基于时空相关性检测的视频序列动目标检测方法

在充分分析了现有算法在复杂背景下所存在的不足的基础上，提出了一种基于视频序列像素时空相关性检测的动目标检测方法。该方法首先用每一帧中像素的空间相关性检测出目标；再用序列图象中目标的时间相关性检验目标的真实性。实验表明，该方法能很好地检测出运动目标，并具有较强的抗干扰能力。

Detection of Moving Object Detection in Video Sequence Based on Detection of Space-time Relativity

On the basis of analyzing the deficiency of the actual algorithm in the complex background. We gave a method of moving object detection based on the detection of the space-time relativity of the pels in a video sequence. Firstly, the space relativity of the pels in a frame is used to detect the object. Then the authenticity of the object is proved with the time relativity of the object in a video sequence. Experimentations indicate that this method has a good anti-jamming ability. And through it, we can detect the moving object from a video sequence well.