A kinect-based human micro-doppler simulator

Erol, Barış; Gürbüz, Sevgi Zübeyde

doi:10.1109/maes.2015.7119820

Cited by 71 publications

(40 citation statements)

References 22 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They could be obtained from traditional MoCAP databases such as [14]- [16], [20]. Moreover, the Kinect sensor could also be used for capturing the desired animation as suggested in [17], [18]. The skeleton and animation are imported to Blender using the bvh format.…”

Section: A Animation Generationmentioning

confidence: 99%

“…There are many existing MoCap databases publicly available such as [14]- [16]. Owing to the fact that these databases are captured for specific scenarios in addition to the high price of the professional MoCap systems, the Kinect sensor is proposed for motion capturing [17], [18]. Nevertheless, eventually for generating huge databases of specific scenarios, one has to rely on nonflexible existing databases or use a sensor for collecting data whether it is a radar sensor or any other kind of sensor.…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, an approach which is built above the techniques mentioned in [12], [17], [18] is described for generating a huge amount of data with the assistance of the open source software Blender [19]. First, the different methods for obtaining the required animation data for the simulation scenarios are introduced.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Human Motion Training Data Generation for Radar Based Deep Learning Applications

Ishak¹,

Appenrodt

Dickmann

et al. 2018

2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)

View full text Add to dashboard Cite

Abstract-Radar sensors are utilized for detection and classification purposes in various applications. In order to use deep learning techniques, lots of training data are required. Accordingly, lots of measurements and labelling tasks are then needed. For the purpose of pre-training or examining first ideas before bringing them into reality, synthetic radar data are of great help. In this paper, a workflow for automatically generating radar data of human gestures is presented, starting with creating the desired animations until synthesizing radar data and getting the final required dataset. The dataset could then be used for training deep learning models. A classification scenario applying this workflow is also introduced.

show abstract

Section: A Animation Generationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Human Motion Training Data Generation for Radar Based Deep Learning Applications

Ishak¹,

Appenrodt

Dickmann

et al. 2018

2018 IEEE MTT-S International Conference on Microwaves for Intelligent Mobility (ICMIM)

View full text Add to dashboard Cite

show abstract

“…The generation of reliable simulated data describing radar signatures of horses' gait can be very valuable to have a benchmark to compare experimental data with, and to obtain the required volume of data to achieve the necessary statistical significance when applying machine learning based classification techniques. Research work on simulated data with these objectives is also reported for human radar data [15]. Using examples of motion-captured data of walking horses, provided by courtesy of the Swedish University of Agriculture Sciences and Qualisys, radar signatures of horses walking towards the radar have been simulated with ranges varying from 30 down to 5 m. The data was acquired in Strömsholm, Sweden, in a sand school fitted with 60 cameras from Qualisys running at 200 frames per second.…”

Section: Simulation Of Horse Gait Radar Signaturementioning

confidence: 99%

Gait analysis of horses for lameness detection with radar sensors

Shrestha

Kernec

Fioranelli

et al. 2017

International Conference on Radar Systems (Radar 2017)

View full text Add to dashboard Cite

This paper presents the preliminary investigation of the use of radar signatures to detect and assess lameness of horses and its severity. Radar sensors in this context can provide attractive contactless sensing capabilities, as a complementary or alternative technology to the current techniques for lameness assessment using video-graphics and inertial sensors attached to the horses' body. The paper presents several examples of experimental data collected at the Weipers Centre Equine Hospital at the University of Glasgow, showing the micro-Doppler signatures of horses and initial results of their analysis.

show abstract

“…Well defined models for human motion have been developed by V. Chen and applied to real data [25]- [28], these can accurately produce expected micro-Doppler contributions from different types of motions. In recent work it has been shown that optical sensors can also be used to develop human micro-Doppler modelling capabilities further through the use of a simple low cost optical sensor [29].…”

Section: Introductionmentioning

confidence: 99%

Through Wall Radar Classification of Human Micro-Doppler using Singular Value Decomposition Analysis

Ritchie

Ash

Chen

et al. 2016

Preprint

View full text Add to dashboard Cite

Abstract:The ability to detect the presence as well as classify the activities of individuals behind visually obscuring structures is of significant benefit to police, security and emergency services in many situations. This paper presents the analysis from a series of experimental results generated using a through-the-wall (TTW) Frequency Modulated Continuous Wave (FMCW) C-Band radar system named Soprano. The objective of this analysis was to classify whether an individual was carrying an item in both hands or not using micro-Doppler information from a FMCW sensor. The radar was deployed at a standoff distance, of approximately 0.5 m, outside a residential building and used to detect multiple people walking within a room. Through the application of digital filtering, it was shown that significant suppression of the primary wall reflection is possible, significantly enhancing the target signal to clutter ratio. Singular Value Decomposition (SVD) signal processing techniques were then applied to the micro-Doppler signatures from different individuals. Features from the SVD information have been used to classify whether the person was carrying an item or walking free handed. Excellent performance of the classifier was achieved in this challenging scenario with accuracies up to 94%, suggesting that future through wall radar sensors may have the ability to reliably recognize many different types of activities in TTW scenarios using these techniques.

show abstract

A kinect-based human micro-doppler simulator

Cited by 71 publications

References 22 publications

Human Motion Training Data Generation for Radar Based Deep Learning Applications

Human Motion Training Data Generation for Radar Based Deep Learning Applications

Gait analysis of horses for lameness detection with radar sensors

Through Wall Radar Classification of Human Micro-Doppler using Singular Value Decomposition Analysis

Contact Info

Product

Resources

About