Estimating Anthropometry and Pose from a Single Uncalibrated Image

Barron, Carlos; Kakadiaris, Ioannis A.

doi:10.1006/cviu.2000.0888

Cited by 69 publications

(45 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ambró sio et al [33] describe a photogrammetric approach that enforces temporal smoothness to resolve the ambiguity due to foreshortening. Barró n and Kakadiaris [34] simultaneously estimate 3D pose and anthropometry (body parameters) from 2D joint positions in a constrained optimization method.…”

Section: Previous Workmentioning

confidence: 99%

Recovering 3D human body configurations using shape contexts

Mori

Malik

2006

IEEE Trans. Pattern Anal. Mach. Intell.

229

140

View full text Add to dashboard Cite

Abstract-The problem we consider in this paper is to take a single two-dimensional image containing a human figure, locate the joint positions, and use these to estimate the body configuration and pose in three-dimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these stored views, the locations of the body joints (left elbow, right knee, etc.) are manually marked and labeled for future use. The input image is then matched to each stored view, using the technique of shape context matching in conjunction with a kinematic chain-based deformation model. Assuming that there is a stored view sufficiently similar in configuration and pose, the correspondence process will succeed. The locations of the body joints are then transferred from the exemplar view to the test shape. Given the 2D joint locations, the 3D body configuration and pose are then estimated using an existing algorithm. We can apply this technique to video by treating each frame independently-tracking just becomes repeated recognition. We present results on a variety of data sets.

show abstract

Section: Previous Workmentioning

confidence: 99%

Recovering 3D human body configurations using shape contexts

Mori

Malik

2006

IEEE Trans. Pattern Anal. Mach. Intell.

229

140

View full text Add to dashboard Cite

show abstract

“…Some authors use monocular views [2][3][4][5], while others focus on multi-camera video streams [6][7][8][9][10]. Some limit their work to the use of calibrated views [8,9], [11][12][13], while others choose noncalibrated images [2].…”

Section: Introductionmentioning

confidence: 99%

3D Human Motion Reconstruction Using Video Processing

Roodsarabi

Behrad

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract.One of the important problems in human motion analysis is the 3D reconstruction of human motion, which utilizes the anatomic point's positions. These points can uniquely define the position and orientation of all anatomical segments. In this paper, a new method for reconstruction of human motion from the image sequence of a single static camera is described. In this method 2D tracking is used for 3D reconstruction, which a database of selected frames are used for the correction of tracking process. We use Discrete Cosine Transform (DCT) block as a "Matrix des criptor" used in the matching process for finding appropriate frame in the database and tracking process. Finally, 3D reconstruction is performed using Taylor method. By using DCT, we can select best frequency region for various tasks such as tracking, matching, correcting joints and so on. Experimental results showed the promise of the algorithm.

show abstract

“…The type of input data is fundamental when determining the best technique for resolving a pose. Some authors use monocular still images 9 , while others focus on multi-camera video streams [1][2][3][4]8,10 . Some limit their work to the use of calibrated views, while others choose non-calibrated images.…”

Section: Introductionmentioning

confidence: 99%

Automatic creation of three-dimensional avatars

et al. 2003

View full text Add to dashboard Cite

Highly accurate avatars of humans promise a new level of realism in engineering and entertainment applications, including areas such as computer animated movies, computer game development interactive virtual environments and tele-presence. In order to provide high-quality avatars, new techniques for the automatic acquisition and creation are required. A framework for the capture and construction of arbitrary avatars from image data is presented in this paper. Avatars are automatically reconstructed from multiple static images of a human subject by utilizing image information to reshape a synthetic three-dimensional articulated reference model. A pipeline is presented that combines a set of hardware-accelerated stages into one seamless system. Primary stages in this pipeline include pose estimation, skeleton fitting, body part segmentation, geometry construction and coloring, leading to avatars that can be animated and included into interactive environments. The presented system removes traditional constraints in the initial pose of the captured subject by using silhouette-based modification techniques in combination with a reference model. Results can be obtained in near-real time with very limited user intervention.

show abstract

Estimating Anthropometry and Pose from a Single Uncalibrated Image

Cited by 69 publications

References 20 publications

Recovering 3D human body configurations using shape contexts

Recovering 3D human body configurations using shape contexts

3D Human Motion Reconstruction Using Video Processing

Automatic creation of three-dimensional avatars

Contact Info

Product

Resources

About