Sparsity aware dynamic gesture recognition using radar sensors with angular diversity

Yang, Le; Li, Gang

doi:10.1049/iet-rsn.2018.5206

Cited by 14 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to classifying human motions, radars have been recently used for gesture recognition which is an important problem in a variety of applications that involve smart homes and human-machine interface for intelligent devices [19][20][21][22][23][24][25][26][27]. The latter is considered vital in aiding the physically impaired who might be wheelchair confined or bed-ridden patients.…”

Section: Introductionmentioning

confidence: 99%

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

Amin

Zeng

Shan

2019

2019 IEEE Radar Conference (RadarConf)

View full text Add to dashboard Cite

We introduce a simple but effective technique in automatic hand gesture recognition using radar. The proposed technique classifies hand gestures based on the envelopes of their micro-Doppler (MD) signatures. These envelopes capture the distinctions among different hand movements and their corresponding positive and negative Doppler frequencies that are generated during each gesture act. We detect the positive and negative frequency envelopes of MD separately, and form a feature vector of their augmentation. We use the k-nearest neighbor (kNN) classifier and Manhattan distance (L1) measure, in lieu of Euclidean distance (L2), so as not to diminish small but critical envelope values. It is shown that this method outperforms both low-dimension representation techniques based on principal component analysis (PCA) and sparse reconstruction using Gaussian-windowed Fourier dictionary, and can achieve very high classification rates.

show abstract

Section: Introductionmentioning

confidence: 99%

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

Amin

Zeng

Shan

2019

2019 IEEE Radar Conference (RadarConf)

View full text Add to dashboard Cite

show abstract

“…38 RIS can effectually meet the KPIs of FSO communication 39 like configurable wavelength division multiplexing, 40 beam steering 41 and dynamic angular diversity. 42 As in the RF spectrum, we have sufficient dimensions and can achieve tunability by using passive elements like varactor diodes 43,44 or using micro-electronic mechanical systems (MEMS) technology. [45][46][47] But in the optical regime due to the limited sizes passive elements can not be used to achieve tunability so for that purpose birefringent materials 48,49 like liquid crystals [50][51][52][53][54] or phase change materials are being deployed.…”

Section: Introductionmentioning

confidence: 99%

Fluid-infiltrated on-axis ultra-compact reconfigurable intelligent surface for application of free-space optical communication

Khalid,

Mahmood,

Mehmood

et al. 2023

Nanophotonics and Micro/Nano Optics IX

View full text Add to dashboard Cite

Free space optical (FSO) communication is an evolving technology that opens up the doors to use huge unlicensed bandwidth and can manifest high-speed communication. As the radio frequency spectrum is getting overburdened and unable to meet the ever-increasing demands of the internet, the optical spectrum can prove to be a paradigm shift to achieve the KPIs of communication including high data-rates, low latency and efficiency. In our study, a fluid-infiltrated reconfigurable intelligent surface (RIS) has been proposed that is proficient in directing the light on the concerned user. We proposed the integration of RIS in FSO communication to simultaneously enhance the data transmission range and acquire reconfigurability on run-time. Our proposed design can provide the communication link to the legitimate user while blocking the eavesdropper's reception. The proposed miniaturesized surface is envisaged to be an efficient meta-device for dynamic applications in FSO Communication.

show abstract

“…Moreover, the differences in radial velocities perceived by the different sensors provide additional valuable information not accessible to a single sensor. Despite the expectable benefits, there is only little literature on the use of sensor networks yet: [8] uses two sensors to distinguish between hand gestures based on hand-crafted features, and [9] deploys a single sensor whose receive antennas are separated apart enough to form a multistatic arrangement. However, there is no investigation of the potential of modern radar sensor networks for classification accuracy and robustness.…”

Section: Introductionmentioning

confidence: 99%

Robust Doppler-Based Gesture Recognition With Incoherent Automotive Radar Sensor Networks

Kern¹,

Steiner²,

Lorenzin³

et al. 2020

IEEE Sens. Lett.

View full text Add to dashboard Cite

In this paper the capabilities of an incoherent radar sensor network for robust Doppler-based gesture recognition are investigated and a significant performance boost is demonstrated. A comprehensive dataset is recorded with an incoherent sensor network consisting of three time-synchronized 77 GHz FMCW radars. Based on this dataset, we show that differential Doppler features obtained from the varying viewing angles result in a significant multistatic gain for classification, particularly for high intra-class variations and low Doppler frequencies. For the most complex dataset crossuser validation accuracy of a CNN with optimized data fusion is improved by 7.4 % to an overall value of 87.1 %, which we regard high as gestures are not designed for distinguishability but reflect everyday control and communication signals.

show abstract

Sparsity aware dynamic gesture recognition using radar sensors with angular diversity

Cited by 14 publications

References 25 publications

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

Hand Gesture Recognition based on Radar Micro-Doppler Signature Envelopes

Fluid-infiltrated on-axis ultra-compact reconfigurable intelligent surface for application of free-space optical communication

Robust Doppler-Based Gesture Recognition With Incoherent Automotive Radar Sensor Networks

Contact Info

Product

Resources

About