3D human pose recovery from image by efficient visual feature selection

نویسندگان

  • Cheng Chen
  • Yi Yang
  • Feiping Nie
  • Jean-Marc Odobez
چکیده

In this paper we propos images. Given the visua to find relevant pose c recover a continuous p propose to use an effic The task is formulated a nent subset, and the c components are used in recovery. As second con dates, where the measu in the database. Sparse to be retrieved. The e evaluations on both syn system we have implem

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images

We address the problem of estimating human body pose from a single image with cluttered background. We train multiple local linear regressors for estimating the 3D pose from a feature vector of gradient orientation histograms. Each linear regressor is capable of selecting relevant components of the feature vector depending on pose by training it on a pose cluster which is a subset of the traini...

متن کامل

Human Pose Estimation with Regression by Fusing Multi-View Visual Information

We consider the problem of estimating 3D human body pose from visual signals within a discriminative framework. It is challenging because there is a wide gap between complex 3D human motion and planar visual observation, which makes this a severally ill-conditioned problem. In this paper, we focus on three critical factors to tackle human body pose estimation, namely, feature extraction, learni...

متن کامل

Online 3D Reconstruction and 6-DoF Pose Estimation for RGB-D Sensors

In this paper, we propose an approach to Simultaneous Localization and Mapping (SLAM) for RGB-D sensors. Our system computes 6-DoF pose and sparse feature map of the environment. We propose a novel keyframe selection scheme based on the Fisher information, and new loop closing method that utilizes feature-to-landmark correspondences inspired by image-based localization. As a result, the system ...

متن کامل

Estimating Human Pose from Occluded Images

We address the problem of recovering 3D human pose from single 2D images, in which the pose estimation problem is formulated as a direct nonlinear regression from image observation to 3D joint positions. One key issue that has not been addressed in the literature is how to estimate 3D pose when humans in the scenes are partially or heavily occluded. When occlusions occur, features extracted fro...

متن کامل

Localized fusion of Shape and Appearance features for 3D Human Pose Estimation

Image based 3D human pose estimation is an important research area because of its application in many different fields such as content-based image retrieval, human computer interaction (HCI), human gait analysis, computer animation in movies, and visual surveillance. There are two basic types of approaches to 3D pose estimation from images. The first type is the generative method, where the pos...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Computer Vision and Image Understanding

دوره 115  شماره 

صفحات  -

تاریخ انتشار 2011