Hand Gesture Recognition Using Micro-Doppler Signatures With Convolutional Neural Network

By Youngwook Kim, Brian Toomajian. IEEE Access, 2016

331 citations recorded by the source corpus.

In this paper, we investigate the feasibility of recognizing human hand gestures using micro-Doppler signatures measured by Doppler radar with a deep convolutional neural network (DCNN). Hand gesture recognition using radar can be applied to control electronic appliances. Compared with an optical recognition system, radar can work regardless of light conditions and it can be embedded in a case. We classify ten different hand gestures, with only micro-Doppler signatures on spectrograms without range information. The ten gestures, which included swiping from left to right, swiping from right to left, rotating clockwise, rotating counterclockwise, pushing, double pushing, holding, and double holding, were measured using Doppler radar and their spectrograms investigated. A DCNN was employed to classify the spectrograms, with 90% of the data utilized for training and the remaining 10% for validation. After five-fold validation, the classification accuracy of the proposed method was found to be 85.6%. With seven gestures, the accuracy increased to 93.1%.

Subfields: Aerospace Engineering, Artificial Intelligence, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/3734e717f119d829406d0ca81796ccf6167912e4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Moeness G. Amin
2. Hanyu Wang
3. Kun Xia
4. S. Gürbüz
5. Jianguang Huang

In Artificial Intelligence

1. Jindong Wang
2. Yiqiang Chen
3. Shuji Hao
4. Moeness G. Amin
5. Hanyu Wang
6. Xiaohui Peng
7. Kun Xia
8. S. Gürbüz

In Human-Computer Interaction

1. Hanyu Wang
2. Kun Xia
3. Jianguang Huang

Citations in the corpus

• Deep Learning for Sensor-based Activity Recognition: A Survey (2017, methodology): “The convolution-pooling combination is common in CNN, and most approaches performed max or average pooling after convolution (Ha et al., 2015; Kim and Toomajian, 2016; Pourbabaee et al., 2017).”
• LSTM-CNN Architecture for Human Activity Recognition (2020, methodology): “Hitherto, this technology has been widely used in the fields of home behavior analysis [2], video surveillance [3], gait analysis [4], and gesture recognition [5], etc.”
• Radar-Based Human-Motion Recognition With Deep Learning: Promising applications for indoor monitoring (2019, background): “Miniaturization of FMCW radars at 60 GHz, such as the radar technology pioneered by the Google Soli sensor [15], has driven radar-based gesture recognition [16]–[19] for the noncontact control of personal electronics, wearable devices, and vehicle consoles.”