Biomedical Engineering Reference
In-Depth Information
Human Body Joints Estimation for Clinical
Jumping Analysis
Liangjia Zhu, Jehoon Lee, Peter Karasev, Ivan Kolesov,
John Xerogeanes, and Allen Tannenbaum
Abstract This paper presents an effective approach to estimate human body joints
from a monocular video captured with a handheld camera for clinical jumping
analysis. In this framework, the video frames are classified into color blobs and
represented by region adjacency graphs (RAGs). Then, the corresponding body
parts in the current frame are extracted and tracked based on the labels of RAG
nodes in the previous frame using a semantic graph growing method. Initially, each
RAG node of the current frame is associated with its most similar RAG node of the
previous frame. Then, in order to reduce the mismatches in the initial association,
the skeleton of legs is constructed to find the correct leg parts. In addition, a loose
stick figure model is used to disambiguate the misassignment by enforcing
geometric constraints defined between consecutive frames. Finally, the joint
positions are estimated and smoothed using a priori knowledge of the jumping
process. Experimental results demonstrate the effectiveness and robustness of
our algorithm.
1
Introduction
Analysis and treatment of anterior cruciate ligament (ACL) injuries frequently need
an analysis of the hip, knee, and ankle movement during the jumping process.
Those body joints can be labeled using sophisticated motion capture systems with
markers attached to patients' joints for a post-injury analysis. However, those
L. Zhu (
*
) • J. Lee • P. Karasev • I. Kolesov
School of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
e-mail:
ljzhu@gatech.edu
J. Xerogeanes
Department of Orthopedic Surgery, Emory University, Atlanta, GA, USA
A. Tannenbaum
Department of Electrical & Computer Engineering, Boston University, Boston, MA, USA
