未标定视频下的动态人体身高测量

Visual metrology for height of pedestrian from uncalibrated video

针对视频下的动态人体身高测量过程中,依赖三维场景的结构化信息,或者需要事先对相机进行标定的情况,提出了一种视觉测量算法对未标定视频中的行人身高进行测量。该方法首先利用帧差法提取每帧图像中的人体区域信息,然后由该区域的主轴方向确定人体的头顶点和垂足点,再由头顶点和垂足点形成的两个平行虚拟平面确定水平消失线、由主轴方向确定竖直消失点,最后根据射影变换的交比不变量来确定人体的身高。该方法以人在正常行走过程中身高基本保持不变为合理假设,并且充分利用了视频中的人体运动信息。实验结果表明,测量结果的平均相对误差低于2.2%,能够满足人体身高测量的精度需要。

Considering that measurements of the pedestrian’s height from video usually depend on the knowledge of 3 D scene information, or the camera’s internal calibration, a visual metrology algorithm is proposed to measure the height of a pedestrian in the uncalibrated video. Firstly, the foreground pedestrian is extracted in each frame image by simple frame difference algorithm. Then the major axis of the foreground is estimated to determine the pedestrian’s top（head）and bottom（foot）points, and two parallel virtual planes are constructed by the top/bottom points to determine the horizontal vanishing line, while the vertical vanishing point is obtained by the intersection of the major axes. Finally, the pedestrian’s height is estimated by the cross ratio theorem. This method is based on the reasonable hypothesis that a pedestrian’s height has very small difference during the normal walking process, and uses motion information sufficiently. Experimental results show that the average relative error is less than 2. 2%, so the precision can achieve the requirement.