Improved numerical inverse kinematics for human pose estimation

Yung-Ho Seo; Chil-Woo Lee; Jong-Soo Choi

doi:10.1117/1.3549255

Translator Disclaimer

1 March 2011 Improved numerical inverse kinematics for human pose estimation

Yung-Ho Seo, Chil-Woo Lee, Jong-Soo Choi

Author Affiliations +

Optical Engineering, 50(3), 037001 (2011). https://doi.org/10.1117/1.3549255

Abstract

We propose a real-time pose estimation method that addresses the weaknesses of the numerical inverse kinematics method. Using conventional inverse kinematics based on the numerical method requires many iterations; moreover, a singularity in the Jacobian matrix as well as a local minimum problem can occur. To solve these problems, we propose an inverse kinematics method combined with an unscented Kalman filter (UKF) to recover intermediate joint information. Because the numerical inverse kinematics method optimizes a state, the solution can often converge to the local minimum and require many iterations. We use several sigma points for analysis to find the optimum state by using an unscented transform. The improved method using a UKF converges faster than the numerical inverse kinematics method for the global minimum of the existing inverse kinematics. We use 2-D image processes to extract body areas from the input images, and a 3-D reconstruction algorithm is used to estimate the 3-D positions of the extracted human body area. Using the improved method, we generate intermediate joints for each body part and the results show that the proposed method reduces the computational complexity and increases the accuracy of estimation compared to conventional numerical inverse kinematics.

©(2011) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Yung-Ho Seo, Chil-Woo Lee, and Jong-Soo Choi "Improved numerical inverse kinematics for human pose estimation," Optical Engineering 50(3), 037001 (1 March 2011). https://doi.org/10.1117/1.3549255

Published: 1 March 2011

ACCESS THE FULL ARTICLE