A Robust Method for Human Pose Estimation Based on Geodesic Distance Features

Handrich, Sebastian; Al-Hamadi, Ayoub

doi:10.1109/smc.2013.159

Cited by 8 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it may meet the problems of miscorrespondence, and heavily relies on the training samples. In the work of [15], the authors adopt the geodesic distance as the feature to avoid the ambiguities in pose estimation, but it mainly aims at estimating the upper body pose. Recently, in [18], the authors optimize the method [13] by introducing a random verification forest so that the vote can be much more accurate.…”

Section: D Pose Estimation From Depth Imagesmentioning

confidence: 99%

Cascaded 3D Full-Body Pose Regression from Single Depth Image at 100 FPS

Xia

Zhang

2018

2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

View full text Add to dashboard Cite

There are increasing real-time live applications in virtual reality, where it plays an important role in capturing and retargetting 3D human pose. But it is still challenging to estimate accurate 3D pose from consumer imaging devices such as depth camera. This paper presents a novel cascaded 3D full-body pose regression method to estimate accurate pose from a single depth image at 100 fps. The key idea is to train cascaded regressors based on Gradient Boosting algorithm from pre-recorded human motion capture database. By incorporating hierarchical kinematics model of human pose into the learning procedure, we can directly estimate accurate 3D joint angles instead of joint positions. The biggest advantage of this model is that the bone length can be preserved during the whole 3D pose estimation procedure, which leads to more effective features and higher pose estimation accuracy. Our method can be used as an initialization procedure when combining with tracking methods. We demonstrate the power of our method on a wide range of synthesized human motion data from CMU mocap database, Human3.6M dataset and real human movements data captured in real time. In our comparison against previous 3D pose estimation methods and commercial system such as Kinect 2017, we achieve the state-of-the-art accuracy.

show abstract

Section: D Pose Estimation From Depth Imagesmentioning

confidence: 99%

Cascaded 3D Full-Body Pose Regression from Single Depth Image at 100 FPS

Xia

Zhang

2018

2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)

View full text Add to dashboard Cite

show abstract

“…Baak et al [1] extract feature points by iteratively computing the geodesic extrema and setting the geodesic distance between previous extreme points to zero, and perform a voting for matching poses using both a local optimization of correspondences of mesh vertices and a nearest-neighbor search of the database. Handrich and Al-Hamadi [7] determine feature points using pose-independent geodesic distances and impose a kinematic skeleton model fitting for obtaining the skeleton points of upper body.…”

Section: A Feature Point Approachesmentioning

confidence: 99%

“…(b) When K is small, the cluster centers of each limb are more likely to locate along the stretching direction of the limb (see the fourth row of Figs. 7,9) and such a distribution of locations guarantees the prediction skeleton points approximately lie on a straight line fitting for those centers; when K is greater, those centers locate irregularly on each limb which makes the prediction of skeleton points incorrect.…”

Section: A Selections Of Cluster Number K and Modelsmentioning

confidence: 99%

“…According to the methodology, research work on pose estimation via depth data can be roughly divided into four categories: the feature point approaches, the pixel classification approaches, the probabilistic graphical model approaches and others. In general, the feature point approaches [12], [1], [13], [8], [7] detect interest points of the range image ( with the extrema of geodesic distances of depth points), and then employ a database lookup scheme (e.g., [1]), classify each interesting point as a point of a body component using its local descriptors (e.g., [12]), or detect additional feature points as the secondary feature (e.g., [1], [13]) for discriminating human poses; the pixel classification approaches [14], [15], [18], [20], [11], [3], [9] determine which body component each pixel belongs to, using the so-called depth difference feature and random decision forests; the probabilistic graphical model approaches [26], [27], [6], [23] represent a human body as a set of rigid or non-rigid parts connected with pairwise constraints and formulate the localization of body parts as an optimization of the prior probability of part configurations. Different approaches fit for different applications of visual media, i.e., the codec and reconstruction of models of human body, the retrieval and analysis of human motion.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, feature point approaches always integrate this technique with other complementary techniques, such as regression forest based decision [8], additional feature landmark detection [13], [1], kinematic model fitting [7] or database lookup [1].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sparse Pose Regression via Componentwise Clustering Feature Point Representation

Liu

Kong

Wang

et al. 2016

IEEE Trans. Multimedia

View full text Add to dashboard Cite

We propose 2D pose estimation from a single range image of human body, using sparse regression with a componentwise clustering feature point representation (CCFPR) model. CCFPR includes primary feature points and secondary feature points. The primary feature points consist of the torso center and five extremal points of human body, and further serve to classify all body pixels as the points of six body components. The secondary feature points are given by the cluster centers of each of the five components other than the torso, using Kmeans cluster. The human pose is obtained by learning a sparse projection matrix, which maps CCFPR to the skeleton points of human body, based on the assumption that each skeleton point be represented by a combination of a few feature points of associated body components. Experimental results on both virtual data and real data show that, under the sparse regression model with suitably selected cluster number, CCFPR outperforms the random decision forest approach and prediction results of KINECT SENSOR V2.

show abstract