Dataset of human motion status using IR-UWB through-wall radar

doi:10.23919/JSEE.2021.000093

Journal of Systems Engineering and Electronics ›› 2021, Vol. 32 ›› Issue (5): 1083-1096.doi: 10.23919/JSEE.2021.000093

• ELECTRONICS TECHNOLOGY • Previous Articles Next Articles

Dataset of human motion status using IR-UWB through-wall radar

Zhengliang ZHU^1,³(), Degui YANG^2,*(), Junchao ZHANG²(), Feng TONG^1,³

¹ Key Laboratory of Underwater Acoustic Communication and Marine Information Technology of the Ministry of Education, Xiamen University, Xiamen 361005, China
² School of Aeronautics and Astronautics, Central South University, Changsha 410083, China
³ College of Ocean and Earth Sciences, Xiamen University, Xiamen 361005, China

Received:2020-09-30 Online:2021-10-18 Published:2021-11-04
Contact: Degui YANG E-mail:zzlcsu@foxmail.com;ah_gui@sina.com;zhangjunchao@csu.edu.cn
About author:|ZHU Zhengliang was born in 1994. He received his B.S. degree from Changsha University of Science and Technology, Changsha, China, in 2017. In 2020, he received his M.S. degree from the Central South University, Changsha, China. Now, He is pursuing his Ph.D. degree at the Key Laboratory of Underwater Acoustic Communication and Marine Information Technology of the Ministry of Education, Xiamen University, Xiamen, China. His current research interests include ultra-wideband radar signal processing and underwater acoustic communication network. E-mail: zzlcsu@foxmail.com||YANG Degui was born in 1978. He received his B.S., M.S., and Ph.D. degrees from the Electronic Science and Engineering School, National University of Defense Technology, China, in 1997, 2002, and 2011, respectively. He is currently a full professor with the School of Aeronautics and Astronautics, Central South University, Changsha, China. From 2016 to 2017, he was an academic visitor of the Imperial College London, U.K. He has authored or coauthored two books and more than 20 articles. His research interests include the optical and radar characteristic analysis and radar signal processing. E-mail: ah_gui@sina.com||ZHANG Junchao was born in 1991. He received his B.S. degree in mechanical engineering and automation from HoHai University, Nanjing, China, in 2014, and Ph.D. degree in pattern recognition and intelligence systems from Shenyang Institude of Automation, Chinese Academy of Sciences, Shenyang, China, in 2019. From 2017 to 2018, he visited the University of Arizona, Tucson, AZ, USA, as a joint Ph.D. student. He works with the School of Aeronautics and Astronautics, Central South University, Changsha, China. His research interests include polarization imaging, image processing, machine learning, and pattern recognition. E-mail: zhangjunchao@csu.edu.cn||TONG Feng was born in 1973. He received his Ph.D. degree in underwater acoustics from Xiamen University, China, in 2000. From 2000 to 2002, he was a post-doctoral fellow with the Department of Radio Engineering, Southeast University, China. In 2003, he joined the Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong, as a research associate for one and a half year. From 2009 to 2010, he was a visiting scholar with the Department of Computer Science and Engineering, University of California, San Diego, USA. He is currently a professor with the Department of Applied Marine Physics and Engineering, Xiamen University. His research interests focus on underwater acoustic communication and acoustic signal processing. E-mail: ftong@xmu.edu.cn
Supported by:
This work was supported by the National Key Research and Development Program of China (2018YFC0810202) and the National Defence Pre-research Foundation of China (61404130119)

Abstract

Abstract:

Ultra-wideband (UWB) through-wall radar has a wide range of applications in non-contact human information detection and monitoring. With the integration of machine learning technology, its potential prospects include the physiological monitoring of patients in the hospital environment and the daily monitoring at home. Although many target detection methods of UWB through-wall radar based on machine learning have been proposed, there is a lack of an opensource dataset to evaluate the performance of the algorithm. This published dataset is measured by impulse radio UWB (IR-UWB) through-wall radar system. Three test subjects are measured in different environments and several defined motion status. Using the presented dataset, we propose a human-motion-status recognition method using a convolutional neural network (CNN), and the detailed dataset partition method and the recognition process flow are given. On the well-trained network, the recognition accuracy of testing data for three kinds of motion status is higher than 99.7%. The dataset presented in this paper considers a simple environment. Therefore, we call on all organizations in the UWB radar field to cooperate to build opensource datasets to further promote the development of UWB through-wall radar.

Key words: impulse radio ultra-wideband (IR-UWB), through-wall radar, human motion status, dataset, convolutional neural network (CNN)

Zhengliang ZHU, Degui YANG, Junchao ZHANG, Feng TONG. Dataset of human motion status using IR-UWB through-wall radar[J]. Journal of Systems Engineering and Electronics, 2021, 32(5): 1083-1096.

Figures/Tables 22

Fig 1

Fig 2

Fig 3

Fig 4

Fig 5

Table 1

Fig 6

Table 2

Table 3

Fig 7

Fig 8

Fig 9

Table 4

Fig 10

Fig 11

Fig 12

Fig 13

Table 5

Fig 14

Table 6

Fig 15

Fig 16

References 37

1	BARANOSKI E J Through-wall imaging: historical perspective and future directions. Journal of the Franklin Institute, 2008, 345 (6): 556- 569.
2	WU S Y, TAN K, XIA Z H, et al Improved human respiration detection method via ultra-wideband radar in through-wall or other similar conditions. IET Radar, Sonar & Navigation, 2016, 10 (3): 468- 476.
3	TIVIVE F H C, BOUZERDOUM A, AMINM G A subspace projection approach for wall clutter mitigation in through-the-wall radar imaging. IEEE Trans. on Geoscience and Remote Sensing, 2015, 53 (4): 2108- 2122. doi: 10.1109/TGRS.2014.2355211
4	LE M, VAN NGUYEN B Multivariate correlation of higher harmonics for heart rate remote measurement using UWB impulse radar. IEEE Sensors Journal, 2020, 20 (4): 1859- 1866. doi: 10.1109/JSEN.2019.2950635
5	YANG D, ZHU Z, LIANG B. Vital sign signal extraction method based on permutation entropy and EEMD algorithm for ultra-wideband radar. IEEE Access, 2019, 7: 178879–178890.
6	GURBUZ S Z, AMIN M G Radar-based human-motion recognition with deep learning: promising applications for indoor monitoring. IEEE Signal Processing Magazine, 2019, 36 (4): 16- 28. doi: 10.1109/MSP.2018.2890128
7	MA Y Y, LIANG F L, WANG P F, et al An accurate method to distinguish between stationary human and dog targets under through-wall condition using UWB radar. Remote Sensing, 2019, 11 (21): 2571. doi: 10.3390/rs11212571
8	MA Y Y, QI F G, WANG P F, et al Multiscale residual attention network for distinguishing stationary humans and common animals under through-wall condition using ultra-wideband radar. IEEE Access, 2020, 8, 121572- 121583. doi: 10.1109/ACCESS.2020.3006834
9	JIANG L B, ZHOU X, CHE L, et al Feature extraction and reconstruction by using 2D-VMD based on carrier-free UWB radar application in human motion recognition. Sensors, 2019, 19 (9): 1962. doi: 10.3390/s19091962
10	JIANG L B, WEI G M, CHE L Human motion recognition method by radar based on CNN. Computer Applications and Software, 2019, 36 (11): 174- 180, 240.
11	JIANG L B, LI C, CHE L Human motion recognition by-ultra-wide band radar. Journal of Electronic Measurement and Instrumentation, 2018, 32 (1): 129- 133.
12	BRYAN J D, KWON J, LEE N, et al Application of ultra-wide band radar for classification of human activities. IET Radar, Sonar & Navigation, 2012, 6 (3): 172- 179.
13	QI F G, LIANG F L, LV H, et al Detection and classification of finer-grained human activities based on stepped-frequency continuous-wave through-wall radar. Sensors, 2016, 16 (6): 885. doi: 10.3390/s16060885
14	QI F G, LV H, LIANG F L, et al MHHT-based method for analysis of micro-Doppler signatures for human finer-grained activity using through-wall SFCW radar. Remote Sensing, 2017, 9 (3): 260. doi: 10.3390/rs9030260
15	DU H, JIN T, HE Y, et al Segmented convolutional gated recurrent neural networks for human activity recognition in ultra-wideband radar. Neurocomputing, 2020, 396, 451- 464. doi: 10.1016/j.neucom.2018.11.109
16	DENG J, DONG W, SOCHER R, et al. ImageNet: a large-scale hierarchical image database. Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2009: 248–255.
17	DU H, JIN T, SONG Y P, et al Unsupervised adversarial domain adaptation for micro-Doppler based human activity classification. IEEE Geoscience and Remote Sensing Letters, 2020, 17 (1): 62- 66. doi: 10.1109/LGRS.2019.2917301
18	LANG Y, WANG Q, YANG Y, et al Unsupervised domain adaptation for micro-Doppler human motion classification via feature fusion. IEEE Geoscience and Remote Sensing Letters, 2019, 16 (3): 392- 396. doi: 10.1109/LGRS.2018.2873776
19	WANG W, ZHANG M, ZHANG L Classification of data stream in sensor network with small samples. IEEE Internet of Things Journal, 2019, 6 (4): 6018- 6025. doi: 10.1109/JIOT.2018.2867649
20	LI Y L, WANG W, JIANG Y Through wall human detection under small samples based on deep learning algorithm. IEEE Access, 2018, 6, 65837- 65844. doi: 10.1109/ACCESS.2018.2877730
21	CMU graphics lab motion capture database. http://mocap.cs.cmu.edu/.
22	LIANG X L, ZHANG H, YE S B, et al Improved denoising method for through-wall vital sign detection using UWB impulse radar. Digital Signal Processing, 2018, 74, 72- 93. doi: 10.1016/j.dsp.2017.12.004
23	FEI Y. Ultra wideband radar theory and technology. Beijing: National Defense Industry Press, 2010. (in Chinese)
24	LI X, QIAO D Y, LI Y, et al. A novel through-wall respiration detection algorithm using UWB radar. Proc. of the 35th IEEE Annual International Conference on Engineering in Medicine and Biology Society, 2013: 1013–1016.
25	YOUNGWOOK K, HAO L Human activity classification based on micro-Doppler signatures using a support vector machine. IEEE Trans. on Geoscience and Remote Sensing, 2009, 47 (5): 1328- 1337. doi: 10.1109/TGRS.2009.2012849
26	ZHANG F, LIANG B G, RONG R I, et al UWB radar life detector system design and test. Fire Science and Technology, 2016, 35 (7): 967- 969.
27	ZHU Z L, LIANG B G, YANG D G, et al Research, fabrication and application of IR-UWB through wall radar system. Transducer and Microsystem Technologies, 2020, 39 (4): 103- 106.
28	WANG G, AMIN M G Imaging through unknown walls using different standoff distances. IEEE Trans. on Signal Processing, 2006, 54 (10): 4015- 4025. doi: 10.1109/TSP.2006.879325
29	ZHOU Z. Machine learning. Beijing: Tsinghua University Press, 2016. (in Chinese)
30	LECUN Y Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86 (11): 2278- 2323. doi: 10.1109/5.726791
31	LECUN Y, BOSER B, DENKER J Backpropagation applied to handwritten zip code recognition. Neural Computation, 1989, 1 (4): 541- 551. doi: 10.1162/neco.1989.1.4.541
32	KIM Y, MOON T Human detection and activity classification based on micro-Doppler signatures using deep convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 2016, 13 (1): 8- 12. doi: 10.1109/LGRS.2015.2491329
33	HUBEL D H, WIESEL T N Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. The Journal of Physiology, 1962, 160 (1): 106- 154. doi: 10.1113/jphysiol.1962.sp006837
34	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition. Proc. of the International Conference on Learning Representations, 2015: arXiv1409.1556v6.
35	VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008: arXiv: 2108.01301.
36	ZHANG Y, ZHU Y P, CHENG Y Q, et al Human target radar echo signal analysis based on micro-Doppler characteristic. Signal Processing, 2009, 25 (10): 1616- 1623.
37	HE F. Researches on key techniques of wide band/ultra-wide band radar detection and signature extraction of locomotor human targets. Changsha: National University of Defense Technology, 2011. (in Chinese)

Parameter	Value
Distance of transceiver antennas/m	0.15
Operating mode	Impulse radio
Central frequency/MHz	500
Pulse width/ns	2
Sampling points of signal	$M$ =768
Sampling interval by equivalent sampling/ps	200
Sampling numbers in single point	${M_s}$ =64
Pulse repetition frequency/kHz	$f_{{p} }$ =400
ADC real-time sampling rate/(kSa/s)	400

Penetrating medium	Human walking	Human standing still	Empty
Free space
Brick-concrete wall

Penetrating medium	Human walking	Human standing still	Empty
Free space
Brick-concrete wall

Layer	Parameter	Value	Parameter’s number
Input layer	Input size	768×32	?
Convolutional layer (C1)	Filter number	16	160
	Activation function	Relu
	Kernel size	3×3
Convolutional layer (C2)	Filter number	32	4640
	Activation function	Relu
	Kernel size	3×3
Convolutional layer (C3)	Filter number	64	18496
	Activation function	Relu
	Kernel size	3×3
Convolutional layer (C4)	Filter number	128	32896
	Activation function	Relu
	Kernel size	2×2
Pooling layer (P5)	Step	2	?
Pooling layer (P5)	Pooling size	2×2	?
Full connected layer (F6)	Number of neurons	128	94126208
Full connected layer (F6)	Activation function	Relu	94126208
Full connected layer (F7)	Number of neurons	64	8256
Full connected layer (F7)	Activation function	Relu	8256
Output layer	Number of neurons	3	195
Output layer	Classifier	Softmax	195

Predicted motion	Human walking (actual labels)	Human standing still (actual labels)	Empty (actual labels)
Human walking	288	1	0
Human standing still	0	287	0
Empty	0	0	288
Accuracy/%	100	99.7	100

Dataset of human motion status using IR-UWB through-wall radar

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 22

References 37

Related Articles 6

Recommended Articles

Metrics

Comments

Model_Name	SAE	SVM
SAE[128]_SVM	Input [24576]-H [5012] - H [1024]-F [128]	Penalty factor: C=1000;
SAE[64]_SVM	Input [24576]-H [5012]- H [1024]-F [64]	Kernel: RBF;
SAE[16]_SVM	Input [24576]-H [5012]- H [1024]-F [16]	Kernel coefficients: Gamma=0.1

[1]	Lei HU, Guoxing YI, Chao HUANG. A sparse algorithm for adaptive pruning least square support vector regression machine based on global representative point ranking [J]. Journal of Systems Engineering and Electronics, 2021, 32(1): 151-162.
[2]	Wantian WANG, Ziyue TANG, Yichang CHEN, Yongjian SUN. Parity recognition of blade number and manoeuvre intention classification algorithm of rotor target based on micro-Doppler features using CNN [J]. Journal of Systems Engineering and Electronics, 2020, 31(5): 884-889.
[3]	Binquan LI, Xiaohui HU. Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach [J]. Journal of Systems Engineering and Electronics, 2019, 30(2): 238-244.
[4]	Baojun ZHAO, Boya ZHAO, Linbo TANG, Wenzheng WANG, Chen WU. Multi-scale object detection by top-down and bottom-up feature pyramid network [J]. Journal of Systems Engineering and Electronics, 2019, 30(1): 1-12.
[5]	Liangkui LIN, Shaoyou WANG, Zhongxing TANG. Using deep learning to detect small targets in infrared oversampling images [J]. Journal of Systems Engineering and Electronics, 2018, 29(5): 947-952.
[6]	Bendong Zhao, Huanzhang Lu, Shangfeng Chen, Junliang Liu, and Dongya Wu. Convolutional neural networks for time series classification [J]. Systems Engineering and Electronics, 2017, 28(1): 162-.