Human posture recognition method based on indoor positioning technology

doi:10.3969/j.issn.0253-2778.2019.10.005

Abstract

Abstract: Solitary elderly person posture recognition, especially when falling down, is a problem of concern today. The traditional method based on machine vision is flawed with too much privacy invasion, high cost and complex factors such as the implementation process, while the method based on acceleration sensor has a lower recognition rate in the stillness of the gesture. This paper introduces a new kind of body posture recognition scheme that employs indoor positioning technologies. The main job is to build an indoor positioning system, and paste tags to the key parts of the clothes and hat. The tags can receive ultra-wideband (UWB) signal from the positioning system. The UWB signal is used to get the distance which is important for the positioning. Finally, body posture can be easily recognized. In gesture recognition algorithm, this paper USES the least squares and the improved extend Kalman filter to suppress the noise of the distances measurement, so as to improve the accuracy of location. The simulation algorithm shows that the improved extend Kalman filter is effective.

Key words: indoor position, posture recognition, elderly monitoring system, wireless body area network, Kalman filter

CLC Number:

HUANG Xiaoping, ZHANG Jian, HU Zelin, LI Miao, ZENG Weihui, LI Hualong. Human posture recognition method based on indoor positioning technology[J]. Journal of University of Science and Technology of China, 2019, 49(10): 805-811.

References

［1］
GONG Shulan, WANG Yuling, ZHANG Mingyu, et al. Design of remote elderly health monitoring system based on MEMS sensors[C]// Electrical Engineering/ Electronics, Computer, Telecommunications and Information Technology. Phuket, Thailand: IEEE, 2017: 27-30
[2] 余家林,孙季丰,李万益.基于多核稀疏编码的三维人体姿态估计[J]. 电子学报, 2016, 44(8): 1899-1908.
YU Jialin, SUN Jifeng, LI Wanyi. 3D human pose estimation based on multi-kernel sparse coding[J]. Acta Electronica Sinica, 2016, 44(8): 1899-1908.
[3] 代钦, 石祥滨, 乔建忠, 等. 结合遮挡级别的人体姿态估计方法[J]. 计算机辅助设计与图形学学报. 2017, 29(2): 279-289.
DAI Qin, SHI Xiangbin, QIAO Jianzhong, et al. Articulated human pose estimation with occlusion level[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(2): 279-289.
[4] KEIN H K, HUNG N K, CHAU M T, et al,Single view image based-3D human pose reconstruction[C]// 9th International Conference on Knowledge and Systems Engineering . Hue, Vietnam: IEEE, 2017: 118-123
[5] FRANCESC M N. 3D human pose estimation from a single image via distance matrix regression[C]// IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, USA: IEEE, 2017: 1561-1570.
[6] HONG Chaoqun, YU Jun, TAO Dacheng, et al. Image-based three-dimensional human pose recovery by multiview locality-sensitive sparse retrieval [J]. IEEE Transactions on Industrial Electronics, 2015, 62(6): 3742 – 3751.
[7] 田国会，尹建芹，韩旭，等. 一种基于关节点信息的人体行为识别新方法[J]. 机器人, 2014, 36(3): 285-292.
TIAN Guohui, YIN Jianqin, HAN Xu, et al. A novel human activity, recognition method using joint points[J]. Robot,2014, 36(3): 285-292.
[8] SOMBANDITH V, WALAIRACHT A, WALAIRACHT S. Recognition of Lao sentence sign language using Kinect sensor[C]// 14th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology. Phuket, Thailand: IEEE, 2017: 656-659.
[9] TRIPATHY S R, CHAKRAVARTY K, SINHA A, et al. Constrained Kalman filter for improving Kinect based measurements[C] // International Symposium on Circuits and Systems. Baltimore, USA: IEEE, 2017: 1-4.
[10] PIERLEONI P, BELLI A, MAURIZI L, et al. A wearable fall detector for elderly people based on AHRS and barometric sensor[J]. IEEE Sensors Journal, 2016, 16 (17): 6733-6744
[11] 李文锋,王隆进,姚道金,等. 基于运动特征分析的人体异常行为模糊识别[J].华中科技大学学报,2014, 42(7): 87-91.
LI Wenfeng，WANG Longjin, YAO Daojin, et al. Fuzzy recognition of abnormal body behaviors based on motion feature analysis[J]. Journal of Huazhong University of Science and Technology, 2014, 42(7): 87-91.
[12] 朱庄生,张雨龙,李驰. 基于MEMS惯性测量单元的多源信息自适应步数检测方法[J].中国惯性技术学报, 2017, 25(3): 299-303.
ZHU Zhuangsheng, ZHANG Yulong, LI Chi. Multi-source information adaptive step detection method based on MEMS inertial measurement unit[J]. Journal of Chinese Inertial Technology, 2017, 25(3)299-303.
[13] 路永乐,张欣,龚爽,等. 基于MEMS惯性传感器的人体多运动模式识别[J]. 中国惯性技术学报, 2016, 24(5): 589-595.
LU Yongle, ZHANG Xin, GONG Shuang, et al. Recognition of multiple human motion patterns based on MEMS inertial sensors[J]. Journal of Chinese Inertial Technology, 2016, 24(5): 589-595.
[14] GENTNER C, ULMSCHNEIDER U. Simultaneous localization and mapping for pedestrians using low-cost ultra-wideband system and gyroscope[C]// International Conference on Indoor Positioning and Indoor Navigation (IPIN). Sapporo, Japan: IEEE, 2017: 1-8.
[15] TANG Yao, WANG Jing, LI Changzhi. Short-range indoor localization using a hybrid Doppler-UWB system[C]// IEEE MTT-S International Microwave Symposium. Honololu, USA: IEEE, 2017: 1011-1014.
[16] YANG Shaowei, WANG Bo. Residual based weighted least square algorithm for bluetooth/UWB indoor localization system[C]// 36th Chinese Control Conference. Dalian, China: IEEE, 2017: 5959-5963.

()
()