基于SVD的改进混合高斯模型弱小运动目标检测算法

Improved mixture Gauss model for dim and small moving target detection based on SVD

为了在提高弱小运动目标的检测准确度的同时满足实时性要求,提出了一种基于SVD的改进混合高斯模型弱小运动目标检测算法。针对普通混合高斯模型阈值选取没有针对性的问题,运用基于奇异值分解(SVD)的动态阈值调整更新方法,提高混合高斯模型对弱小运动目标检测准确度。实验结果表明,该算法能够准确、高效地检测特定弱小运动目标。

In order to improve the detection accuracy of dim and small moving targets and meet the real-time requirement, an improved mixture Gauss model based on SVD (singular value decomposition) is proposed for such detection. In view of the problem that there is no pertinence in the threshold selection of ordinary mixture Gauss model, a dynamic threshold adjustment update method based on SVD is used to improve the detection accuracy of the mixture Gauss model for dim and small moving targets. The experimental results show that the algorithm can accurately and efficiently detect specific dim and small moving targets.