Posture estimation using structure and motion models

Abstract

Sensing of human motion is very important for humancomputer interactive applications such as virtual reality, gesture recognition, and communication. A vision system is suitable for human-computer interaction since this involves passive sensing and the system can estimate the motion of the user without any discomfort for the user. In this paper, we propose an algorithm for fast posture estimation of the user from an image sequence by using the position information of the hands and head. Our algorithm is founded on a model based method. The parameters of a geometric model are calculated from human kinematics. It is inadequate to obtain a unique solution from the image information such as position of the head and hands. The unknown parameters are predicted by the motion models and the previous posture parameters, then the unknown parameters are adjusted by a minimization method.

A Survey of Computer Vision-Based Human Motion Capture

“…Wren and Pentland [145] generalized the concept of knowing the motion beforehand by suggesting that various behavior models may be used to improve the pose estimation. An example of this was also published by Iwai et al [65] where six different motion models are used.…”

“…A good example is Chroma-keying where a person appears in front of a one-color, usually blue, screen wearing nonblue clothes. By thresholding, the person can easily be separated from the background [32,65]. The opposite approach, where the subject wears one color, usually dark, clothes against a different background is also very popular [12].…”

Fuzzy human motion analysis: A review

“…A variety of works in the model based human motion tracking have employed the kinematic chain [82,83,84,85,86,87,88,89,90,91]. Bregler et al [94] demonstrated a comprehensive visual motion estimation technique using the kinematic chain in a complex video sequence, as depicted in Figure 9.…”

“…In the model based human motion tracking, the human body models such as the stick figures, 2D and 3D motion description models are adopted to model the complex, non-rigid structure of the human body [82,83,84,85,86,87,88,89,90,91]. Readers can refer to [20,21,24,92] for the detailed reviews.…”

“…Readers can refer to [20,21,24,92] for the detailed reviews. The stick figure model represents the human body as a combination of sticks or line segments connected by the joints [82,83,84,85], while the 2D models represents the human body using 2D ribbons or blobs [83,86,87]. 3D models are used to depict the human body structure in a more detailed manner using cones, cylinders, spheres, ellipses etc.…”