航迹起始跟踪。通过实验仿真，表明该方法消噪效果很好，能减少虚假航迹的数量，即使多个 目标的航迹出现交叉也能实现目标的区分和跟踪。

关键词: 小波, 逻辑法, 多目标, 数据处理, 航迹跟踪