Micro-Doppler-Based Human Activity Classification Using the Mote-Scale BumbleBee Radar

Cagliyan, Bahri; Gürbüz, Sevgi Zübeyde

doi:10.1109/lgrs.2015.2452946

Cited by 59 publications

(25 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The recorded data were processed through STFT to characterize the micro-Doppler signature in the armed vs unarmed case through features that can be extracted from the spectrograms, as in [6][7][8][9]. The STFTs were initially calculated using 0.…”

Section: Discussionmentioning

confidence: 99%

“…Target identification and classification based on micro-Doppler signatures have been investigated over a number of years for a variety of applications in security, warfare, search and rescue context [3,4]. It has been shown how human microDoppler signatures collected using a monostatic radar system and analysed through Short Time Fourier Transform (STFT) can be used to discriminate between animals and humans [5,6] , to distinguish between different activities performed by different people such as running, walking, crawling [7,8] or to identify different people performing the same activity on the basis of different micro-motion patterns [9] , and even to potentially distinguish between men and women [10] .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Fioranelli

Ritchie

Griffiths

2016

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

Fioranelli, F., Ritchie, M., and Griffiths, H. (2016) Centroid features for classification of armed/unarmed multiple personnel using multistatic human microdoppler. IET Radar, Sonar and Navigation, (doi:10.1049/iet-rsn.2015.0493) This paper is a postprint of a paper submitted to and accepted for publication in IET Radar, Sonar and Navigation and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at IET Digital Library There may be differences between this version and the published version. You are advised to consult the publisher's version if you wish to cite from it.http://eprints.gla.ac.uk/118776/ AbstractThis paper analyses the use of human micro-Doppler signatures collected using a multistatic radar system to identify and classify unarmed and potentially armed personnel walking within a surveillance area. The signatures were recorded in a series of experimental tests and analysed through Short Time FourierTransform followed by feature extraction and classification. Features based on Singular ValueDecomposition and on the centroid of the micro-Doppler signature are proposed and their suitability for armed vs unarmed classification purposes discussed. It is shown that classification accuracy above 95%can be achieved using a single feature. Features based on the centroid of the signatures are shown to be also effective in cases where there are two people walking together in the same direction and at similar speed, and one of them may be armed or not, i.e. for targets not easily separable in range or in Doppler.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Fioranelli

Ritchie

Griffiths

2016

IET Radar, Sonar & Navigation

View full text Add to dashboard Cite

show abstract

“…Another radio-based technique is represented by micro-Doppler signatures (MDS). Commercial radar motes can be used to discern among a small set of activities, such as walking, running, and crawling, with high accuracy values [22]. A larger set of MDS captured from humans performing 18 movements has been collected and presented in Ref.…”

Section: Related Work On Not Vision-based Devicesmentioning

confidence: 99%

Human Action Recognition with RGB-D Sensors

Cippitelli¹,

Gambi²,

Spinsante³

2017

Motion Tracking and Gesture Recognition

View full text Add to dashboard Cite

Human action recognition, also known as HAR, is at the foundation of many different applications related to behavioral analysis, surveillance, and safety, thus it has been a very active research area in the last years. The release of inexpensive RGB-D sensors fostered researchers working in this field because depth data simplify the processing of visual data that could be otherwise difficult using classic RGB devices. Furthermore, the availability of depth data allows to implement solutions that are unobtrusive and privacy preserving with respect to classic video-based analysis. In this scenario, the aim of this chapter is to review the most salient techniques for HAR based on depth signal processing, providing some details on a specific method based on temporal pyramid of key poses, evaluated on the well-known MSR Action3D dataset.

show abstract

“…The use of Doppler radar for human fall detection has attracted considerable interests [2,5,8,13,16] in recent years. A Doppler radar is able to characterize through the Doppler effect the motion dynamics of a human fall, which can be explored for its detection.…”

Section: Introductionmentioning

confidence: 99%

“…In addition to the Doppler radar, other variations of radar have also been examined for fall detection [2,7,16,20].…”

Section: Introductionmentioning

confidence: 99%

Radar placement for fall detection: Signature and performance

Rantz

et al. 2018

AIS

View full text Add to dashboard Cite

Abstract. Two popular mounting positions of Doppler radar for human fall detection are in the ceiling center and at the torso level. This paper examines the fall signatures observed by a Doppler radar at the two positions and evaluates their consistencies with respect to the fall directions and locations. The complementary characteristics of the fall signatures motivate the integration of the features from the ceiling mounted and torso level radars to improve the fall detection performance. Experimental results using the data collected of an elderly at a senior residence apartment for almost a year support our studies and the benefit of using both radars. The false alarm rate is reduced by a factor of 10 at 100% detection rate when compared to using a ceiling radar alone.

show abstract

Micro-Doppler-Based Human Activity Classification Using the Mote-Scale BumbleBee Radar

Cited by 59 publications

References 16 publications

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Centroid features for classification of armed/unarmed multiple personnel using multistatic human micro‐Doppler

Human Action Recognition with RGB-D Sensors

Radar placement for fall detection: Signature and performance

Contact Info

Product

Resources

About