CAJ | 학술논문

减背景法是计算机视觉领域常用的前景目标获取方法,减背景法的关键是背景模型的建立和更新以及减除背景后的噪声滤除.基于统计的背景建模方法计算量都比较大,背景更替方法建模避免了大量的计算.动态扩展滤波法是一种对前景目标信息破坏程度低,对噪声具有很好滤出效果的滤波方法.在摄像头静止的情况下,利用背景更替的背景建模及更新方法结合动态扩展滤波能够提取出清晰的前景目标.
감배경법시계산궤시각영역상용적전경목표획취방법,감배경법적관건시배경모형적건립화경신이급감제배경후적조성려제.기우통계적배경건모방법계산량도비교대,배경경체방법건모피면료대량적계산.동태확전려파법시일충대전경목표신식파배정도저,대조성구유흔호려출효과적려파방법.재섭상두정지적정황하,이용배경경체적배경건모급경신방법결합동태확전려파능구제취출청석적전경목표.
Background subtraction is a method used mostly to get foreground objects in computer vision field;the keys of background subtraction are the building and updating of background and fihering of noises.The method based on background alternation needs a little of computation than the one based on statistic.Dynamic expanding filtering can do a little damage to the foreground objects and remove noises very well.When the camera is immobile,by using the methods mentioned,the foreground objects can be gotten clearly.