A generalized parametric 3D shape representation for articulated pose estimation
نویسندگان
چکیده
We present a novel parametric 3D shape representation, Generalized sum of Gaussians (G-SoG), which is particularly suitable for pose estimation of articulated objects. Compared with the original sum-of-Gaussians (SoG), G-SoG can handle both isotropic and anisotropic Gaussians, leading to a more flexible and adaptable shape representation yet with much fewer anisotropic Gaussians involved. An articulated shape template can be developed by embedding G-SoG in a tree-structured skeleton model to represent an articulated object. We further derive a differentiable similarity function between G-SoG (the template) and SoG (observed data) that can be optimized analytically for efficient pose estimation. The experimental results on a standard human pose estimation dataset show the effectiveness and advantages of G-SoG over the original SoG as well as the promise compared with the recent algorithms that use more complicated shape models.
منابع مشابه
Shape Models of the Human Body for Distributed Inference
of “Shape Models of the Human Body for Distributed Inference” by Silvia Zuffi, Ph.D., Brown University, May 2015 In this thesis we address the problem of building shape models of the human body, in 2D and 3D, which are realistic and efficient to use. We focus our efforts on the human body, which is highly articulated and has interesting shape variations, but the approaches we present here can b...
متن کاملCombined discriminative and generative articulated pose and non-rigid shape estimation
Estimation of three-dimensional articulated human pose and motion from images is a central problem in computer vision. Much of the previous work has been limited by the use of crude generative models of humans represented as articulated collections of simple parts such as cylinders. Automatic initialization of such models has proved difficult and most approaches assume that the size and shape o...
متن کاملA Study on Human Gaze Detection Based on 3D Eye Model
Robust fake iris detection p. 10 A study on fast Iris restoration based on focus checking p. 19 A spatio-temporal metric for dynamic mesh comparison p. 29 Facetoface : an isometric model for facial animation p. 38 Matching two-dimensional articulated shapes using generalized multidimensional scaling p. 48 Further developments in geometrical algorithms for ear biometrics p. 58 Composition of com...
متن کامل3-d Hand Pose Estimation and Shape Model Refinement from a Monocular Image Sequence
This paper proposes a method to precisely estimate the shape and pose of articulated objects like a human hand. First, rough estimation is obtained using silhouette matching. Next, we apply the extended Kalman lter to tting a model to an image. However, because monocular images contain no depth information, ambiguity of the shape and pose cannot essentially be resolved for articulated objects. ...
متن کامل3D Body Reconstruction for Immersive Interaction
In this paper we present an approach for capturing 3D body motion and inferring human body posture from detected silhouettes. We show that the integration of two or more silhouettes allows us to perform a 3D body reconstruction while each silhouette can be used for identifying human body postures. The 3D reconstruction is based on the representation of body parts using Generalized Cylinders pro...
متن کامل