Characterizing Vehicle Occupant Body Dimensions and Postures Using a Statistical Body Shape Model

Byoung Keon Daniel Park, Matthew P. Reed

Research output: Contribution to journalArticle

Abstract

Reliable, accurate data on vehicle occupant characteristics could be used to personalize the occupant experience, potentially improving both satisfaction and safety. Recent improvements in 3D camera technology and increased use of cameras in vehicles offer the capability to effectively capture data on vehicle occupant characteristics, including size, shape, posture, and position. In previous work, the body dimensions of standing individuals were reliably estimated by fitting a statistical body shape model (SBSM) to data from a consumer-grade depth camera (Microsoft Kinect). In the current study, the methodology was extended to consider seated vehicle occupants. The SBSM used in this work was developed using laser scan data gathered from 147 children with stature ranging from 100 to 160 cm and BMI from 12 to 27 kg/m2 in various sitting postures. A principal component (PC) analysis was conducted based on these scans along with the manually-measured body landmarks, and 100 PC scores were retained to account for 99% of variance in the body shape and sitting postures. A PC-based fast fitting method was applied to estimate the occupant characteristics by fitting the SBSM to an incomplete depth image of a subject. The results demonstrate that a fast, inexpensive system can be used to produce useful estimates of occupant characteristics that could be applied to improve personalization of component adjustments, restraint systems, and infotainment systems.

Original languageEnglish (US)
JournalSAE Technical Papers
Volume2017-March
Issue numberMarch
DOIs
StatePublished - Mar 28 2017

Fingerprint

Cameras
Principal component analysis
Data acquisition
Lasers

ASJC Scopus subject areas

  • Automotive Engineering
  • Safety, Risk, Reliability and Quality
  • Pollution
  • Industrial and Manufacturing Engineering

Cite this

Characterizing Vehicle Occupant Body Dimensions and Postures Using a Statistical Body Shape Model. / Park, Byoung Keon Daniel; Reed, Matthew P.

In: SAE Technical Papers, Vol. 2017-March, No. March, 28.03.2017.

Research output: Contribution to journalArticle

Park, Byoung Keon Daniel; Reed, Matthew P. / Characterizing Vehicle Occupant Body Dimensions and Postures Using a Statistical Body Shape Model.

In: SAE Technical Papers, Vol. 2017-March, No. March, 28.03.2017.

Research output: Contribution to journalArticle

@article{2f468c6c76114baa98184b4950ec492d,
title = "Characterizing Vehicle Occupant Body Dimensions and Postures Using a Statistical Body Shape Model",
abstract = "Reliable, accurate data on vehicle occupant characteristics could be used to personalize the occupant experience, potentially improving both satisfaction and safety. Recent improvements in 3D camera technology and increased use of cameras in vehicles offer the capability to effectively capture data on vehicle occupant characteristics, including size, shape, posture, and position. In previous work, the body dimensions of standing individuals were reliably estimated by fitting a statistical body shape model (SBSM) to data from a consumer-grade depth camera (Microsoft Kinect). In the current study, the methodology was extended to consider seated vehicle occupants. The SBSM used in this work was developed using laser scan data gathered from 147 children with stature ranging from 100 to 160 cm and BMI from 12 to 27 kg/m2 in various sitting postures. A principal component (PC) analysis was conducted based on these scans along with the manually-measured body landmarks, and 100 PC scores were retained to account for 99% of variance in the body shape and sitting postures. A PC-based fast fitting method was applied to estimate the occupant characteristics by fitting the SBSM to an incomplete depth image of a subject. The results demonstrate that a fast, inexpensive system can be used to produce useful estimates of occupant characteristics that could be applied to improve personalization of component adjustments, restraint systems, and infotainment systems.",
author = "Park, {Byoung Keon Daniel} and Reed, {Matthew P.}",
year = "2017",
month = "3",
doi = "10.4271/2017-01-0497",
volume = "2017-March",
journal = "SAE Technical Papers",
issn = "0148-7191",
publisher = "SAE International",
number = "March",

}

TY - JOUR

T1 - Characterizing Vehicle Occupant Body Dimensions and Postures Using a Statistical Body Shape Model

AU - Park,Byoung Keon Daniel

AU - Reed,Matthew P.

PY - 2017/3/28

Y1 - 2017/3/28

N2 - Reliable, accurate data on vehicle occupant characteristics could be used to personalize the occupant experience, potentially improving both satisfaction and safety. Recent improvements in 3D camera technology and increased use of cameras in vehicles offer the capability to effectively capture data on vehicle occupant characteristics, including size, shape, posture, and position. In previous work, the body dimensions of standing individuals were reliably estimated by fitting a statistical body shape model (SBSM) to data from a consumer-grade depth camera (Microsoft Kinect). In the current study, the methodology was extended to consider seated vehicle occupants. The SBSM used in this work was developed using laser scan data gathered from 147 children with stature ranging from 100 to 160 cm and BMI from 12 to 27 kg/m2 in various sitting postures. A principal component (PC) analysis was conducted based on these scans along with the manually-measured body landmarks, and 100 PC scores were retained to account for 99% of variance in the body shape and sitting postures. A PC-based fast fitting method was applied to estimate the occupant characteristics by fitting the SBSM to an incomplete depth image of a subject. The results demonstrate that a fast, inexpensive system can be used to produce useful estimates of occupant characteristics that could be applied to improve personalization of component adjustments, restraint systems, and infotainment systems.

AB - Reliable, accurate data on vehicle occupant characteristics could be used to personalize the occupant experience, potentially improving both satisfaction and safety. Recent improvements in 3D camera technology and increased use of cameras in vehicles offer the capability to effectively capture data on vehicle occupant characteristics, including size, shape, posture, and position. In previous work, the body dimensions of standing individuals were reliably estimated by fitting a statistical body shape model (SBSM) to data from a consumer-grade depth camera (Microsoft Kinect). In the current study, the methodology was extended to consider seated vehicle occupants. The SBSM used in this work was developed using laser scan data gathered from 147 children with stature ranging from 100 to 160 cm and BMI from 12 to 27 kg/m2 in various sitting postures. A principal component (PC) analysis was conducted based on these scans along with the manually-measured body landmarks, and 100 PC scores were retained to account for 99% of variance in the body shape and sitting postures. A PC-based fast fitting method was applied to estimate the occupant characteristics by fitting the SBSM to an incomplete depth image of a subject. The results demonstrate that a fast, inexpensive system can be used to produce useful estimates of occupant characteristics that could be applied to improve personalization of component adjustments, restraint systems, and infotainment systems.

UR - http://www.scopus.com/inward/record.url?scp=85018446040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85018446040&partnerID=8YFLogxK

U2 - 10.4271/2017-01-0497

DO - 10.4271/2017-01-0497

M3 - Article

VL - 2017-March

JO - SAE Technical Papers

T2 - SAE Technical Papers

JF - SAE Technical Papers

SN - 0148-7191

IS - March

ER -