A Generic Regression Framework for Pose Recognition on Color and Depth Images
This work addresses pose recognition for applications like human-computer interaction, but it is incremental as it builds on existing cascaded regression methods by adapting them to depth data.
The paper tackles 3D pose estimation from single depth images by designing an intermediate body parts representation that transforms pose estimation into a per-pixel classification problem, achieving accurate predictions invariant to pose, body shape, and clothing.
Cascaded regression method is a fast and accurate method on finding 2D pose of objects in RGB images. It is able to find the accurate pose of objects in an image by a great number of corrections on the good initial guess of the pose of objects. This paper explains the algorithm and shows the result of two experiments carried by the researchers. The presented new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition approach, designing an intermediate body parts representation that maps the difficult pose estimation problem into a simpler per-pixel classification problem. Our large and highly varied training dataset allows the classifier to estimate body parts invariant to pose, body shape, clothing. Finally, we generate confidence-scored 3D proposals of several body parts by re-projecting the classification result and finding local modes.