一种改进的基于平均背景模型的运动目标检测算法

An Improvement of Moving Object Detection Algorithm Based on Average Background Model

通过实验仿真分析探讨了基于背景差分法的两种运动目标检测算法(平均背景模型法和codebook模型法)的性能和存在问题,并在此基础上提出了一种改进的平均背景模型的算法.算法采用当前图像与背景相减后差分图像的灰度直方图进行阈值的选取,同时引进新的背景更新方法,由分割得到的前景图像来控制背景更新的区域.实验结果表明,改进后的算法在与原算法使用相同的初始帧数的基础上,目标检测的完整性和有效性均有所提高,且能够适应背景缓慢变化的场景.

It first implement two moving object detection algorithms based on the background difference method（the averaging background method and the codebook background method） by simulation experiments,and discuss their performance and problems.Furthermore,an improved average background model is proposed,including the choice of threshold and background updating.As the experimental results shown,the improved algorithm can enhance the detection effectiveness compared with the original algorithm in the case of the same number of initial frames,and can be used in broader field.