3D dynamic pose estimation from markerless optical data

Abstract

This chapter provides an overview of three-dimensional (3D) dynamic Pose (position and orientation) estimation of human movement without the use of markers or sensors, more commonly known as Markerless Motion Capture (Markerless Mocap). As with Marker-based Motion Capture (Marker-based Mocap), the methods presented estimate the Pose of an underlying multibody subject-specific model comprising rigid segments with anatomically defined local reference frames and joint constraints. In addition, the model has an overlying surface representing the skin, or clothing, depending on the context. The focus of this chapter is on Markerless Mocap algorithms best suited to biomechanical analyses of human movement. In other words, those techniques appropriate for estimating 3D Pose directly, and accurately, from recorded data. Of all the approaches to Markerless Mocap, 3D-to-3D Pose estimation is most similar to Marker-based Mocap techniques because it requires arrays of multiple, time synchronous, video cameras encircling the capture volume. In addition to the underlying multibody skeletal model that marker-based and markerless techniques have in common, during Markerless Mocap, the subject is identified by a surface model overlying the skeleton. In each frame of motion data, a pixelated surface, comprised of a dense collection of points lying on the surface, is extracted from the scene and registered to the model. Neither marker-based nor 3D-to-3D Markerless Mocap is typically accurate enough to record the Pose of the bones at a resolution for studying joint dynamicsAn alternative markerless approach to joint level biomechanics has emerged. Biplanar videogradiography (or Dynamic Stereo X-ray) uses a 3D-to-2D approach to Markerless Mocap, whereby only two views of the subject are acquired because of space limitations and to minimize radiation exposure. A brief introduction to 3D-to-2D registration will be presented because this is covered in more detail in another chapter.