Hand Gesture Recognition via Radar Sensors and Convolutional Neural Networks

Franceschini, Stefano Sellari; Ambrosanio, Michele; Vitale, Sergio; Baselice, Fabio; Gifuni, Angelo; Grassini, Giuseppe; Pascazio, Vito

doi:10.1109/radarconf2043947.2020.9266565

Cited by 26 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, Franceschini S et al. [15] used Doppler radar sensors to collect signals from hand gestures. The system finally achieved an accuracy of 97% in 6 gestures after analysing the mixed signals and using CNN to recognise the gestures.…”

Section: Related Workmentioning

confidence: 99%

UltraDigit: An ultrasound signal‐based in‐air digit input system via transfer learning

Yang,

Zhang,

Wang

2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

With the popularity of smart devices, people pay more attention to the experience of text input. The authors propose an in‐air digit input system, namely UltraDigit, which enables users to input digits in the air using acoustic signal via transfer learning. Different from other technologies, UltraDigit can obtain the finger movement through a speaker and a microphone built in the smartphone, which does not need the assistance of other hardware. In addition, the authors use the idea of transfer learning with a small amount of data to train classification model, which achieves good performance with low training cost (such as time cost and data cost). Experimental results show the average accuracy of digit recognition is 92.9%, which verifies the validity of the ultrasound signal‐based contactless digit input.

show abstract

Section: Related Workmentioning

confidence: 99%

UltraDigit: An ultrasound signal‐based in‐air digit input system via transfer learning

Yang,

Zhang,

Wang

2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…They showed that the pro-posed RD-CNN achieved better accuracy on a publicly available radar-based HAR dataset. Franceschini et al [ 30 ] analyzed the doppler signature of a radar sensor and proposed a low-cost hand gesture recognition approach using CNN. They achieved 97% accuracy.…”

Section: Related Workmentioning

confidence: 99%

STC-NLSTMNet: An Improved Human Activity Recognition Method Using Convolutional Neural Network with NLSTM from WiFi CSI

Islam

Jannat

Hossain

et al. 2022

Sensors

View full text Add to dashboard Cite

Human activity recognition (HAR) has emerged as a significant area of research due to its numerous possible applications, including ambient assisted living, healthcare, abnormal behaviour detection, etc. Recently, HAR using WiFi channel state information (CSI) has become a predominant and unique approach in indoor environments compared to others (i.e., sensor and vision) due to its privacy-preserving qualities, thereby eliminating the need to carry additional devices and providing flexibility of capture motions in both line-of-sight (LOS) and non-line-of-sight (NLOS) settings. Existing deep learning (DL)-based HAR approaches usually extract either temporal or spatial features and lack adequate means to integrate and utilize the two simultaneously, making it challenging to recognize different activities accurately. Motivated by this, we propose a novel DL-based model named spatio-temporal convolution with nested long short-term memory (STC-NLSTMNet), with the ability to extract spatial and temporal features concurrently and automatically recognize human activity with very high accuracy. The proposed STC-NLSTMNet model is mainly comprised of depthwise separable convolution (DS-Conv) blocks, feature attention module (FAM) and NLSTM. The DS-Conv blocks extract the spatial features from the CSI signal and add feature attention modules (FAM) to draw attention to the most essential features. These robust features are fed into NLSTM as inputs to explore the hidden intrinsic temporal features in CSI signals. The proposed STC-NLSTMNet model is evaluated using two publicly available datasets: Multi-environment and StanWiFi. The experimental results revealed that the STC-NLSTMNet model achieved activity recognition accuracies of 98.20% and 99.88% on Multi-environment and StanWiFi datasets, respectively. Its activity recognition performance is also compared with other existing approaches and our proposed STC-NLSTMNet model significantly improves the activity recognition accuracies by 4% and 1.88%, respectively, compared to the best existing method.

show abstract

“…Radar object detection. Low-Definition (LD) radar has been used for many applications such as hand gesture recognition [10], object or person detection at gates [15] and aerial monitoring [26]. For automotive applications, single views of the RAD tensor are chosen as input of specific neural network architectures to detect objects' signatures in the considered view, either RA [8], [40] or RD [28].…”

Section: Radar Backgroundmentioning

confidence: 99%

Raw High-Definition Radar for Multi-Task Learning

Rebut¹,

Ouaknine²,

Malik³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fig. 1: Overview of our RADIal dataset. RADIal includes a set of 3 sensors (camera, laser scanner, high-definition radar) and comes with GPS and vehicle's CAN traces; 25K synchronized samples are recorded in raw format. (a) Camera image with projected laser point cloud in red and radar point cloud in indigo, vehicle annotation in orange and free driving space annotation in green; (b) Radar power spectrum with bounding box annotations; (c) Free driving space annotation in bird-eye view, with annotated vehicle bounding boxes in orange, radar point cloud in indigo and laser point cloud in red; (d) Range-Azimuth map in Cartesian coordinates overlayed with radar point cloud and laser point cloud; (e) GPS trace in red and odometry trajectory reconstruction in green.

show abstract

Hand Gesture Recognition via Radar Sensors and Convolutional Neural Networks

Cited by 26 publications

References 16 publications

UltraDigit: An ultrasound signal‐based in‐air digit input system via transfer learning

UltraDigit: An ultrasound signal‐based in‐air digit input system via transfer learning

STC-NLSTMNet: An Improved Human Activity Recognition Method Using Convolutional Neural Network with NLSTM from WiFi CSI

Raw High-Definition Radar for Multi-Task Learning

Contact Info

Product

Resources

About