A Multi-Domain Fusion Human Motion Recognition Method Based on Lightweight Network

Chen, Pengyun; Jian, Qiang; Wu, Peilun; Guo, Shisheng; Cui, Guolong; Jiang, Chaoshu; Kong, Lingjiang

doi:10.1109/lgrs.2021.3132692

Cited by 10 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When implementing HAR using radar sensors, the MFFNs can be divided into featurelevel fusion networks [28][29][30][31][32][33][34][35] and decision-level fusion networks [36][37][38]. Feature-level fusion methods extract features from multiple inputs and combine them to create an even more comprehensive and richer feature representation.…”

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

“…Feature-level fusion methods extract features from multiple inputs and combine them to create an even more comprehensive and richer feature representation. For example, simple stitching operations on features [29][30][31][32][33][34][35] and feature fusion summation operations [28] are the most common methods.…”

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

“…However, this approach is only suitable for feature fusion with correlated features [32]. In another study, Chen et al designed a pre-trained MobileNetV3 lightweight network model and a feature pyramid network (FPN) based multiscale feature extraction model to overcome the challenge of insufficient data [33]. A hierarchical fusion network (HFN) with multi-domain features was proposed in the literature using narrowband radar.…”

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network

Lin

Song

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes a human activity recognition (HAR) method for frequency-modulated continuous wave (FMCW) radar sensors. The method utilizes a multi-domain feature attention fusion network (MFAFN) model that addresses the limitation of relying on a single range or velocity feature to describe human activity. Specifically, the network fuses time-Doppler (TD) and time-range (TR) maps of human activities, resulting in a more comprehensive representation of the activities being performed. In the feature fusion phase, the multi-feature attention fusion module (MAFM) combines features of different depth levels by introducing a channel attention mechanism. Additionally, a multi-classification focus loss (MFL) function is applied to classify confusable samples. The experimental results demonstrate that the proposed method achieves 97.58% recognition accuracy on the dataset provided by the University of Glasgow, UK. Compared to existing HAR methods for the same dataset, the proposed method showed an improvement of about 0.9–5.5%, especially in the classification of confusable activities, showing an improvement of up to 18.33%.

show abstract

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

Section: Har Based On Multi-domain Feature Fusion Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network

Lin

Song

Zhao

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The activation function is an important aspect of a neural network, which determines the learning ability of the network. In the basic MobileNetV3 model, H‐Swish [37] is used as the activation function. Given the large amount of data and the variety of classifications of PV module defect images, an activation function with higher efficiency, stronger robustness and as simple as possible than H‐Swish is needed.…”

Section: Diagnose Models and Evaluation Indicatorsmentioning

confidence: 99%

Automatic defect identification of PV panels with IR images through unmanned aircraft

Tang,

Ren,

Xia

et al. 2023

IET Renewable Power Gen

View full text Add to dashboard Cite

In order to improve the reliability and performance of photovoltaic systems, a fault diagnosis method for photovoltaic modules based on infrared images and improved MobileNet‐V3 is proposed. Firstly, the defect images of open‐source photovoltaic modules and their existing problems are analysed; based on the existing problems, image enhancement and data enhancement are performed on the infrared defect images of photovoltaic modules, so that the infrared images meet the requirements of image availability and sample quantity. Finally, the basic MobileNet‐V3 network is improved to realize fault classification of photovoltaic modules. The experimental results show that, compared with the traditional CNN and the basic MobileNet V3, the proposed fault classification method not only has high accuracy and fast diagnosis speed, but also has a high recognition rate for various fault categories, which has good practicability and application value.

show abstract

Face Recognition Based on Point Cloud Data Captured by Low-cost mmWave Radar Sensors

Zhong

Yuan

Zou

et al. 2023

2023 IEEE 13th Annual Computing and Communication Workshop and Conference (CCWC)

View full text Add to dashboard Cite

A Multi-Domain Fusion Human Motion Recognition Method Based on Lightweight Network

Cited by 10 publications

References 15 publications

Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network

Human Activity Recognition Method Based on FMCW Radar Sensor with Multi-Domain Feature Attention Fusion Network

Automatic defect identification of PV panels with IR images through unmanned aircraft

Face Recognition Based on Point Cloud Data Captured by Low-cost mmWave Radar Sensors

Contact Info

Product

Resources

About