海面背景红外目标的识别算法

Recognition algorithm for sea background infrared targets

为了实现多角度状态的舰船目标识别,针对低信噪比下海面背景的目标红外图像,提出了一种基于分段拟合的稳定提取海天线信息的算法。在此基础上对经过目标分割后得到的感兴趣区域统计提取舰船目标的形状特征、位置特征等,考虑海面的干扰目标,设计综合分类器,通过对提取的各目标特征进行概率融合的方法实现目标判断。进行了仿真平台软件的试验测试。结果表明,使用该算法可以实现在不同环境和未知海天线的情况下对海面舰船目标多角度状态的可靠识别。

An efficient sub-fitting algorithm was developed to get sea surface information for sea background, infrared imagery with low SNR at variant angles. The target features including shape and position are then extracted in the areas of interest obtained by object segmentation. Finally, an integrated classifier implements target recognition using the probability based feature fusion method. The algorithm is validated in simulations showing it can recognize targets at variant angles and in variant environmental conditions.