DNN Transfer Learning From Diversified Micro-Doppler for Motion Classification

Seyfioğlu, Mehmet Saygın; Erol, Barış; Gürbüz, Sevgi Zübeyde; Amin, Moeness G.

doi:10.1109/taes.2018.2883847

Cited by 84 publications

(45 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Convolutional autoencoders (CAEs) [14] has been proposed that uses unsupervised pretraining to alleviate the demand for training data. Despite this, another study [15] showed that transfer learning [16]- [18] was superior to CAEs when less than 550 samples were acquirable.…”

Section: Introductionmentioning

confidence: 96%

“…In recent years, HAR has made remarkable advance by applying deep learning (DL) algorithms [12]- [18] to micro-Doppler signatures. Instead of handcrafted feature selection, DL makes it possible to extract features automatically.…”

Section: Introductionmentioning

confidence: 99%

“…However, all of the methods [12]- [16], [18] mentioned above ignored the fact that the raw signals received by radars are complex time-series data, whose amplitude and phase could be connected with the kinematics of the observed target [5]. In general, the raw data is preprocessed by a short-time Fourier transform (STFT) to obtain spectrograms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Hybrid CNN–LSTM Network for the Classification of Human Activities Based on Micro-Doppler Radar

2020

View full text Add to dashboard Cite

Many deep learning (DL) models have shown exceptional promise in radar-based human activity recognition (HAR) area. For radar-based HAR, the raw data is generally converted into a 2-D spectrogram by using short-time Fourier transform (STFT). All the existing DL methods treat the spectrogram as an optical image, and thus the corresponding architectures such as 2-D convolutional neural networks (2D-CNNs) are adopted in those methods. These 2-D methods that ignore temporal characteristics ordinarily lead to a complex network with a huge amount of parameters but limited recognition accuracy. In this paper, for the first time, the radar spectrogram is treated as a time sequence with multiple channels. Hence, we propose a DL model composed of 1-D convolutional neural networks (1D-CNNs) and long shortterm memory (LSTM). The experiments results show that the proposed model can extract spatio-temporal characteristics of the radar data and thus achieves the best recognition accuracy and relatively low complexity compared to the existing 2D-CNN methods. INDEX TERMS Radar signal processing, human activity recognition, convolutional neural network, recurrent neural network, deep learning.

show abstract

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Hybrid CNN–LSTM Network for the Classification of Human Activities Based on Micro-Doppler Radar

2020

View full text Add to dashboard Cite

show abstract

“…In [18] DCNNs were used to classify human activities from their spectrograms, and in [19] a novel DCNN architecture was proposed to specifically account for the diversity induced by the different aspect angles on the radar signatures of human movements, especially with respect to their Doppler signature. Modifications to the conventional architectures of DCNNs were proposed in [2], [20], [21], in particular exploiting Convolutional Auto-Encoders (CAEs) to perform unsupervised pre-training of the weights of the network. CAEs and DCNNs for classification were also combined with a novel technique to augment the amount of available data in the training set by using Kinect-based motion caption simulations, enhanced by a diversification technique to improve the fidelity of the simulated synthetic data.…”

Section: Introductionmentioning

confidence: 99%

Continuous Human Activity Classification From FMCW Radar With Bi-LSTM Networks

et al. 2020

View full text Add to dashboard Cite

Recognition of human movements with radar for ambient activity monitoring is a developed area of research that yet presents outstanding challenges to address. In real environments, activities and movements are performed with seamless motion, with continuous transitions between activities of different duration and a large range of dynamic motions, compared with discrete activities of fixed-time lengths which are typically analysed in the literature. This paper proposes a novel approach based on recurrent LSTM and Bi-LSTM network architectures for continuous activity monitoring and classification. This approach uses radar data in the form of a continuous temporal sequence of micro-Doppler or range-time information, differently from from other conventional approaches based on convolutional networks that interpret the radar data as images. Experimental radar data involving 15 participants and different sequences of 6 actions are used to validate the proposed approach. It is demonstrated that using the Dopplerdomain data together with the Bi-LSTM network and an optimal learning rate can achieve over 90% mean accuracy, whereas range-domain data only achieved approximately 76%. The details of the network architectures, insights in their behaviour as a function of key hyper-parameters such as the learning rate, and a discussion on their performance across are provided in the paper.

show abstract

“…In addition to the above applications, it is also adopted in radar signal-processing applications. The typical cases include target detection [ 27 ], synthetic aperture radar(SAR)image interpretation [ 28 ] and moving-human-body classification [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Millimeter-Wave Array Radar-Based Human Gait Recognition Using Multi-Channel Three-Dimensional Convolutional Neural Network

Jiang

Zhang

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

At present, there are two obvious problems in radar-based gait recognition. First, the traditional radar frequency band is difficult to meet the requirements of fine identification with due to its low carrier frequency and limited micro-Doppler resolution. Another significant problem is that radar signal processing is relatively complex, and the existing signal processing algorithms are poor in real-time usability, robustness and universality. This paper focuses on the two basic problems of human gait detection with radar and proposes a human gait classification and recognition method based on millimeter-wave array radar. Based on deep-learning technology, a multi-channel three-dimensional convolution neural network is proposed on the basis of improving the residual network, which completes the classification and recognition of human gait through the hierarchical extraction and fusion of multi-dimensional features. Taking the three-dimensional coordinates, motion speed and intensity of strong scattering points in the process of target motion as network inputs, multi-channel convolution is used to extract motion features, and the classification and recognition of typical daily actions are completed. The experimental results show that we have more than 92.5% recognition accuracy for common gait categories such as jogging and normal walking.

show abstract

DNN Transfer Learning From Diversified Micro-Doppler for Motion Classification

Cited by 84 publications

References 51 publications

A Hybrid CNN–LSTM Network for the Classification of Human Activities Based on Micro-Doppler Radar

A Hybrid CNN–LSTM Network for the Classification of Human Activities Based on Micro-Doppler Radar

Continuous Human Activity Classification From FMCW Radar With Bi-LSTM Networks

Millimeter-Wave Array Radar-Based Human Gait Recognition Using Multi-Channel Three-Dimensional Convolutional Neural Network

Contact Info

Product

Resources

About