Simulation Method of Virtual Human Pose Optimization Based On VR Peripherals

doi:10.16182/j.issn1004731x.joss.21-0022

Abstract

Abstract:

The commonly used VR peripheral is the position tracker worn on the operator body and is not very convenient. Focus on the problem, a visual sensor combination-based scheme is proposed to realize the simple and real-time unmarked virtual human driven simulation. On the basis of the parameterized human model SMPL, by minimizing the objective function of multiple error terms, the driven accuracy of the virtual human is improved, and the fitted human body model conforming to the operator form and posture is calculated and the ergonomic evaluation is realized. The module is verified by a case of evaluation in a ship cabin. The result shows that the proposed method is available.

Key words: virtual human, parameterized human model, ergonomic evaluation, azure kinect

CLC Number:

TP391.9

Muqing Wang, Lei Zhang, Xiumin Fan, Xiaomeng Luo, Wenmin Zhu. Simulation Method of Virtual Human Pose Optimization Based On VR Peripherals[J]. Journal of System Simulation, 2022, 34(6): 1296-1303.

Figures/Tables 16

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 1

Fig. 8

Fig. 9

Table 2

Table 3

Fig. 10

Table 4

Fig. 11

Table 5

References 14

1	Fernández R P, Alonso V. Virtual Reality in a Shipbuilding Environment[J]. Advances in Engineering Software(S0965-9978), 2015, 81(3): 30-40.
2	蔡乾亚, 单小芬, 曾贞贞, 等. 船舶复杂建造工艺人机工程仿真评价方法[J]. 船舶与海洋工程, 2018, 34(6): 46-51.
	Cai Qianya, Shan Xiaofen, Zeng Zhenzhen, et al. Evaluation Method for Ergonomics Simulation of Complex Ship Building Process[J]. Naval Architecture and Ocean Engineering, 2018, 34(6): 46-51.
3	李石磊, 梁加红, 吴冰, 等. 虚拟人运动生成与控制技术综述[J]. 系统仿真学报, 2011, 23(9): 1758-1771.
	Li Shilei, Liang Jiahong, Wu Bing, et al. Survey of Virtual Character Motion Generation and Control[J]. Journal of System Simulation, 2011, 23(9): 1758-1771.
4	邱世广, 武殿梁, 范秀敏, 等. 基于船舶人机工程的虚拟人操作驱动建模仿真技术[J]. 上海交通大学学报, 2012, 46(9): 1366-1370.
	Qiu Shiguang, Wu Dianliang, Fan Xiumin, et al. Ship Ergonomics Evaluation Based on Virtual Human Real-Time Driven Modeling Technology[J]. Journal of Shanghai Jiaotong University, 2012, 46(9): 1366-1370.
5	郭庆, 萨路, 黄一峰, 等. 沉浸式维修性虚拟验证平台开发与应用[J]. 实验室研究与探索, 2017, 36(9): 92-96, 122.
	Guo Qing, Lu Sa, Huang Yifeng, et al. Research and Development of Immersion Virtual Reality Maintainability Verification Platform[J]. Research and Exploration in Laboratory, 2017, 36(9): 92-96, 122.
6	Zhu W, Fan X, Zhang Y. Applications and Research Trends of Digital Human Models in the Manufacturing Industry[J]. Virtual Reality & Intelligent Hardware (S2096-5796), 2019(6): 558-579.
7	Loper M, Mahmood N, Romero J, et al. SMPL: A Skinned Multi-Person Linear Model[J]. Acm Transactions on Graphics(S0730-0301), 2015, 34(6): 248.
8	Bogo F, Kanazawa A, Lassner C, et al. Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image[C]// The 14th European Conference on Computer Vision. Amsterdam, Holland: Springer International Publishing, 2016: 561-578.
9	瞿师, 冯晓萌, 于荣欢, 等. 一种人体运动重定向方法[J]. 计算机应用研究, 2012, 29(4): 1353-1355.
	Qu Shi, Feng Xiaomeng, Yu Ronghuan, et al. Retargeting for Human Motion[J]. Application Research of Computers, 2012, 29(4): 1353-1355.
10	黎子聪, 曾繁忠, 吴自辉, 等. 虚拟乒乓球手的强化学习训练方法[J]. 计算机辅助设计与图形学学报, 2020, 32(6): 997-1008.
	Li Zicong, Zeng Fanzhong, Wu Zihui, et al. Training a Virtual Tabletennis Player Based on Reinforcement Learning [J]. Journal of Computer-Aided Design and Computer Graphics, 2020, 32(6): 997-1008.
11	Shotton J, Sharp T, Kipman A, et al. Real-Time Human Pose Recognition in Parts from Single Depth Images [J]. Communications of the ACM(S0001-0782), 2013, 56(1): 116-124.
12	Friedman. Classification and Regression Trees[M]//Software Project Effort Estimation. Switzerland: Springer, Cham, 2014: 295-304.
13	蔡青宏. 基于单张深度图的三维人体重建技术研究[D]. 长沙: 湖南大学, 2018.
	Cai Qinghong. Research on 3D Human Reconstruction Technology Based on Single Depth Map[D]. Changsha: Hunan University, 2018.
14	徐博成. 基于Kinect的人体动作损伤评估方法[D]. 青岛: 青岛科技大学, 2017.
	Xu Bocheng. Evaluation Method of Human Body Injury Based on Kinect[D]. Qingdao: Qingdao University of Science and Technology, 2017.

状态	1	2	3	4	5
拟合前	33.4	29.5	27.7	30.8	42.4
拟合后	21.8	18.1	17.1	18.0	16.2

项目	描述	得分	修正
前臂	弯曲60°～100°	1	外展或跨越中线： +1
前臂	弯曲0°～60°或大于100°	2	外展或跨越中线： +1

关节	三维位置/m	局部旋转/(°)
0	(0.047 2, -0.075 5, 2.253 6)	(-2.58, 171.15, -7.76)
1	(0.115 2, -0.162 0, 2.276 2)	(-50.54, -1.03, -7.35)
2	(-0.020 1, -0.167 6, 2.258 5)	(-46.54, 0.07, 14.89)
…
22	(0.349 6, 0.724 6, 1.864 7)	(3.78, 4.04, 6.43)
23	(-0.073 6, 0.695 9, 1.782 3)	(-0.38, -3.80, -2.93)

项目	得分	项目	得分	项目	得分
上肢姿势	5	颈部姿势	4	受力评分	0
前臂姿势	1	躯体姿势	1	C值	5
腕部姿势	1	腿部姿势	1	D值	5
腕部扭转	1	肌肉评分	0	RULA	6

序号	问题	分数(5分制)
1	仿真环境具有真实感	3.67
2	模型姿态与操作者一致	4.33
3	人因评价与实际感受一致	4.50