Centimeter human skeleton pose estimation
Abstract
A method, apparatus and system for human skeleton pose estimation includes synchronously capturing images of a human moving through an area from a plurality of different points of view, for each of the plurality of captured images, determining a bounding box that bounds the human in the captured image and identifying pixel locations of the bounding box in the image, for each of the plurality of captured images, determining 2D and single-view 3D skeletons from the pixel locations of the bounding box, determining a first, multi-view 3D skeleton using a combination of the 2D and single-view 3D skeletons, and optimizing the first, multi-view 3D skeleton to determine a final 3D skeleton pose for the human. The method, apparatus and system can further include illuminating the area with structured light during the capturing of the images of the human moving through the area.
- Inventors:
- Issue Date:
- Research Org.:
- Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); SRI International, Menlo Park, CA (United States)
- Sponsoring Org.:
- USDOE
- OSTI Identifier:
- 1892667
- Patent Number(s):
- 11263443
- Application Number:
- 16/868,870
- Assignee:
- SRI International (Menlo Park, CA)
- Patent Classifications (CPCs):
-
G - PHYSICS G06 - COMPUTING G06N - COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
G - PHYSICS G06 - COMPUTING G06T - IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- DOE Contract Number:
- AC05-76RL01830
- Resource Type:
- Patent
- Resource Relation:
- Patent File Date: 05/07/2020
- Country of Publication:
- United States
- Language:
- English
Citation Formats
Brookshire, Jonathan D., Samarasekera, Supun, and Minhas, Kshitij Singh. Centimeter human skeleton pose estimation. United States: N. p., 2022.
Web.
Brookshire, Jonathan D., Samarasekera, Supun, & Minhas, Kshitij Singh. Centimeter human skeleton pose estimation. United States.
Brookshire, Jonathan D., Samarasekera, Supun, and Minhas, Kshitij Singh. Tue .
"Centimeter human skeleton pose estimation". United States. https://www.osti.gov/servlets/purl/1892667.
@article{osti_1892667,
title = {Centimeter human skeleton pose estimation},
author = {Brookshire, Jonathan D. and Samarasekera, Supun and Minhas, Kshitij Singh},
abstractNote = {A method, apparatus and system for human skeleton pose estimation includes synchronously capturing images of a human moving through an area from a plurality of different points of view, for each of the plurality of captured images, determining a bounding box that bounds the human in the captured image and identifying pixel locations of the bounding box in the image, for each of the plurality of captured images, determining 2D and single-view 3D skeletons from the pixel locations of the bounding box, determining a first, multi-view 3D skeleton using a combination of the 2D and single-view 3D skeletons, and optimizing the first, multi-view 3D skeleton to determine a final 3D skeleton pose for the human. The method, apparatus and system can further include illuminating the area with structured light during the capturing of the images of the human moving through the area.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2022},
month = {3}
}
Works referenced in this record:
Method and system for 3D hand skeleton tracking
patent-application, January 2018
- Mao, Wentao; Zhang, Xu; Ma, Gengyu
- US Patent Application 15/649716; 20180024641
Apparatus and method for generating skeleton model using motion data and image data
patent-application, September 2010
- Kim, Chang Yeong; Bang, Won Chul; Kim, Do Kyoon
- US Patent Application 12/539170; 20100238168