夜间图像匹配中的斑状噪声预处理

Speckle noise pre-processing technology on imagecaptured at night for pattern matching

夜间图像匹配中,实时夜间图像中的斑状噪声影响了边缘相关匹配的性能。在分析了斑状噪声特点的基础上,提出了一种新的基于标记的噪声预处理方法,先标记出图像中的斑状噪声点,在匹配时被标记的噪声点不参与相关统计,从而达到消除斑状噪声对匹配影响的目的。该方法与传统的中值滤波、均值滤波等方法相比,更能提高相关匹配的性能,试验结果验证了该方法的有效性。

The real-time images captured at night in pattern matching are usually corrupted by speckle noise, which depresses the matching performance. In order to suppress the influence of speckle noise to pattern matching, a new method has been proposed in the paper. The speckle noise is marked and then is out of correlation statistics in pattern matching. Compared with the most popular algorithms, such as median filtering and the average filtering, this method is more efficient for pattern matching. Experimental results show that this method is available.