【24h】

Study on moving-object-detection arithmetic based on W4 theory

机译:基于W4理论的运动目标检测算法研究

获取原文

摘要

The classic W4 theory is recognized as an importance branch of the moving object detection field because it can simply and effectively describe a background model, calculate the result very quickly. But we find that this theory has two disadvantages: the first is the definition of the stationary pixels, the second is the background updating criterion when some foreground moving object is fused in to the background. So we modify the background-pixels- segment equation and the background model updating criterion. A new modified moving object detection arithmetic is presented in this paper. The experiment results certify that the presented arithmetic is right and the result used the new arithmetic is superior to the result used the classic W4 theory in the same condition.
机译:经典的W4理论被认为是运动物体检测领域的重要分支,因为它可以简单有效地描述背景模型,非常快速地计算出结果。但是我们发现该理论有两个缺点:第一个是固定像素的定义,第二个是将某些前景移动物体融合到背景中时的背景更新标准。因此,我们修改了背景像素分段方程和背景模型更新准则。提出了一种新的改进的运动目标检测算法。实验结果证明,在相同条件下,该算法是正确的,新算法的计算结果要优于经典W4理论的计算结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号