20 Modeling and Measurement of a Pedestrian’s Center-of-Mass Trajectory 163 Fig. 20.2 Picture of a test. The pedestrian walking in front of the mobile platform. MS Kinect and a laptop are on the mobile platform taking images at approximately 30 fps 1 0.8 1.2 X (m) 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 Z (m) Front view 2.4 2.6 2.8 3 Y (m) 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 Z (m) Lateral view Fig. 20.3 Segmented human body the point clouds to a proper orientation is performed using Eq. (20.6). Figure 20.3 shows the cloud of points for the pedestrian body. A geometric 3D centroid is calculated and tracked on all the point clouds. T.x; a/ D 2 66 4 1 0 0 0 0 cos.˛/ sin.˛/ 0 0 sin.˛/ cos.˛/ 0 0 0 0 1 3 77 5 (20.6)
RkJQdWJsaXNoZXIy MTMzNzEzMQ==