NDLI: Random tree walk toward instantaneous 3D human pose estimation

Content Provider	IEEE Xplore Digital Library
Author	Ho Yub Jung Soochahn Lee Yong Seok Heo Il Dong Yun
Copyright Year	2015
Description	Author affiliation: Dept. of Electr. Eng., Soonchunghyang U, Asan, South Korea (Soochahn Lee) \|\| Dept. of Electr. & Comp. Eng., Ajou Univ., Suwon, South Korea (Yong Seok Heo) \|\| Div. of Comp. & Electr. Sys. Eng, Hankuk U. of Foreign Studies, Yongin, South Korea (Ho Yub Jung; Il Dong Yun)
Abstract	The availability of accurate depth cameras have made real-time human pose estimation possible; however, there are still demands for faster algorithms on low power processors. This paper introduces 1000 frames per second pose estimation method on a single core CPU. A large computation gain is achieved by random walk sub-sampling. Instead of training trees for pixel-wise classification, a regression tree is trained to estimate the probability distribution to the direction toward the particular joint, relative to the current position. At test time, the direction for the random walk is randomly chosen from a set of representative directions. The new position is found by a constant step toward the direction, and the distribution for next direction is found at the new position. The continual random walk through 3D space will eventually produce an expectation of step positions, which we estimate as the joint position. A regression tree is built separately for each joint. The number of random walk steps can be assigned for each joint so that the computation time is consistent regardless of the size of body segmentation. The experiments show that even with large computation gain, the accuracy is higher or comparable to the state-of-the-art pose estimation methods.
Starting Page	2467
Ending Page	2474
File Size	1220322
Page Count	8
File Format	PDF
ISSN	10636919
e-ISBN	9781467369640
DOI	10.1109/CVPR.2015.7298861
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2015-06-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Tracking Training
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Beyond Physical Connections: Tree Models in Human Pose Estimation

Learning descriptors for object recognition and 3D pose estimation

Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation

Human Pose Estimation Using Body Parts Dependent Joint Regressors

Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation

Alternating Regression Forests for Object Detection and Pose Estimation

2D-3D Pose Consistency-based Conditional Random Fields for 3D Human Pose Estimation

Random tree walk toward instantaneous 3D human pose estimation

Similar Documents

Beyond Physical Connections: Tree Models in Human Pose Estimation

Learning descriptors for object recognition and 3D pose estimation

Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation

Human Pose Estimation Using Body Parts Dependent Joint Regressors

Computationally Efficient Regression on a Dependency Graph for Human Pose Estimation

Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest

Loose-limbed People: Estimating 3D Human Pose and Motion Using Non-parametric Belief Propagation

Alternating Regression Forests for Object Detection and Pose Estimation

2D-3D Pose Consistency-based Conditional Random Fields for 3D Human Pose Estimation

Random tree walk toward instantaneous 3D human pose estimation