The driver’s whole-body posture at the time of a collision is a key factor in determining the magnitude of injury to the driver. However, current researchs on driver posture models only consider the upper body posture of the driver, and the lower body area which is not perceived by sensors is not studied. This paper investigates the driver’s posture and establishes a 3D posture model of the driver’s whole body through the application of machine vision algorithms and regression model statistics. This study proposes an improved Kinect-OpenPose algorithm for identifying the 3D spatial coordinates of nine keypoints of the driver’s upper body. The posture prediction regression model of four keypoints of the lower body is established by conducting volunteer posture acquisition experiments on the developed simulated driving seat and analyzing the volunteer posture data through using the principal components of the upper body keypoints and the seat parameters. The experiments proved that the error of the regression model in this paper is minor than that of current studies, and the accuracy of the keypoint location and the keypoint connection length of the established driver whole body posture model is high, which provides implications for future studies.
DingusTAKlauerSGNealeVL, et al. The 100-car naturalistic driving study, phase II- results of the 100-car field experiment. Blacksburg, VA: NHTSA, 2006.
2.
RooijLV. Effect of various pre-crash braking strategies on simulated human kinematic response with varying levels of driver attention. In: Proceedings of the 22nd international technical conference on the enhanced safety of vehicles (ESV), Washington, DC, 2011, pp.1–9.
3.
Hault-DubrulleARobacheFDelilleR, et al. Influence of pre-crash driver posture on injury outcome: airbag interaction with human upper extremities. Comput Methods Biomech Biomed Eng2012; 15(S1): 295–297.
4.
AkamatsuMGreenPBenglerK. Automotive technology and human factors research: past, present, and future. Int J Vehicular Technol2013; 2013: 1–27.
5.
ReedMPManaryMAFlannaganCAC, et al. A statistical method for predicting automobile driving posture. Human Factors2002; 44(4): 557–568.
6.
ParkJEbertSMReedMP, et al. Statistical models for predicting automobile driving postures for men and women including effects of age. Human Factors2016; 58(2): 261–278.
7.
ParkJEbertSMReedMP, et al. A statistical model including age to predict passenger postures in the rear seats of automobiles. Ergonomics2016; 59: 796–805.
8.
LinderAOlsénSErikssonJ, et al. Influence of gender, height, weight, age, seated position and collision site related to neck pain symptoms in rear end impacts. In: Proceedings: IRCOBI conference, Dublin, Ireland, 12–14 November 2012, pp.12–14.
9.
HuJZhangKFantaA, et al. Stature and body shape effects on driver injury risks in frontal crashes: a parametric human modelling study. In: IRCOBI, conference proceedings, Antwerp, Belgium, 13–15 November 2017, pp.13–15.
10.
VianoDCArepallyS. Assessing the safety performance of occupant restraint system. SAE technical paper902328, 1990.
11.
ShiaVAGaoYVasudevanR, et al. Semiautonomous vehicular control using driver modeling. IEEE Trans Intell Transp Syst2014; 15(6): 2696–2709.
12.
AminIJTaylorAJParkinRM. Driver tracking and posture detection using low-resolution infrared sensing. Proc IMechE, Part D: J Automobile Engineering2007; 221(9): 1079–1088.
13.
TranCTrivediMM. Towards a vision-based system exploring 3D driver posture dynamics for driver assistance: issues and possibilities. In: Intelligent vehicles symposium (IV), La Jolla, CA, 2010. IEEE.
14.
TomaMIRothkrantzL J MAntonyaC. Car driver skills assessment based on driving postures recognition. In: 2012 IEEE 3rd international conference on cognitive infocommunications (CogInfoCom), Kosice, Slovakia, 2012, pp.439–446. IEEE.
15.
XingYLvCZhangZ, et al. Identification and analysis of driver postures for In-vehicle driving activities and secondary tasks recognition. IEEE Trans Comput Soc Syst2018; 5(1): 95–108.
16.
ParkBJonesMMillerC, et al. In-vehicle occupant head tracking using a low-cost depth camera. In: WCX world congress experience, Detroit, michigan, 2018.
17.
ParkBK.D.EbertS.MillerC.ReedM.P. (2021) Robust markerless 3D head tracking of a vehicle occupant using openpose. In: CassentiD.ScatagliniS.RajuluS.WrightJ. (eds) Advances in simulation and digital human modeling. AHFE 2020. Advances in Intelligent Systems and Computing, vol 1206. Springer, Cham.
18.
ComaniciuDMeerP. Mean shift: a robust approach toward feature space analysis. IEEE Trans PAMI2002; 24(5): 603–619.
19.
ShottonJSharpTKipmanA, et al. Real-Time human pose recognition in parts from single depth images. Commun ACM2013; 56(1): 116–124.
20.
ShottonJGirshickRFitzgibbonA, et al. Efficient human pose estimation from single depth images. IEEE Trans Pattern Anal Mach Intell2013; 35(12): 2821–2840.
21.
XuXMcGorryRW. The validity of the first and second generation Microsoft kinect™ for identifying joint center locations during static postures. Appl Ergon2015; 49: 47–54.
22.
PlantardPAuvinetEPierresAS, et al. Pose estimation with a kinect for ergonomic studies: evaluation of the accuracy using a virtual mannequin. Sensors2015; 15(1): 1785–1803.
23.
CaoZHidalgoGSimonT, et al. OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell2021; 43(1): 172–186.
24.
ZhangZ. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell2000; 22(11): 1330–1334.
25.
AndreoniGSantambrogioGCRabuffettiM, et al. Method for the analysis of posture and interface pressure of car drivers. Appl Ergon2002; 33(6): 511–522.
26.
RienerAFerschaA. Driver activity recognition from sitting postures. In: Paul-StueveT (ed.) Mensch & Computer 2007 Workshopband. Weimar: Verlag der Bauhaus-Universität Weimar, 2007, pp. 55–62.
27.
RienerAFerschaA. Supporting implicit human-to-vehicle interaction: driver identification from sitting postures. In: The first annual international symposium on vehicular computing systems (ISVCS 2008), Dublin, Ireland, 2008.
28.
InagakiT. Smart collaboration between humans and machines based on mutual understanding. Annu Rev Control2008; 32(2): 253–261.
29.
KlarinMMSpasojević-BrkićVKStanojevićPD, et al. Anthropometrical limitations in the construction of passenger vehicles: case study. Proc IMechE, Part D: J Automobile Engineering2008; 222(8): 1409–1419.
30.
SenJKanchanTGhoshA, et al. Estimation of stature from lengths of index and ring fingers in a north-eastern Indian population. J Forensic Leg Med2014; 22: 10–15.
31.
BjelicaDMasanovicBJaraniJ, et al. Estimation of stature from arm span in albanian population. In: International scientific conference on transformation process in sport “sport Performance”, Budva, Montenegro, 2018.
