Putting the pieces together: Connected Poselets for human pose estimation

Holt, Brian; Ong, Eng-Jon; Cooper, Helen; Bowden, Richard

doi:10.1109/iccvw.2011.6130386

Cited by 31 publications

(29 citation statements)

References 28 publications

(48 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our results to the state-of-the-art [13] on a publicly available dataset, and evaluate our results both quantitatively and qualitatively.…”

Section: Resultsmentioning

confidence: 99%

“…Appearance datasets include Buffy [9], People [18], Leeds Sports Poses [14]. Depth datasets are limited to CDC4CV Poselets [13] with 345 training and 347 test frames at 640x480 pixels over 3 subjects and Stanford ToF [10] with 2284 frames at a resolution of 144x176 fo a single subject.…”

Section: A Datasetmentioning

confidence: 99%

“…The availability of depth information from real-time depth cameras has simplified the task of pose estimation [28], [10], [22], [13], [11], [20] over traditional image capture devices by supporting high accuracy background subtraction, working in low-illumination environments, being invariant to colour and texture, providing depth gradients to resolve ambiguities and providing a calibrated estimate of the scale of the object. However, even with these advantages, there remains much to be done to achieve a pose estimation system that is fast and robust.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Accurate static pose estimation combining direct regression and geodesic extrema

Holt

Ong

Bowden

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

Abstract-Human pose estimation in static images has received significant attention recently but the problem remains challenging. Using data acquired from a consumer depth sensor, our method combines a direct regression approach for the estimation of rigid body parts with the extraction of geodesic extrema to find extremities. We show how these approaches are complementary and present a novel approach to combine the results resulting in an improvement over the state-of-the-art. We report and compare our results a new dataset of aligned RGB-D pose sequences which we release as a benchmark for further evaluation.

show abstract

“…We compare our results to the state-of-the-art [13] on a publicly available dataset, and evaluate our results both quantitatively and qualitatively.…”

Section: Resultsmentioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate static pose estimation combining direct regression and geodesic extrema

Holt

Ong

Bowden

2013

2013 10th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hernandez et al [18] use Graph Cuts optimization to classify pixels to seven body parts, while Baak et al [19] follow a data-driven hybrid strategy, combining local optimization and global retrieval techniques. In the same context, Probabilistic Graphical Models [20] as well as hybrid approaches, such as Connected Poselets [21], have also been used to infer the body pose.…”

Section: Related Workmentioning

confidence: 99%

Robust articulated upper body pose tracking under severe occlusions

Sigalas

Pateraki

Trahanias

2014

2014 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Articulated human body tracking is one of the most thoroughly examined, yet still challenging, tasks in Human Robot Interaction. The emergence of low-cost real-time depth cameras has greatly pushed forward the state of the art in the field. Nevertheless, the overall performance in complex, real life scenarios is an open-ended problem, mainly due to the high-dimensionality of the problem, the common presence of severe occlusions in the observed scene data, and errors in the segmentation and pose initialization processes.In this paper we propose a novel model-based approach for markerless pose detection and tracking of the articulated upper body of multiple users in RGB-D sequences. The main contribution of our work lies in the introduction and further development of a virtual User Top View, a hypothesized view aligned to the main torso axis of each user, to robustly estimate the 3D torso pose even under severe intra-and inter-personal occlusions, exempting at the same time the requirement of arbitrary initialization. The extracted 3D torso pose, along with a human arm kinematic model, gives rise to the generation of arms hypotheses, tracked via Particle Filters, and for which ordered rendering is used to detect possible occlusions and collisions.Experimental results in realistic scenarios, as well as comparative tests against the NiTE TM user generator middleware using ground truth data, validate the effectiveness of the proposed method.

show abstract

“…While a tremendous efforts have been devoted to gesture analysis, scene reconstruction and SLAM (Simultaneous Localization and Mapping) [1], [2], [3], only few study face recognition using RGB-D images. Although several 3D based approaches are claimed to be able to handle recognition across poses using one single RGB (or intensity) image [4], [5], the advantage given by the additional depth map in the RGB-D image is yet to be studied.…”

Section: Introductionmentioning

confidence: 99%

RGB-D Based Face Reconstruction and Recognition

Hsu

Liu

Peng

et al. 2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Most RGB-D based research focuses on gesture analysis, scene reconstruction and SLAM, but only few study its impacts on face recognition. A common yet challenging scenario considered in face recognition across pose takes a single 2D face of frontal pose as the galley and other poses as the probe set. We consider a similar scenario but with a RGB-D image pair taken at frontal pose in the gallery, only 2D images with a large scope of poses in the probe set, and study the advantage of the additional depth map on top of the regular RGB image. We formulate the 3D face reconstruction using the RGB-D image as a constrained optimization, and compare the results with different reconstruction settings. The reconstructed 3D face allows the generation of 2D face with specific poses, which can be matched with the probes. Experiments on the Biwi Kinect Head Pose Database and Eurecom Database show that the additional depth map substantially improves the crosspose recognition performance, and the depth-based component selection also improves the recognition under occlusion and expression variation.

show abstract

Putting the pieces together: Connected Poselets for human pose estimation

Cited by 31 publications

References 28 publications

Accurate static pose estimation combining direct regression and geodesic extrema

Accurate static pose estimation combining direct regression and geodesic extrema

Robust articulated upper body pose tracking under severe occlusions

RGB-D Based Face Reconstruction and Recognition

Contact Info

Product

Resources

About