序列图像运动目标检测的一种快速算法

研究了序列视频图像中运动目标的检测与跟踪快速算法．研究基于Kalman滤波理论的渐消记忆最小二乘法，用该方法重建背景图像；采用图像差分算法提取运动目标；提出简化的等效灰度投影算法来计算目标的质心；采用记忆外推跟踪算法实现图像目标的跟踪，并且对全部算法做了仿真．仿真结果表明算法简单、有效、执行速度快、具有很强的适应性，能够用于单镜头序列图像中运动目标的检测与跟踪．

A fast algorithm for moving object detection in image sequence

The fast algorithm for moving objects detection and tracking in sequential images is studied in this paper. The fading memory recursive least- square based on Kalman filter is discussed, and it is applied to rebuild image background. Then the moving object is extracted by the method of images difference. A simplified equivalent gray value projection algorithm is proposed for object centroid calculation. The memory extrapolation is used to achieve target tracking. The algorithm is simulated. The results show that the algorithm proposed in this paper is simple, effective, high speed, and strong adaptability. So this algorithm can be used for moving object detection and tracking in sequences of monocular images.