Issue No. 09 - September (2006 vol. 28)
Fengjun Lv , Inst. for Robotics & Intelligent Syst., Univ. of Southern California, Los Angeles, CA
A self-calibration method to estimate a camera's intrinsic and extrinsic parameters from vertical line segments of the same height is presented. An algorithm to obtain the needed line segments by detecting the head and feet positions of a walking human in his leg-crossing phases is described. Experimental results show that the method is accurate and robust with respect to various viewing angles and subjects
Cameras, Calibration, Legged locomotion, Humans, Layout, Robustness, Head, Image reconstruction, Parameter estimation, Tracking
Fengjun Lv, Tao Zhao and R. Nevatia, "Camera calibration from video of a walking human," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 28, no. 9, pp. 1513-1518, 2009.