基于非线性扩散滤波的运动细胞检测方法

摘要

将非线性扩散滤波和背景差分法相结合，提出了一种新的运动细胞检测方法。通过在时间域内使用非线性扩散滤波，消除了背景差分法对阈值的强依赖性，并消除了图像噪声，增强了图像边界。实验结果表明，新方法能够较好地检测出运动细胞。%Combining the background subtraction and non‐linear diffusion filtering ,the paper proposes a new approach for automatic detection multiple cells .T hrough improving non‐linear diffusion filtering in the time domain ,it eliminates the strongly dependent on the threshold value of background subtraction and the image noise ,and enhances the image bounda‐ry .The experiment results show that the approach can detect the multiple cells effectively .