RadHAR

Singh, Akash Deep; Sandha, Sandeep Singh; García, Luis Antonio Ribot; Srivastava, Mani

doi:10.1145/3349624.3356768

Cited by 167 publications

(58 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A comparison with several reference classifiers reveals superior accuracy of 97.61% on the recorded data set. On a publicly available dataset [60], an accuracy improvement of 6% (97.8%) is reported.…”

Section: The History Of Continuous Human Activity Recognitionmentioning

confidence: 96%

A Survey on Radar-Based Continuous Human Activity Recognition

Ullmann¹,

Guendel

Kruse

et al. 2023

IEEE J. Microw.

View full text Add to dashboard Cite

Radar-based human motion and activity recognition is currently a topic of great research interest, as the aging population increases and older individuals prefer an independent lifestyle. This technology has a wide range of applications, such as fall detection in assisted living, gesture recognition for human-machine interfaces, and many more. Numerous studies exist on various approaches for radar-based activity capture and classification. However, most of these employ rather artificial data, often obtained in laboratory environments, and typically collected under particular conditions. Specifically, most research so far has aimed at distinguishing a predefined set of single activities with a defined start, stop and duration. This paper aims at drawing the attention to a so far less researched issue, one that will be of vital importance for future real-world application of radar-based human activity recognition: continuous activity recognition, i.e. recognizing specific activities in a stream of several sequential activities with unknown duration and arbitrary transitions between different classes of activities. A review on the current state of the art in this relatively new topic is given, followed by a discussion on future research directions.INDEX TERMS Radar applications, radar signal processing, continuous human activity recognition, activities of daily living.This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination.

show abstract

Section: The History Of Continuous Human Activity Recognitionmentioning

confidence: 96%

A Survey on Radar-Based Continuous Human Activity Recognition

Ullmann¹,

Guendel

Kruse

et al. 2023

IEEE J. Microw.

View full text Add to dashboard Cite

show abstract

“…Its advantage is that it can detect targets from multiple angles, but it can only detect specified objects. In the human activity recognition scene, Akash et al [29] proposed radhar, which is a framework for performing accurate har using sparse and non-uniform point clouds. Since human activity usually lasts for a few seconds, point clouds are accumulated within a sliding time window to capture the time dependence.…”

Section: Related Workmentioning

confidence: 99%

mmBehavior: Human Activity Recognition System of millimeter-wave Radar Point Clouds Based on Deep Recurrent Neural Network

et al. 2023

Preprint

View full text Add to dashboard Cite

Sensing human activities through wireless technology is the key to human-computer interaction. Relevant studies show that millimeter-wave radar has attracted more and more attention because it can accurately measure distance, velocity, and angle, and extract 3D point cloud images. However, the millimeter-wave point cloud is very sparse. For example, the depth neural network of PointNet is designed to deal with the LIDAR point cloud, which is not effective on the millimeter-wave radar point cloud. Therefore, in this paper, we propose a user activity perception system mmBheavior based on commercial millimeter-wave radar chip. Firstly, we use an improved clustering algorithm P-DBSCAN, which overcomes the problem of DBSCAN parameter sensitivity and realizes adaptive user target detection in the environment of changing number of people. Then we propose a new neural network architecture P-BiLSTMNet, which improves PointNet + + and introduces BiLSTM to learn the time dependence of point cloud. Experiments show that the system can classify all kinds of motion, and the accuracy is more than 93%.

show abstract

“…For the control of devices with hand gestures, gesture recognition algorithms based on a wide range of neural networks have been proposed, involving, e.g., 2D-CNNs [12], 2D-CNNs with LSTMs [34], or 3D-CNNs with LSTM [42]. These approaches exploit spectral information in the form of micro-Doppler spectrograms [12] or range-Doppler spectra [34], but it is also possible to distinguish between gestures [10] and activities [29] using radar point clouds. The latter are a more compact representation of the radar observations and are obtained by finding valid targets in the radar data.…”

Section: Related Workmentioning

confidence: 99%

“…Point clouds facilitate the application of geometrical transformations [29] as well as the inclusion of additional information [10]. While most research considers small-scale gesture recognition close to the radar sensor, reliable macro gesture recognition at larger distances has been also shown to be feasible with radar sensors for applications such as smart homes [18] or traffic scenarios [11,10].…”

Section: Related Workmentioning

confidence: 99%

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

Holzbock,

Kern,

Waldschmidt

et al. 2023

Preprint

View full text Add to dashboard Cite

We present a joint camera and radar approach to enable autonomous vehicles to understand and react to human gestures in everyday traffic. Initially, we process the radar data with a PointNet followed by a spatio-temporal multilayer perceptron (stMLP). Independently, the human body pose is extracted from the camera frame and processed with a separate stMLP network. We propose a fusion neural network for both modalities, including an auxiliary loss for each modality. In our experiments with a collected dataset, we show the advantages of gesture recognition with two modalities. Motivated by adverse weather conditions, we also demonstrate promising performance when one of the sensors lacks functionality.

show abstract

RadHAR

Cited by 167 publications

References 14 publications

A Survey on Radar-Based Continuous Human Activity Recognition

A Survey on Radar-Based Continuous Human Activity Recognition

mmBehavior: Human Activity Recognition System of millimeter-wave Radar Point Clouds Based on Deep Recurrent Neural Network

Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles

Contact Info

Product

Resources

About