Multidimensional Feature Representation and Learning for Robust Hand-Gesture Recognition on Commercial Millimeter-Wave Radar

Xia, Zhaoyang; Luomei, Yixiang; Zhou, Chenglong; Xu, Feng

doi:10.1109/tgrs.2020.3010880

Cited by 56 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…17,18 Therefore, only by integrating the images and data of active and passive millimeter wave imaging, can target objects with different shapes and materials be identified more accurately. According to the image feature selection criteria, [19][20][21] the following image feature extraction is studied in this paper.…”

Section: Image Feature Extraction and Object Classification Recognitionmentioning

confidence: 99%

Active and passive mixed millimeter wave imaging target recognition method based on multi‐feature fusion

Zhang

Zong

Qiu

2022

Int J RF Mic Comp-Aid Eng

View full text Add to dashboard Cite

Due to millimeter-wave (MMW) has a strong ability to penetrate clothing, MMW holographic imaging technology can conduct a non-contact inspection of the human body's surface. Therefore, it is of great significance to study the security inspection equipment and target recognition technology based on millimeter wave imaging. In this paper, an active and passive hybrid millimeter wave imaging target recognition method based on multi-feature fusion is pro-

show abstract

Section: Image Feature Extraction and Object Classification Recognitionmentioning

confidence: 99%

Active and passive mixed millimeter wave imaging target recognition method based on multi‐feature fusion

Zhang

Zong

Qiu

2022

Int J RF Mic Comp-Aid Eng

View full text Add to dashboard Cite

show abstract

“…Compared with the IR-UWB radar, the FMCW radar provides multidimensional information including target range, velocity and angle with multiple antennas. The FMCW signal of the i-th detected people with a 2-D MIMO antenna array is expressed as follows [23]:…”

Section: Fmcw and Ir-uwb Radar Signal Modelmentioning

confidence: 99%

“…The RDM was then averaged over time to obtain RD(r, v) for target detection. The neighbor threshold detection method [23] was applied iteratively to select the point with the local maximal amplitude in RD(r, v), detecting the distance r i and velocity v i of the i-th target. The azimuth angle α i was then computed with angle FFT.…”

Section: Target Detection and Roi Selectionmentioning

confidence: 99%

Indoor Activity and Vital Sign Monitoring for Moving People with Multiple Radar Data Fusion

et al. 2021

View full text Add to dashboard Cite

The monitoring of human activity and vital signs plays a significant role in remote health-care. Radar provides a non-contact monitoring approach without privacy and illumination concerns. However, multiple people in a narrow indoor environment bring dense multipaths for activity monitoring, and the received vital sign signals are heavily distorted with body movements. This paper proposes a framework based on Frequency Modulated Continuous Wave (FMCW) and Impulse Radio Ultra-Wideband (IR-UWB) radars to address these challenges, designing intelligent spatial-temporal information fusion for activity and vital sign monitoring. First, a local binary pattern (LBP) and energy features are extracted from FMCW radar, combined with the wavelet packet transform (WPT) features on IR-UWB radar for activity monitoring. Then the additional information guided fusing network (A-FuseNet) is proposed with a modified generative and adversarial structure for vital sign monitoring. A Cascaded Convolutional Neural Network (CCNN) module and a Long Short Term Memory (LSTM) module are designed as the fusion sub-network for vital sign information extraction and multisensory data fusion, while a discrimination sub-network is constructed to optimize the fused heartbeat signal. In addition, the activity and movement characteristics are introduced as additional information to guide the fusion and optimization. A multi-radar dataset with an FMCW and two IR-UWB radars in a cotton tent, a small room and a wide lobby is constructed, and the accuracies of activity and vital sign monitoring achieve 99.9% and 92.3% respectively. Experimental results demonstrate the superiority and robustness of the proposed framework.

show abstract

“…Gesture recognition has been implemented with multiple types of sensors, such as cameras [7,8], and radars [9] or their combination [10]. Most of these works explore obtaining highly discriminative features, for example, Ge et al used a 3D-CNN-based method for 3D volumetric representation of the hand depth image to obtain 3D spatial information [8], and Molchanov et al combined radar, image, and depth sensors to provide complementary information about the shape, color, and the instantaneous angular velocity of the hand [10].…”

Section: Motivationmentioning

confidence: 99%

Gesture Recognition Via Learning Deep Spatio-Temporal Features In Wi-Fi Sensing

Xie

2021

Preprint

View full text Add to dashboard Cite

Internet of Things (IoT) expects to incorporate massive machine-type (MCT) devices, such as vehicles, sensors, and wearable devices, which brings a large number of application tasks that need to be processed. Additionally, data collected from various devices needs to be executed and processed in a timely, reliable, and efficient manner. Gesture recognition has enabled IoT applications such as human-computer interaction and virtual reality. In this work, we propose a cross-domain device-free gesture recognition (DFGR) model, that exploits 3D-CNN to obtain spatiotemporal features in Wi-Fi sensing. To adapt the sensing data to the 3D model, we carry out 3D data segment and supplement in addition to signal denoising and time-frequency transformation. We demonstrate that our proposed model outperforms the state-of-the-art method in the application of DFGR even cross 3 domain factors simultaneously, and is easy to converge and convenient for training with a less complicated hierarchical structure.

show abstract

Multidimensional Feature Representation and Learning for Robust Hand-Gesture Recognition on Commercial Millimeter-Wave Radar

Cited by 56 publications

References 41 publications

Active and passive mixed millimeter wave imaging target recognition method based on multi‐feature fusion

Active and passive mixed millimeter wave imaging target recognition method based on multi‐feature fusion

Indoor Activity and Vital Sign Monitoring for Moving People with Multiple Radar Data Fusion

Gesture Recognition Via Learning Deep Spatio-Temporal Features In Wi-Fi Sensing

Contact Info

Product

Resources

About