Limits...
Articulated Non-Rigid Point Set Registration for Human Pose Estimation from 3D Sensors.

Ge S, Fan G - Sensors (Basel) (2015)

Bottom Line: We introduce a visible point extraction method to initialize a new template for the current frame from the previous frame, which effectively reduces the ambiguity and uncertainty during registration.Third, to support robust and stable pose tracking, we develop a segment volume validation technique to detect tracking failures and to re-initialize pose registration if needed.The experimental results on both benchmark 3D laser scan and depth datasets demonstrate the effectiveness of the proposed framework when compared with state-of-the-art algorithms.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USA. song.ge@okstate.edu.

ABSTRACT
We propose a generative framework for 3D human pose estimation that is able to operate on both individual point sets and sequential depth data. We formulate human pose estimation as a point set registration problem, where we propose three new approaches to address several major technical challenges in this research. First, we integrate two registration techniques that have a complementary nature to cope with non-rigid and articulated deformations of the human body under a variety of poses. This unique combination allows us to handle point sets of complex body motion and large pose variation without any initial conditions, as required by most existing approaches. Second, we introduce an efficient pose tracking strategy to deal with sequential depth data, where the major challenge is the incomplete data due to self-occlusions and view changes. We introduce a visible point extraction method to initialize a new template for the current frame from the previous frame, which effectively reduces the ambiguity and uncertainty during registration. Third, to support robust and stable pose tracking, we develop a segment volume validation technique to detect tracking failures and to re-initialize pose registration if needed. The experimental results on both benchmark 3D laser scan and depth datasets demonstrate the effectiveness of the proposed framework when compared with state-of-the-art algorithms.

No MeSH data available.


Illustration of two metrics used for segment volume validation.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541828&req=5

f5-sensors-15-15218: Illustration of two metrics used for segment volume validation.

Mentions: Segment overlapping metric (M1): This metric checks the overlapping ratios between every two body segments represented by OBBs in a labeled point set X̂ of P segments, as defined below:(8)M1(Si)=maxj≠iV(B(Si)∩B(Sj))V(B(Si))where Si and Sj (i, j = 1, …, P) denote two body segments in X̂, B(Si) represents the OBB of Si and V(·) is the volume of an OBB (i.e., the total number of points). We compute M1 (Si, Sj) by calculating the percentage of the points, which belong to both Si and Sj, over the total number of points in Si. A large value of M1(Si) implies a significant overlap between Si and other segments, indicating inaccurate correspondence estimation (Figure 5a).


Articulated Non-Rigid Point Set Registration for Human Pose Estimation from 3D Sensors.

Ge S, Fan G - Sensors (Basel) (2015)

Illustration of two metrics used for segment volume validation.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541828&req=5

f5-sensors-15-15218: Illustration of two metrics used for segment volume validation.
Mentions: Segment overlapping metric (M1): This metric checks the overlapping ratios between every two body segments represented by OBBs in a labeled point set X̂ of P segments, as defined below:(8)M1(Si)=maxj≠iV(B(Si)∩B(Sj))V(B(Si))where Si and Sj (i, j = 1, …, P) denote two body segments in X̂, B(Si) represents the OBB of Si and V(·) is the volume of an OBB (i.e., the total number of points). We compute M1 (Si, Sj) by calculating the percentage of the points, which belong to both Si and Sj, over the total number of points in Si. A large value of M1(Si) implies a significant overlap between Si and other segments, indicating inaccurate correspondence estimation (Figure 5a).

Bottom Line: We introduce a visible point extraction method to initialize a new template for the current frame from the previous frame, which effectively reduces the ambiguity and uncertainty during registration.Third, to support robust and stable pose tracking, we develop a segment volume validation technique to detect tracking failures and to re-initialize pose registration if needed.The experimental results on both benchmark 3D laser scan and depth datasets demonstrate the effectiveness of the proposed framework when compared with state-of-the-art algorithms.

View Article: PubMed Central - PubMed

Affiliation: School of Electrical and Computer Engineering, Oklahoma State University, Stillwater, OK 74078, USA. song.ge@okstate.edu.

ABSTRACT
We propose a generative framework for 3D human pose estimation that is able to operate on both individual point sets and sequential depth data. We formulate human pose estimation as a point set registration problem, where we propose three new approaches to address several major technical challenges in this research. First, we integrate two registration techniques that have a complementary nature to cope with non-rigid and articulated deformations of the human body under a variety of poses. This unique combination allows us to handle point sets of complex body motion and large pose variation without any initial conditions, as required by most existing approaches. Second, we introduce an efficient pose tracking strategy to deal with sequential depth data, where the major challenge is the incomplete data due to self-occlusions and view changes. We introduce a visible point extraction method to initialize a new template for the current frame from the previous frame, which effectively reduces the ambiguity and uncertainty during registration. Third, to support robust and stable pose tracking, we develop a segment volume validation technique to detect tracking failures and to re-initialize pose registration if needed. The experimental results on both benchmark 3D laser scan and depth datasets demonstrate the effectiveness of the proposed framework when compared with state-of-the-art algorithms.

No MeSH data available.