基于多传感器的警犬姿态实时重建与仿真

doi:10.16182/j.issn1004731x.joss.201812031

系统仿真学报 ›› 2018, Vol. 30 ›› Issue (12): 4738-4746.doi: 10.16182/j.issn1004731x.joss.201812031

基于多传感器的警犬姿态实时重建与仿真

祝朝政¹, 何明^1,2,*, 杨晟^3,4, 杨铖¹, 宋珍华⁵

1. 中国人民解放军陆军工程大学指挥控制工程学院, 江苏南京 211117;
2. 军事科学院系统工程网络信息研究所,北京 100071;
3. 河海大学计算机与信息学院,南京 211100;
4. 南京荟英电子科技有限公司, 南京 211100;
5. 公安部南京警犬研究所,南京 210012

收稿日期:2018-04-10 修回日期:2018-05-23 出版日期:2018-12-10 发布日期:2019-01-03
通讯作者: 何明(1978-),男,新疆石河子,博士,教授,研究方向为大数据,人工智能。
作者简介:祝朝政(1995-),男,河南信阳,硕士生,研究方向为机器视觉,嵌入式系统。
基金资助:
国家重点研发计划(2016YFC0800310)

Real-time Reconstruction and Simulation of Police Dog Posture Based on Multi-sensor Data Vest

Zhu Chaozheng¹, He Ming^1,2,*, Yang Sheng^3,4, Yang Cheng¹, Song Zhenhua⁵

1. College of Command Control Engineer, Army Engineering University, Nanjing 211117, China;
2. Institute of Network Information, Academy of Systems Engineering, Academy of Military Sciences, Beijing 100071, China;
3. College of Information and Computer, HoHai University, Nanjing 211110, China;
4. Nanjing Huiying Electronics Technology Corporation, Nanjing 211100, China;
5. Nanjing Police Dog Research Institute, Ministry of Public Security, Nanjing 210012, China

Received:2018-04-10 Revised:2018-05-23 Online:2018-12-10 Published:2019-01-03

摘要/Abstract

摘要： 实时警犬姿态重建能为警方带犬执勤提供了一种智能、便捷、超视距的交互方式。针对警犬的生物运动特性,设计实现了全新的多传感器警犬数据背心;基于多个体积小、功耗低传感器,构建了新的警犬运动姿态融合方法,可以捕获警犬的不同姿态数据,包括站姿、坐姿、卧姿等;针对警犬频繁抖动问题,提出了基于多传感器数据背心的警犬姿态重建方法,引入一种改进的核函数ELM (Extreme Learning Machines)算法,求解最优重建姿态结果。通过分析和对比实验仿真,表明本方法能够实时重建出真实可信的警犬姿态。

关键词: 姿态重建, 运动捕获, 警犬, 基于核函数的ELM算法

Abstract: Real-time police dog posture reconstruction provides an intelligent, convenient and over-the-horizon interactive way for police on duty with dogs. For the biological movement characteristics of police dogs, a new multi-sensor dog data vest was designed and implemented. Based on multiple small size and low power consumption sensors, a new police dog motion fusion method was proposed to capture the different posture data of police dogs, including standing, sitting and prone position, etc. For frequent jitter of police dogs, this paper proposed a method of dog posture reconstruction based on multi-sensor data vest, and introduced an improved kernel function ELM algorithm to solve the optimal reconstruction posture results. The analysis and comparison of experimental simulation show that this method can reconstruct the real and credible police dog posture in real time.

Key words: posture reconstruction, motion capture, police dog, the ELM algorithm based on kernel function

中图分类号:

TP391.9

祝朝政, 何明, 杨晟, 杨铖, 宋珍华. 基于多传感器的警犬姿态实时重建与仿真[J]. 系统仿真学报, 2018, 30(12): 4738-4746.

Zhu Chaozheng, He Ming, Yang Sheng, Yang Cheng, Song Zhenhua. Real-time Reconstruction and Simulation of Police Dog Posture Based on Multi-sensor Data Vest[J]. Journal of System Simulation, 2018, 30(12): 4738-4746.

参考文献

[1] 孙勇, 宋天童. 大型安保勤务中警犬安检技术团队组建模式探析[J]. 中国人民公安大学学报(自然科学版). 2017, 23(1): 55-59.
Sun Yong, Song Tiantong.Analysis of the formation model of police dog inspection technical team in large-scale security service[J]. Journal of People's Public Security University of China (Sicience and Technology), 2017, 23(1): 55-59
[2] Cao Z, Simon T, Wei S E, et al.Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields[J]//IEEE Conference on Computer Vision and Pattern Recognition. IEEE Computer Society, 2016: 1302-1310.
[3] Simon T, Joo H, Matthews I, et al.Hand Keypoint Detection in Single Images using Multiview Bootstrapping[J]//IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4645-4653.
[4] Wei S E, Ramakrishna V, Kanade T, et al.Convolutional Pose Machines[C]// Computer Vision and Pattern Recognition, 2016: 33-47.
[5] Chen X, Yuille A L.Articulated pose estimation by a graphical model with image dependent pairwise relations[C]//Advances in neural information processing systems. 2014: 1736-1744.
[6] Insafutdinov E, Pishchulin L, Andres B, et al.DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model[C]//. European Conference on Computer Vision, 2016: 34-50.
[7] Othmezouri G, Sakata I, Schiele B, et al.Monocular 3D pose estimation and tracking by detection[Z]. IEEE, 2015: 623-630.
[8] Fang B, Sun F, Liu H, et al.3D human gesture capturing and recognition by the IMMU-based data glove[J]. Neurocomputing, 2018, 277: 198-207.
[9] Xu Y, Wang Y, Su Y, et al.Research on the Calibration Method of Micro Inertial Measurement Unit for Engineering Application[J]. Journal of Sensors, 2016(1): 1-11.
[10] Lambrecht J M, Kirsch R F.Miniature low-power inertial sensors: promising technology for implantable motion capture systems[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2014, 22(6): 1138-1147.
[11] Ahmed H, Tahir M.Improving the Accuracy of Human Body Orientation Estimation With Wearable IMU Sensors[J]. IEEE Transactions on Instrumentation & Measurement , 2017(99): 1-8.
[12] Maeda Y, Terao K, Shimokawa F, et al.Reduction of contact force dependence on the MEMS hardness sensor using reference plane to detect human body hardness[C]// Sensors. IEEE, 2016: 1-4.
[13] Dranitsyna E V.IMU calibration using sins navigation solution: Selection of the rate table motion scenario[C]// Saint Petersburg International Conference on Integrated Navigation Systems, 2017: 1-5.
[14] Tompson J, Goroshin R, Jain A, et al.Efficient object localization using convolutional networks[C] //Proce edings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 648-656.
[15] Belagiannis V, Zisserman A, editors. Recurrent Human Pose Estimation[C]// IEEE International Conference on Automatic Face & Gesture Recognition, 2017: 468-475.
[16] Lecun Y, Bengio Y, Hinton G.Deep learning[J]. Nature, 2015, 521(7553): 436.
[17] Abadi M, Agarwal A, Barham P, et al.TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems[J]. 2016.
[18] Ivanov A V, Zhilenkov A A.The use of IMU MEMS-sensors for designing of motion capture system for control of robotic objects[C]// IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering. IEEE, 2018: 890-893.
[19] Paden B E.Lower Bounds on the Frequency Estimation Error in Magnetically Coupled MEMS Resonant Sensors[J]. IEEE Transactions on Biomedical Circuits & Systems, 2016, 10(1): 18-24.

基于多传感器的警犬姿态实时重建与仿真

Real-time Reconstruction and Simulation of Police Dog Posture Based on Multi-sensor Data Vest

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	何鹏, 胡少军, 何东健. 基于Kinect的树运动轨迹获取与振动频率分析[J]. 系统仿真学报, 2017, 29(7): 1411-1418.
[2]	崔丽君, 黄天羽, 冯枫, 张杰, 杨凯, 刘陈. 基于少量惯性传感器的姿态重建与仿真[J]. 系统仿真学报, 2017, 29(10): 2261-2267.