视频序列中运动目标检测技术

Moving Objects Detection Algorithm in Video Sequences

本文提出了一种视频序列中运动目标检测的方法。首先,通过估计相邻两帧之间的相对噪声的特征参数检测出运动变化区域,然后结合当前帧的边界信息确定运动目标的边界位置,最后根据边界位置检测和提取出运动目标。实验结果表明,本文的方法能有效地检测出和提取出运动目标并具有较强的稳健性。

This paper presents an algorithm of detecting moving objects in video sequences. First, moving change region is detected based on estimating the parameters of relative noise between two consecutive frames. Then, edge location of moving objects is generated through combining moving change region and edge information in the current frame. Finally, moving object is detected according to its edge location. Experimental results show that the proposed algorithm is effective with strong robustness.