基于鱼眼视频图像的人群运动估计算法

Estimation algorithm of crowd motion based on fisheye video image

随着公共活动在规模和数量上的不断增长,人群危险事件的预防已成为人群监控安全领域的重要问题。本文针对常规相机在人群监控领域的局限性,使用鱼眼镜头对人群进行监控,提出了基于图像金字塔迭代的LK光流算法,得到人群运动的矢量,对人群运动的方向和速度等信息进行估计,便于提前预防危险事件的发生。通过对比实验验证,结果表明该算法与高精度的全搜索块匹配算法结实验结果接近,且耗时更少,适用于人群监控领域。

With the continuous growth of public activities in scale and quantity, prevention of dangerous events in the crowd has become an important issue in the field of crowd monitoring and security. To deal with the limitation of common camera involved in crowd monitoring, the fisheye lens have been applied to capture videos, hnage pyramid iterative LK optical flow algorithm is applied to obtain the motion vector. The information of the direction and speed of the movement of the crowd is estimated for preventing the occurrence of dangerous events in advance. The comparative experiment and analysis with full search method demonstrate that Image pyrantid iterative LK optical flow algorithm is effective and suitable for the field of crowd monitoring.