Pose-conditioned joint angle limits for 3D human pose reconstruction

Akhter, Ijaz; Black, Michael J.

doi:10.1109/cvpr.2015.7298751

Cited by 378 publications

(384 citation statements)

References 24 publications

Supporting

Mentioning

381

Contrasting

Unclassified

Order By: Relevance

“…Given 2D joint locations, lifting them to 3D pose is challenging. Existing approaches use bone length and depth ordering constraints [Mori and Malik 2006;Taylor 2000], sparsity assumptions [Wang et al 2014;Zhou et al 2015,a], joint limits [Akhter and Black 2015], inter-penetration constraints [Bogo et al 2016], temporal dependencies [Rhodin et al 2016b], and regression [Yasin et al 2016]. Treating 3D pose as a hidden variable in 2D estimation is an alternative [Brau and Jiang 2016].…”

Section: Multi-viewmentioning

confidence: 99%

VNect

et al. 2017

View full text Add to dashboard Cite

Fig. 1. We recover the full global 3D skeleton pose in real-time from a single RGB camera, even wireless capture is possible by streaming from a smartphone (left). It enables applications such as controlling a game character, embodied VR, sport motion analysis and reconstruction of community video (right). Community videos (CC BY) courtesy of Real Madrid C.F. [2016] and RUSFENCING-TV [2017].We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fullyconvolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control-thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

show abstract

Section: Multi-viewmentioning

confidence: 99%

VNect

et al. 2017

View full text Add to dashboard Cite

show abstract

“…One class of learning approaches uses direct mapping from image features [32,60,131,132,133,162,263], and another class of approaches maps the image features to 2D parts and then uses modeling or learning approaches to map 2D parts to 3D poses [78,134,135,136,137]. …”

Section: Methodsologiesmentioning

confidence: 99%

“…The set of joint positions and limb orientations are both effective representations of a human pose. One coordinate-free representation is introduced in [137]: the local coordinates of the upper-arms, upper-legs, and the head can be converted into spherical coordinates, and the discretized azimuthal and polar angles of the bones can be defined. The kinematic model allows us to incorporate prior beliefs about joint angles.…”

Section: Human Body Modelsmentioning

confidence: 99%

Human Pose Estimation from Monocular Images: A Comprehensive Survey

Gong

Zhang

Gonzàlez

et al. 2016

Sensors

127

View full text Add to dashboard Cite

Human pose estimation refers to the estimation of the location of body parts and how they are connected in an image. Human pose estimation from monocular images has wide applications (e.g., image indexing). Several surveys on human pose estimation can be found in the literature, but they focus on a certain category; for example, model-based approaches or human motion analysis, etc. As far as we know, an overall review of this problem domain has yet to be provided. Furthermore, recent advancements based on deep learning have brought novel algorithms for this problem. In this paper, a comprehensive survey of human pose estimation from monocular images is carried out including milestone works and recent advancements. Based on one standard pipeline for the solution of computer vision problems, this survey splits the problem into several modules: feature extraction and description, human body models, and modeling methods. Problem modeling methods are approached based on two means of categorization in this survey. One way to categorize includes top-down and bottom-up methods, and another way includes generative and discriminative methods. Considering the fact that one direct application of human pose estimation is to provide initialization for automatic video surveillance, there are additional sections for motion-related methods in all modules: motion features, motion models, and motion-based methods. Finally, the paper also collects 26 publicly available data sets for validation and provides error measurement methods that are frequently used.

show abstract

“…With a simple adjustment to the height and weight, the 3-D human model that we created can be used to analyze the pose, stability, and shadows in any image of people. It is possible that the manual estimation of the pose and lighting can be replaced with recent advances in automatic pose (Akhter & Black, 2015) and lighting (Kee & Farid, 2010b) estimation. Such advances will simplify and accelerate the speed with which 3-D models can be constructed.…”

Section: Discussionmentioning

confidence: 99%

A 3-D Stability Analysis of Lee Harvey Oswald in the Backyard Photo

Farid

Pittala

Whiting

2015

JDFSL

View full text Add to dashboard Cite

Fifty years have passed since the assassination of U.S. President Kennedy. Despite the long passage of time, it is still argued that the famous backyard photo of Oswald, holding the same type of rifle used to assassinate the President, is a fake. These claims include, among others, that Oswald's pose in the photo is physically implausible. We describe a detailed 3-D stability analysis to determine if this claim is warranted.

show abstract

Pose-conditioned joint angle limits for 3D human pose reconstruction

Cited by 378 publications

References 24 publications

VNect

VNect

Human Pose Estimation from Monocular Images: A Comprehensive Survey

A 3-D Stability Analysis of Lee Harvey Oswald in the Backyard Photo

Contact Info

Product

Resources

About