People Walking Classification Using Automotive Radar

This dataset contains complex signals coming from a mmWave FMCW radar system. Signals were acquired during a measurement campaign taken indoor and aimed to assess people's different ways of walking. Measurement setup and devices are described. The dataset consists of the acquisitions of six different types of activities, performed by 29 subjects who repeat each activity several times. Therefore, the dataset contains multiple different experiments for each activity, for a total of 231 acquisitions. The subjects walk without any constraint or do not follow any pattern, thus making this dataset useful not only for human gait recognition but also to evaluate the performance of different radar data processing algorithms.

show abstract

“…The repository is divided into two parts. The first one contains all the data collected during the experiments described in [1] . Fig.…”

Section: Data Descriptionmentioning

confidence: 99%

“…The second part of the dataset contains data related to different activities, performed in the same test area, which have not been considered in [1] . The data structure is depicted in Fig.…”

Section: Data Descriptionmentioning

confidence: 99%

Millimeter wave radar data of people walking

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…It is possible also that the target is composed of any multiple parts, that could be rotating or moving independently from the bulk. For example, in the case of a vehicle, the rotating elements can be the wheels; in the case of a moving person, arms or legs can be the moving elements [13]. These movements produce another Doppler effect called micro-Doppler and it is possible to exploit this effect to identify the target signature, or to measure other parameters [14,15].…”

Section: Radar Micro-doppler Effect For a Vibrating Targetmentioning

confidence: 99%

Performance Evaluation of Vibrational Measurements through mmWave Automotive Radars

et al. 2020

Self Cite

View full text Add to dashboard Cite

Thanks to the availability of a significant amount of inexpensive commercial Frequency Modulated Continuous Wave Radar sensors, designed primarily for the automotive domain, it is interesting to understand if they can be used in alternative applications. It is well known that with a radar system it is possible to identify the micro-Doppler feature of a target, to detect the nature of the target itself (what the target is) or how it is vibrating. In fact, thanks to their high transmission frequency, large bandwidth and very short chirp signals, radars designed for automotive applications are able to provide sub-millimeter resolution and a large detection bandwidth, to the point that it is here proposed to exploit them in the vibrational analysis of a target. The aim is to evaluate what information on the vibrations can be extracted, and what are the performance obtainable. In the present work, the use of a commercial Frequency Modulated Continuous Wave radar is described, and the performances achieved in terms of displacement and vibration frequency measurement of the target are compared with the measurement results obtained through a laser vibrometer, considered as the reference instrument. The attained experimental results show that the radar under test and the reference laser vibrometer achieve comparable outcomes, even in a cluttered scenario.

show abstract

“…Radar-based gait measurement methods were proposed to address the drawbacks of other sensor-based techniques [ 7 , 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 , 17 , 18 ]. Radar-based methods can remotely measure the velocity of whole human body parts without placing any constraints on the participant.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, micro-Doppler radar (MDR) has achieved accurate motion recognition and classification for various problems based on the deep-learning approach [ 7 , 8 ]. Because the MDR can measure micro-motions of humans, it is used for the recognition of detailed motions such as vital signs [ 9 ], gesture classification [ 10 ], and classifications of human gait types (e.g., classification with/without arm swinging [ 11 ] and slow/fast walking [ 12 ]). In addition, MDR-based techniques have been applied to obtain detailed gait measurement data that are used for personal identification [ 13 , 14 ] and the identification of gait type for rehabilitation and hospital applications [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Utilization of Micro-Doppler Radar to Classify Gait Patterns of Young and Elderly Adults: An Approach Using a Long Short-Term Memory Network

Hayashi

Saho

Shioiri

et al. 2021

Sensors

View full text Add to dashboard Cite

To develop a daily monitoring system for early detection of fall risk of elderly people during walking, this study presents a highly accurate micro-Doppler radar (MDR)-based gait classification method for the young and elderly adults. Our method utilizes a time-series of velocity corresponding to leg motion during walking extracted from the MDR spectrogram (time-velocity distribution) in an experimental study involving 300 participants. The extracted time-series was inputted to a long short-term memory recurrent neural network to classify the gaits of young and elderly participant groups. We achieved a classification accuracy of 94.9%, which is significantly higher than that of a previously presented velocity-parameter-based classification method.

show abstract

People Walking Classification Using Automotive Radar

Cited by 30 publications

References 41 publications

Millimeter wave radar data of people walking

Millimeter wave radar data of people walking

Performance Evaluation of Vibrational Measurements through mmWave Automotive Radars

Utilization of Micro-Doppler Radar to Classify Gait Patterns of Young and Elderly Adults: An Approach Using a Long Short-Term Memory Network

Contact Info

Product

Resources

About