Dual Generative Models for Human Pose Estimation
ثبت نشده
چکیده
Given a image photographed somebody in action, we describe a dual-generative-model approach for estimating human body pose from silhouette. In contrast to existing techniques, which mostly learn regression model whereby make inference of body pose for unknown input [1, 2, 6, 7], we transform the problem into searching of the best pair of upper pose and lower pose. This searching strategy can reduce significantly computational cost from global search of O(m̃n) to two subposes search of O(m + n) 1plus some cost of auxiliary works, however which can be extremely optimized. For regular cases, we observed that it is easy to divide image into two subimages representing upper and lower body. A local generative model is used to select from database enough candidates of upper and lower poses, and combine them under spatial constraint into full poses. Together with the full-body scores evaluated from a global generative model, we overall evaluate all full pose candidates and choose the best subpose pair accordingly. Examples are given of body pose estimation from both synthesized images and real images, both showing promising results.
منابع مشابه
Shape Outlier Detection Using Pose Preserving Dynamic Shape Models
In this paper, we introduce a framework for shape outlier, like carrying object, detection in different people from different views using pose preserving dynamic shape models. We model dynamic human shape deformations in different people using kinematics manifold embedding and decomposition of nonlinear mapping using kernel map and multilinear analysis. The generative model supports pose-preser...
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 کاملCarrying Object Detection Using Pose Preserving Dynamic Shape Models
In this paper, we introduce a framework for carrying object detection in different people from different views using pose preserving dynamic shape models. We model dynamic shape deformations in different people using kinematics manifold embedding and decomposable generative models by kernel map and multilinear analysis. The generative model supports pose-preserving shape reconstruction in diffe...
متن کاملFENZI, OSTERMANN: EMBEDDING GEOMETRY IN CLASS GENERATIVE MODELS 1 Embedding Geometry in Generative Models for Pose Estimation of Object Categories
Regression-based models built on local gradient-based feature descriptors have showed to be successful for continuous pose estimation of object categories. Nonetheless, a crucial weakness of these methods is that no geometric information is taken into account. Therefore, geometrically inconsistent poses may be preferred, and this forces to employ a coarse-grained pose estimator as a pre-process...
متن کاملCombining PGMs and Discriminative Models for Upper Body Pose Detection
In this project, I utilized probabilistic graphical models together with discriminative models such as SVM to perform upper body pose estimation. Figure 1 illustrates the definition of a problem in terms of input and output. Pose estimation is an important problem that has a wide array of applications such as pedestrian detection, sports video analysis, action recognition, etc. The entire human...
متن کامل