Sparsity-based dynamic hand gesture recognition using micro-Doppler signatures

Li, Gang; Zhang, Rui; Ritchie, Matthew; Griffiths, Hugh

doi:10.1109/radar.2017.7944336

Cited by 45 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed method is compared with that of the Sparse-SVM method proposed by the same 214 authors [34]. With the Sparse-SVM method, the time-frequency trajectories of the dynamic hand gestures are extracted 215 by the OMP algorithm as described in Section III-A and inputted into SVM for recognition.…”

Section: A Analysis About the Recognition Accuracies And The Sparsitmentioning

confidence: 99%

Sparsity-Driven Micro-Doppler Feature Extraction for Dynamic Hand Gesture Recognition

Zhang

Ritchie

2018

IEEE Trans. Aerosp. Electron. Syst.

Self Cite

113

View full text Add to dashboard Cite

Section: A Analysis About the Recognition Accuracies And The Sparsitmentioning

confidence: 99%

Sparsity-Driven Micro-Doppler Feature Extraction for Dynamic Hand Gesture Recognition

Zhang

Ritchie

2018

IEEE Trans. Aerosp. Electron. Syst.

Self Cite

113

View full text Add to dashboard Cite

“…A K-band continuous wave (CW) radar has been exploited in HGR. It obtained up to 90% accuracy for 4 wide-range hand gestures [16]. N. Patel et al developed WiSee, a novel gesture recognition system based on a dual-channel Doppler radar that leveraged wireless signals to enable whole-home sensing and recognition under complex conditions [3].…”

Section: Related Workmentioning

confidence: 99%

“…Radar technologies based on sound or radio frequency (RF) active sensing can obtain range profile, Doppler and angle of arrival (AOA) features from the received signal. Such features are competitive and suitable for use in identifying the signature of hand gestures [7], [16], [17]. The range resolution is determined by the bandwidths of RF waves [18].…”

Section: Introductionmentioning

confidence: 99%

Micro Hand Gesture Recognition System Using Ultrasonic Active Sensing

2018

View full text Add to dashboard Cite

In this paper, we propose a micro hand gesture recognition system and methods using ultrasonic active sensing. This system uses micro dynamic hand gestures for recognition to achieve human-computer interaction (HCI). The implemented system, called hand-ultrasonic gesture (HUG), consists of ultrasonic active sensing, pulsed radar signal processing, and time-sequence pattern recognition by machine learning. We adopt lower frequency (300 kHz) ultrasonic active sensing to obtain high resolution range-Doppler image features. Using high quality sequential range-Doppler features, we propose a state-transition-based hidden Markov model for gesture classification. This method achieves a recognition accuracy of nearly 90% by using symbolized range-Doppler features and significantly reduces the computational complexity and power consumption. Furthermore, to achieve higher classification accuracy, we utilize an end-to-end neural network model and obtain a recognition accuracy of 96.32%. In addition to offline analysis, a real-time prototype is released to verify our method's potential for application in the real world.INDEX TERMS Ultrasonic active sensing, range-Doppler, micro hand gesture recognition, hidden Markov model, neural network.

show abstract

“…Micro-gesture recognition [1], [2] has gained significant interest in the context of industrial precision control [3], human-machine interaction, automotive driving assistance [4] and remote medical aid including emergency examination and surgery [5]. Compared with the past decades, more sensing technologies are available in the commercial market due to the rapid development of wireless network and miniaturized fabrication.…”

Section: Introductionmentioning

confidence: 99%

Hierarchical Sensor Fusion for Micro-Gesture Recognition With Pressure Sensor Array and Radar

Liang

Shrestha

et al. 2020

IEEE J. Electromagn. RF Microw. Med. Biol.

View full text Add to dashboard Cite

Enlighten-Research publications by members of the University of Glasgow http://eprints.gla.ac.uk The schematic of the hierarchical sensor fusion system for gesture recognition. Take-Home Messages  We proposed a hierarchical model to utilize radar as an 'Enhancer' to complement with the PSA (Pressure Sensor Array) in improving the static gestures recognition rates, on the contrary, in the dynamic gesture case scenario the PSA acts as an 'Enhancer' to boost the radar performance.  Sequential forward selection (SFS) significantly reduces the computational intensity in terms of less features and improves the classification performance.  For the second-stage of the hierarchical model, soft and hard fusion methods are implied respectively to promote the classification accuracy and eliminate the false alarms. Different weights of the 'Enhancer' output are verified and compared in terms of the accuracy in the soft fusion process.  Soft fusion improves the accuracy by 16.7% and 11.1% with respect to static and dynamic gesture identification, whereas hard fusion reduces the accuracy variance across all the participants and produces a subsequent improvement about 5.5% in the dynamic gestures.  Future work involves more gestures and more participants with neural network-based algorithm and additional sensors configurations and fusion approaches.

show abstract

Sparsity-based dynamic hand gesture recognition using micro-Doppler signatures

Cited by 45 publications

References 15 publications

Sparsity-Driven Micro-Doppler Feature Extraction for Dynamic Hand Gesture Recognition

Sparsity-Driven Micro-Doppler Feature Extraction for Dynamic Hand Gesture Recognition

Micro Hand Gesture Recognition System Using Ultrasonic Active Sensing

Hierarchical Sensor Fusion for Micro-Gesture Recognition With Pressure Sensor Array and Radar

Contact Info

Product

Resources

About