Part template: 3D representation for multiview human pose estimation

Shen, Jianfeng; Yang, Wenming; Liao, Qingmin

doi:10.1016/j.patcog.2013.01.001

Cited by 8 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The line fitting method [12] was excluded because it is designed to work with a single cylindrical shape to be fitted, therefore its application in such scenario has no sense. Since MSAC and Tran et al approaches require vertex normals, we computed them for each point by lo-cally fitting a plane on its 80 neighbours 4 To extract multiple cylinders with MSAC approach, we iteratively removed all points falling inside the region delimited by ± 5% of the estimated radius. Note that, while MSAC approach needs to run each time the input is modified, our algorithm performs the ellipses fitting just once at the beginning, then the extraction is performed by dynamically run the game-theoretical selection with a modified payoff matrix (as explained in 3.5 ).…”

Section: Real-world Experimentsmentioning

confidence: 99%

“…For this reason, 3D data are widely employed in a variety of fields, ranging from cultural heritage [1] to industrial inspection [2,3] . Many practical applications employing point cloud data require the extraction and identification of one or more well-known objects included in the scene: some examples are human pose estimation [4] , object segmentation [5,6] and model fitting [7] . Despite the high quality offered by modern acquisition devices, in some situations 3D data captured from a scene are far from being perfect.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Cylinders extraction in non-oriented point clouds as a clustering problem

Bergamasco

Pistellato

Albarelli

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

Finding geometric primitives in 3D point clouds is a fundamental task in many engineering applications such as robotics, autonomous-vehicles and automated industrial inspection. Among all solid shapes, cylinders are frequently found in a variety of scenes, comprising natural or man-made objects. Despite their ubiquitous presence, automated extraction and fitting can become challenging if performed "in-the-wild", when the number of primitives is unknown or the point cloud is noisy and not oriented.In this paper we pose the problem of extracting multiple cylinders in a scene by means of a Game-Theoretic inlier selection process exploiting the geometrical relations between pairs of axis candidates. First, we formulate the similarity between two possible cylinders considering the rigid motion aligning the two axes to the same line. This motion is represented with a unitary dual-quaternion so that the distance between two cylinders is induced by the length of the shortest geodesic path in SE(3). Then, a Game-Theoretical process exploits such similarity function to extract sets of primitives maximizing their inner mutual consensus. The outcome of the evolutionary process consists in a probability distribution over the sets of candidates (ie axes), which in turn is used to directly estimate the final cylinder parameters. An extensive experimental section shows that the proposed algorithm offers a high resilience to noise, since the process inherently discards inconsistent data. Compared to other methods, it does not need point normals and does not require a fine tuning of multiple parameters.

show abstract

Section: Real-world Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Cylinders extraction in non-oriented point clouds as a clustering problem

Bergamasco

Pistellato

Albarelli

et al. 2020

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…However, this is a challenging task due to the lack of depth information in 2D images. To overcome this difficulty, some literature have presented typical solutions by assuming that the RGB-D image [1] or the multi-view image [2,3] is available. Benefited from these supplementary data, many works have made impressive progress over the past years.…”

Section: Introductionmentioning

confidence: 99%

Joint Representation of Multiple Geometric Priors via a Shape Decomposition Model for Single Monocular 3D Pose Estimation

Jiang,

Yu,

et al. 2019

Preprint

View full text Add to dashboard Cite

In this paper, we aim to recover the 3D human pose from 2D body joints of a single image. The major challenge in this task is the depth ambiguity since different 3D poses may produce similar 2D poses. Although many recent advances in this problem are found in both unsupervised and supervised learning approaches, the performances of most of these approaches are greatly affected by insufficient diversities and richness of training data. To alleviate this issue, we propose an unsupervised learning approach, which is capable of estimating various complex poses well under limited available training data. Specifically, we propose a Shape Decomposition Model (SDM) in which a 3D pose is considered as the superposition of two parts which are global structure together with some deformations. Based on SDM, we estimate these two parts explicitly by solving two sets of different distributed combination coefficients of geometric priors. In addition, to obtain geometric priors, a joint dictionary learning algorithm is proposed to extract both coarse and fine pose clues simultaneously from limited training data. Quantitative evaluations on several widely used datasets demonstrate that our approach yields better performances over other competitive approaches. Especially, on some categories with more complex deformations, significant improvements are achieved by our approach.Furthermore, qualitative experiments conducted on in-the-wild images also show the effectiveness of the proposed approach.

show abstract