本文描述一种多特征实时电视跟踪器,应用3×3中值滤波器对目标图像进行预处理,采用SOBEL算法提取目标的边缘信息,利用目标灰度和边缘联合特征的贝叶斯分类算法检测和分割目标,在低对比度小目标情况下可以稳定跟踪目标,经外场试验取得满意的结果,该电视跟踪器已用于地空武器系统中。 This paper describes a multi-feature real-time TV tracker. The 3 × 3 median filter is used to preprocess the target image. The SOBEL algorithm is used to extract the edge information of the target. The Bayesian classification algorithm based on the target gray and the edge feature is used to detect the edge information. And segmentation target, the target can be stably tracked in the case of small targets with low contrast, and satisfactory results have been obtained through field experiments. The television tracker has been used in the ground-air weapon system.