Vital Sign Detection in Any Orientation Using a Distributed Radar Network via Modified Independent Component Analysis

Ren, Weili; Qi, Fugui; Foroughian, Farnaz; Kvelashvili, Tsotne; Liu, Quanhua; Kıłıc, Özlem; Li, Teng; Fathy, Aly E.

doi:10.1109/tmtt.2021.3101655

Cited by 20 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [22], the respiratory waveform was determined through empirical formulas, and then it was removed from the measured signal to obtain the heartbeat signal and has achieved good results. Most studies on radar-based heartbeat signal measurement primarily focus on the average heart rate during the observation period [23][24][25][26][27][28], resulting in insufficient exploration of cardiac health information. Thus, it is necessary to conduct more in-depth research on the heartbeat signal to further uncover valuable insights into cardiac health.…”

Section: Introductionmentioning

confidence: 99%

Noncontact Cardiac Activity Detection Based on Single-Channel ISM Band FMCW Radar

Qu,

Wei,

Zhang

2023

Biosensors

View full text Add to dashboard Cite

The heart is an important organ that maintains human life activities, and its movement reflects its health status. Utilizing electromagnetic waves as a sensing tool, radar sensors enable noncontact measurement of cardiac motion, offering advantages over conventional contact-based methods in terms of comfort, hygiene, and efficiency. In this study, the high-precision displacement detection algorithm of radar is applied to measure cardiac motion. Experimental is conducted using a single out-channel frequency modulated continuous wave (FMCW) radar operating in the ISM frequency band with a center frequency of 24 GHz and a bandwidth of 150 MHz. Since the detection signal is influenced by both respiratory and heartbeat movements, it is necessary to eliminate the respiratory signal from the measurement signal. Firstly, the harmonic composition of the respiratory signal is analyzed, and a method is proposed to calculate the parameters of the respiratory waveform by comparing the respiratory waveform coverage area with the area of the circumscribed rectangle. This allows for determining the number of respiratory harmonics, assisting in determining whether respiratory harmonics overlap with the frequency range of the heartbeat signal. Subsequently, a more accurate cardiac motion waveform is extracted. A reference basis is provided for extracting cardiac health information from radar measurement waveforms by analyzing the corresponding relationship between certain extreme points of the waveform and characteristic positions of the electrocardiogram (ECG) signal. This is achieved by eliminating the fundamental frequency component of the heartbeat waveform to emphasize other spectral components present in the heartbeat signal and comparing the heartbeat waveform, the heartbeat waveform with the fundamental frequency removed, and the heartbeat velocity waveform with synchronized ECG signals.

show abstract

Section: Introductionmentioning

confidence: 99%

Noncontact Cardiac Activity Detection Based on Single-Channel ISM Band FMCW Radar

Qu,

Wei,

Zhang

2023

Biosensors

View full text Add to dashboard Cite

show abstract

“…Outdoor injured human searching in public security field mainly includes two categories ( 1 ): (1) One is about the trapped survivor detection under ruins in the abnormal post-disaster environment (earthquakes, building collapses, landslides, etc). To address this problem, our group firstly proposed the bio-radar detection technology ( 2 ) in the field of Disaster Rescue Medicine and developed a series of bio-radar equipment, which could acquire survivor's vital sign ( 3 – 6 ), locations ( 7 ) and even behaviors ( 8 , 9 ) through ruins or wall. Based on the IoT technology, our bio-radar equipment radar equipment and other equipment together form the land-based search-rescue IoT equipment system, which has been successfully applied in many post-disaster search-rescue operations.…”

Section: Introductionmentioning

confidence: 99%

UAV multispectral multi-domain feature optimization for the air-to-ground recognition of outdoor injured human targets under cross-scene environment

Xia

Zhu³

et al. 2023

Front. Public Health

Self Cite

View full text Add to dashboard Cite

ObjectiveUAV-based multispectral detection and identification technology for ground injured human targets, is a novel and promising unmanned technology for public health and safety IoT applications, such as outdoor lost injured searching and battlefield casualty searching, and our previous research has demonstrated its feasibility. However, in practical applications, the searched human target always exhibits low target-background contrast relative to the vast and diverse surrounding environment, and the ground environment also shifts randomly during the UAV cruise process. These two key factors make it difficult to achieve highly robust, stable, and accurate recognition performance under the cross-scene situation.MethodsThis paper proposes a cross-scene multi-domain feature joint optimization (CMFJO) for cross-scene outdoor static human target recognition.ResultsIn the experiments, we first investigated the impact severity of the cross-scene problem and the necessity to solve it by designing 3 typical single-scene experiments. Experimental results show that although a single-scene model holds good recognition capability for its scenes (96.35% in desert scenes, 99.81% in woodland scenes, and 97.39% in urban scenes), its recognition performance for other scenes deteriorates sharply (below 75% overall) after scene changes. On the other hand, the proposed CMFJO method was also validated using the same cross-scene feature dataset. The recognition results for both individual scene and composite scene show that this method could achieve an average classification accuracy of 92.55% under cross-scene situation.DiscussionThis study first tried to construct an excellent cross-scene recognition model for the human target recognition, named CMFJO method, which is based on multispectral multi-domain feature vectors with scenario-independent, stable and efficient target recognition capability. It will significantly improve the accuracy and usability of UAV-based multispectral technology method for outdoor injured human target search in practical applications and provide a powerful supporting technology for public safety and health.

show abstract

“…Additionally, it generates continuous range-Doppler (R-D) images and combines them to make R-D video (i.e., an R-D map sequence) to detect and track the target. Because FMCW radar is less complex than the pulse-based radar system, it can be utilized in small radar platforms and near-field target detection environments, such as the detection of automobiles and humans [ 1 , 2 , 3 , 4 , 5 ].…”

Section: Introductionmentioning

confidence: 99%

Reconstruction of Range-Doppler Map Corrupted by FMCW Radar Asynchronization

Lee

Shin

et al. 2023

Sensors

View full text Add to dashboard Cite

Frequency-modulated continuous wave (FMCW) radar system synchronization using external clock signals can cause repeated Range-Doppler (R-D) map corruption when clock signal asynchronization problems occur between the transmitter and receiver. In this paper, we propose a signal processing method for the reconstruction of the corrupted R-D map owing to the FMCW radar’s asynchronization. After calculating the image entropy for each R-D map, the corrupted ones are extracted and reconstructed using the normal R-D maps acquired before and after the individual maps. To verify the effectiveness of the proposed method, three target detection experiments were conducted: a human target detection in an indoor environment and a wide place and a moving bike-rider target detection in an outdoor environment. The corrupted R-D map sequence of observed targets in each case was reconstructed properly and showed the validity by comparing the map-by-map range and speed changes in the detected target with the ground-truth information of the target.

show abstract

Vital Sign Detection in Any Orientation Using a Distributed Radar Network via Modified Independent Component Analysis

Cited by 20 publications

References 44 publications

Noncontact Cardiac Activity Detection Based on Single-Channel ISM Band FMCW Radar

Noncontact Cardiac Activity Detection Based on Single-Channel ISM Band FMCW Radar

UAV multispectral multi-domain feature optimization for the air-to-ground recognition of outdoor injured human targets under cross-scene environment

Reconstruction of Range-Doppler Map Corrupted by FMCW Radar Asynchronization

Contact Info

Product

Resources

About