【摘要】 该文研究了基于Kalman滤波理论的渐消记忆递归最小二乘法,探讨了渐消记忆递归最小二乘法在重建图像背景中的应用,并用于实现在复杂背景下视频图像动目标的检测。首先用该算法对复杂背景进行更新预测,然后用当前帧图像与预测背景差分提取动目标,最后用灰度投影算法计算出目标的质心。整个目标检测方法简单、有效,便于用硬件快速实现。文中给出了实验结果。更多还原

【Abstract】 The fading memory recursive least-squares based on Kalman filter is studied,and the fading recursive least-squares applied to rebuild image background is also discussed in this paper,which is used for moving visual object detection in image sequence under the complex background.First,this algorithm is adopted to predict and update the complex image background,and then the moving object is segmented by current frame difference from predicted background.And at last the gray projection algorithm is used to calculate the centroid of detected object.This method of object detection is simple and efficient ,and can be more quickly achieved by hardware.The experiment result of image processing is also described.更多还原