arXiv subjects

Bernhard Kleiner

Publications and source records attributed to Bernhard Kleiner.

5 recordsLinked to original sources

arXiv2019

Person Identification and Body Mass Index: A Deep Learning-Based Study on Micro-Dopplers

Obtaining a smart surveillance requires a sensing system that can capture accurate and detailed information for the human walking style. The radar micro-Doppler ($\boldsymbolμ$-D) analysis is proved to be a reliable metric for studying human locomotions. Thus, $\boldsymbolμ$-D signatures can be used to identify humans based on their walking styles. Additionally, the signatures contain information about the radar cross section (RCS) of the moving subject. This paper investigates the effect of human body characteristics on human identification based on their $\boldsymbolμ$-D signatures. In our proposed experimental setup, a treadmill is used to collect $\boldsymbolμ$-D signatures of 22 subjects with different genders and body characteristics. Convolutional autoencoders (CAE) are then used to extract the latent space representation from the $\boldsymbolμ$-D signatures. It is then interpreted in two dimensions using t-distributed stochastic neighbor embedding (t-SNE). Our study shows that the body mass index (BMI) has a correlation with the $\boldsymbolμ$-D signature of the walking subject. A 50-layer deep residual network is then trained to identify the walking subject based on the $\boldsymbolμ$-D signature. We achieve an accuracy of 98% on the test set with high signal-to-noise-ratio (SNR) and 84% in case of different SNR levels.

cs.CV↗

arXiv2018

Micro-Doppler Based Human-Robot Classification Using Ensemble and Deep Learning Approaches

Radar sensors can be used for analyzing the induced frequency shifts due to micro-motions in both range and velocity dimensions identified as micro-Doppler ($\boldsymbolμ$-D) and micro-Range ($\boldsymbolμ$-R), respectively. Different moving targets will have unique $\boldsymbolμ$-D and $\boldsymbolμ$-R signatures that can be used for target classification. Such classification can be used in numerous fields, such as gait recognition, safety and surveillance. In this paper, a 25 GHz FMCW Single-Input Single-Output (SISO) radar is used in industrial safety for real-time human-robot identification. Due to the real-time constraint, joint Range-Doppler (R-D) maps are directly analyzed for our classification problem. Furthermore, a comparison between the conventional classical learning approaches with handcrafted extracted features, ensemble classifiers and deep learning approaches is presented. For ensemble classifiers, restructured range and velocity profiles are passed directly to ensemble trees, such as gradient boosting and random forest without feature extraction. Finally, a Deep Convolutional Neural Network (DCNN) is used and raw R-D images are directly fed into the constructed network. DCNN shows a superior performance of 99\% accuracy in identifying humans from robots on a single R-D map.

cs.CV↗

arXiv2017

Power-Based Real-Time Respiration Monitoring Using FMCW Radar

Non-contact vital sign detection is a required application nowadays in many fields as patient monitoring and static human detection. Within the last decade, radar has been introduced as a smart and convenient sensor for non-contact respiration monitoring. Radar sensors are considered suitable for such application for its capability to work through obstacles and in harsh environmental conditions. FMCW radar has been introduced as a powerful tool in this field for its capability of detecting both the breathing target position and his chest micro-motions induced due to breathing. Most of the presented techniques for using the radar for respiration detection is based on bandpass filtering or wavelet transforms on the required harmonics in either the range or Doppler dimension. However, both techniques affect the real-time capability of the monitoring and work on limited distances and aspect angles. A recognizable fluctuation effect is observed in the received range spectrum overtime due to respiration chest movements. The proposed technique in this paper is based on detecting and processing the power changes in real-time over different aspect angles and distances. Two radar modules working on different carrier frequency bands, bandwidths and output power levels were tested and compared.

eess.SP↗

arXiv2017

Stairs Detection for Enhancing Wheelchair Capabilities Based on Radar Sensors

Powered wheelchair users encounter barriers to their mobility everyday. Entering a building with non barrier-free areas can massively impact the user mobility related activities. There are a few commercial devices and some experimental that can climb stairs using for instance adaptive wheels with joints or caterpillar drive. These systems rely on the use for sensing and control. For safe automated obstacle crossing, a robust and environment invariant detection of the surrounding is necessary. Radar may prove to be a suitable sensor for its capability to handle harsh outdoor environmental conditions. In this paper, we introduce a mirror based two dimensional Frequency-Modulated Continuous-Wave (FMCW) radar scanner for stair detection. A radar image based stair dimensioning approach is presented and tested under laboratory and realistic conditions.

cs.HC↗

arXiv2017

Real-Time Capable Micro-Doppler Signature Decomposition of Walking Human Limbs

Unique micro-Doppler signature ($\boldsymbolμ$-D) of a human body motion can be analyzed as the superposition of different body parts $\boldsymbolμ$-D signatures. Extraction of human limbs $\boldsymbolμ$-D signatures in real-time can be used to detect, classify and track human motion especially for safety application. In this paper, two methods are combined to simulate $\boldsymbolμ$-D signatures of a walking human. Furthermore, a novel limbs $μ$-D signature time independent decomposition feasibility study is presented based on features as $μ$-D signatures and range profiles also known as micro-Range ($μ$-R). Walking human body parts can be divided into four classes (base, arms, legs, feet) and a decision tree classifier is used. Validation is done and the classifier is able to decompose $μ$-D signatures of limbs from a walking human signature on real-time basis.

cs.CV↗