Multi-target human gait classification using LSTM recurrent neural networks applied to micro-Doppler

Klarenbeek, G.J.; Harmanny, R. I. A.; Cifola, Lorenzo

doi:10.23919/eurad.2017.8249173

Cited by 45 publications

(28 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LSTM is an alternative RNN architecture which can overcome this shortcoming. A detailed explanation of LSTM can be found in [25][26][27][28].…”

Section: Long Short-term Memorymentioning

confidence: 99%

“…Time-series analysis appears in many application domains, including speech recognition, handwriting recognition, weather readings, and financial recordings [18][19][20]. We consider two common time-series recognition methods, namely, the NN-dynamic time warping (DTW) (NN classifier with the DTW distance) [21][22][23][24] method and the long short-term memory (LSTM) method [25][26][27][28]. The former is a conventional machine learning (ML) technique that utilizes the DTW distance which is a sum-measure over a parametrization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Arm Motion Classification Using Time-Series Analysis of the Spectrogram Frequency Envelopes

2020

View full text Add to dashboard Cite

Hand and arm gesture recognition using radio frequency (RF) sensing modality proves valuable in man-machine interfaces and smart environments. In this paper, we use the time-series analysis method to accurately measure the similarity of the micro-Doppler (MD) signatures between the training and test data, thus providing improved gesture classification. We characterize the MD signatures by the maximum instantaneous Doppler frequencies depicted in the spectrograms. In particular, we apply two machine learning (ML) techniques, namely, the dynamic time warping (DTW) method and the long short-term memory (LSTM) network. Both methods take into account the values as well as the temporal evolution and characteristics of the time-series data. It is shown that the DTW method achieves high gesture classification rates and is robust to time misalignment.

show abstract

“…The LSTM is an alternative RNN architecture which can overcome this shortcoming. A detailed explanation of LSTM can be found in [25][26][27][28].…”

Section: Long Short-term Memorymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Arm Motion Classification Using Time-Series Analysis of the Spectrogram Frequency Envelopes

2020

View full text Add to dashboard Cite

show abstract

“…By selecting and classifying the micro-Doppler features in the time-Doppler map, human activities can be recognized by various models. For example, G. Klarenbeek et al applied a LSTM structure with the time-Doppler maps to realize the multi-target human gait classification [26].…”

Section: Human Target Analysis With Hrrp and Micro-doppler Profilesmentioning

confidence: 99%

Toward Deep Learning-Based Human Target Analysis

He¹,

Li²,

Jing³

2019

UWB Technology and Its Applications

View full text Add to dashboard Cite

In this chapter, we describe methods toward deep learning-based human target analysis. Firstly, human target analysis in 2D and 3D domains of radar signal is introduced. Furthermore, range-Doppler surface for human target analysis using ultra-wideband radar is described. The construction of range-Doppler surface involves range-Doppler imaging, adaptive threshold detection, and isosurface extraction. In comparison with micro-Doppler profiles and high-resolution range profiles, range-Doppler surface contains range, Doppler, and time information simultaneously. An ellipsoid-based human motion model is designed for validation. Range-Doppler surfaces simulated for different human activities are demonstrated and discussed. With the rapid emergence of deep learning, the development of radar target recognition has been accelerated. We describe several deep learning algorithms for human target analysis. Finally, a few future research considerations are listed to spark inspiration.

show abstract

“…Further work on the use of CNNs in the context of human activity recognition for assisted living has been presented [22], focusing on aspects such as most suitable pre-processing and time-frequency distribution for the micro-Doppler signatures [23], combination of information from different radar domains including range-Doppler and range-time to enhance performance [24], different architectures mixing Auto-Encoders (AE) with CNNs [25][26], and challenges and strategies to train deep networks effectively with limited experimental radar data available [27]. Other works have looked at classifying different human gaits in the context of area surveillance using ground-based radar, in particular identifying individual pedestrians as opposed to group of multiple people, either using CNNs or Recurrent Neural Networks (RNNs) on the spectrograms [28][29], and at classification of armed/unarmed personnel using multistatic radar [30]. In this work, we present and discuss a modular pipelined approach to achieve near real-time radar data processing and multiple moving object tracking, and to subsequently classify these objects.…”

Section: Introductionmentioning

confidence: 99%

Practical classification of different moving targets using automotive radar and deep neural networks

Angelov

Robertson

Murray-Smith

et al. 2018

IET Radar, Sonar & Navigation

109

View full text Add to dashboard Cite

In this work, we present results for classification of different classes of targets (car, single and multiple people, bicycle) using automotive radar data and different neural networks. A fast implementation of radar algorithms for detection, tracking, and micro-Doppler extraction is proposed in conjunction with the automotive radar transceiver TEF810X and microcontroller unit SR32R274 manufactured by NXP Semiconductors. Three different types of neural networks are considered, namely a classic convolutional network, a residual network, and a combination of convolutional and recurrent network, for different classification problems across the 4 classes of targets recorded. Considerable accuracy (close to 100% in some cases) and low latency of the radar pre-processing prior to classification (approximately 0.55s to produce a 0.5s long spectrogram) are demonstrated in this paper, and possible shortcomings and outstanding issues are discussed.

show abstract

Multi-target human gait classification using LSTM recurrent neural networks applied to micro-Doppler

Cited by 45 publications

References 4 publications

Arm Motion Classification Using Time-Series Analysis of the Spectrogram Frequency Envelopes

Arm Motion Classification Using Time-Series Analysis of the Spectrogram Frequency Envelopes

Toward Deep Learning-Based Human Target Analysis

Practical classification of different moving targets using automotive radar and deep neural networks

Contact Info

Product

Resources

About