11 results
Now showing1 - 10 of 11
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Light-weight and person-independent radar-based hand gesture recognition for classification and regression of continuous gestures(IEEE, 2024-05-01); ; ; ; This paper proposes a novel pre-processing technique for radar-based short-range gesture sensing using a frequency modulated continuous wave (FMCW) radar. The pre-processing is light-weight and works without Fourier transformation. The signal after pre-processing represents the backscattering central dynamics of the hand as a complex-valued time signal of a point target. It is shown that the proposed processing provides competitive classification results compared to conventional frequency domain-based solutions, while being less computationally intensive and having better generalization performance. The pre-processed time domain signal preserves a high temporal resolution of the hand movement. Due to this fact, it is possible to integrate a periodic control gesture into the system. In doing so, the system not only detects that a gesture is performed continuously and periodically, but also estimates its speed. This is an essential property for controlling scalable parameters such as brightness or volume at different speeds. The real-time capability was proven on a Raspberry Pi 3B with an ARM Cortex-A53 CPU. The proposed processing causes a CPU utilization of only 6%. The nn inference is done within 75 ms with a classification accuracy of 96.7%.Publicationtype: Journal Article37 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Out-of-distribution detection for radar-based gesture recognition using metric-learningThe paper addresses the question how and to what extent metric learning can be beneficial for reducing the false alarm rate in radar-based hand gesture recognition systems. To this end, we evaluate different metric learning approaches for out-of-distribution or unknown motion detection. We found that metric learning can help to significantly increase the out-of-distribution capabilities of the network. We further investigated what conditions must be met for metric learning to work well, and found that the composition of the data set for known gestures has a large influence on the out-of-distribution detection rate.Publicationtype: Conference Paper52 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Improved indoor semi-static human target detection and localization using FMCW radarThis paper presents a novel processing approach for semi-static human indoor perception and localization with Frequency modulated continuous wave (FMCW) radar. When analyzing semi-static targets with FMCW radar, minimal phase variations of standing or sitting human targets in slow-time can result in missed detections under traditional processing schemes. The common approach of studying micro-Doppler signatures over an extended period of time can, however, be costly in terms of both memory and compute resources. In this work, we introduce an approach with low memory and computational footprint, which relies on signatures beyond micro-Doppler for a novel presence score. We show on real-world recordings how this maximal variance based presence score can bring improvement in detection of static humans. To further increase detections in the range angle space, we introduce a novel angle of arrival estimation by creating a synthetic spatial signal from all phase differences between antennas over time. We show a 22.9% gain in human detection performance on a large dataset of humans in semi-static applications and highlight the reduction in computational complexity of both of these concepts.Publicationtype: Conference Paper22 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Radar-Based Gesture Recognition Using a Variational Autoencoder With Deep Statistical Metric Learning(2022-11-01); ; ; Radar-based gesture recognition systems are a promising concept for new human–machine interfaces. However, the systems are sensitive to user-dependent gesture patterns, sensor noise characteristics, background environments, and unknown gestures or background motions. To overcome such challenges, we propose a variational autoencoder architecture-based deep metric learning, which is optimized using a novel loss function combining a statistical distance triplet loss and the center loss. By learning the statistical distance between distributions, the proposed solution, compared with triplet loss, is able to better learn the nonlinear characteristics in the data, is less sensitivity to training strategy, and is capable of creating close knit embedding clusters. Moreover, it is experimentally demonstrated that the proposed gesture recognition system using radar spectrograms has improved classification accuracy and random gesture rejection accuracy compared with the state-of-the-art deep metric learning approaches. Furthermore, we proof the real-world capability of the system by implementing a real-time demonstrator, which allows playing “Tetris” with hand gestures.Publicationtype: Journal Article74 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , HARadNet: Anchor-free target detection for radar point clouds using hierarchical attention and multi-task learningTarget localization and classification from radar point clouds is a challenging task due to the inherently sparse nature of the data with highly non-uniform target distribution. This work presents HARadNet, a novel attention based anchor free target detection and classification network architecture in a multi-task learning framework for radar point clouds data. A direction field vector is used as motion modality to achieve attention inside the network. The attention operates at different hierarchy of the feature abstraction layer with each point sampled according to a conditional direction field vector, allowing the network to exploit and learn a joint feature representation and correlation to its neighborhood. This leads to a significant improvement in the performance of the classification. Additionally, a parameter-free target localization is proposed using Bayesian sampling conditioned on a pre-trained direction field vector. The extensive evaluation on a public radar dataset shows an substantial increase in localization and classification performance.Publicationtype: Journal Article47 9 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Bayesradar : Bayesian Metric-Kalman filter learning for improved and reliable radar target classification(IEEE, 2021-10-25); ; ; ; Publicationtype: Conference Paper81 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Data-driven Radar Processing Using a Parametric Convolutional Neural Network for Human Activity Classification(2021-09-01); ; ; The paper proposes a data-driven pre-processing optimization for radar data using a parametric convolutional neural network. The proposed method is applied on human activity classification as a use case. Present radar-based activity recognition system exploit micro-Doppler signature by generating Doppler spectrograms or a temporal series of range-Doppler maps, followed by deep neural networks or machine learning approaches for classification. Those radar data representations are typically generated on the basis of short-time Fourier transformations. A Fourier transformation equally resolves the frequency space, which may be sub-optimal in some applications. Although deep convolutional neural networks (DCNN) have been shown to implicitly learn features from raw sensor data in other fields, such as speech recognition, yet, for the case of radar-based DCNNs, pre-processing is required to develop a scalable and robust classification or regression application. In this paper, we propose a parametric convolutional neural network that mimics the radar pre-processing across fast-time and slow-time radar data through 2D sinc filter or 2D wavelet filter kernels to extract features for classification of various human activities. During training only the filter parameters of the 2D sinc filters or 2D wavelets are learned, leading to optimized feature representation for the classification task. It is demonstrated that our proposed solution shows improved results compared to equivalent DCNN architectures that rely on Doppler spectrograms or radar data cubes as input data.Publicationtype: Journal Article84 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Improved Target Detection and Feature Extraction using a Complex-Valued Adaptive Sine Filter on Radar Time Domain DataIn state-of-art radar classification tasks the raw time domain ADC data is transformed to frequency domain wherein the target is detected. Feature data, such as the micro-Doppler signature, is extracted for classification of e.g. a performed gesture or a person based on its gait. However, the transformation into frequency domain using short-time Fourier transform resulting in erroneous target detection due to superposition of target components thus leading to sub-optimal feature for subsequent classification task. Thus, in this paper we propose a target feature extraction approach that operates directly on 2D time domain radar data by using a complex-valued adaptive 2D sine filter. The proposed approach tracks the target's slow-time and fast-time frequencies by a regulation loop, which progressively adjusts the filter's center frequency to the target location. We demonstrate that the proposed approach extracts better features in both single- and multi-target scenarios, leading to improved classification accuracy in gait classification problems using radars. Furthermore, the proposed time domain feature extraction approach facilitates the use of a parametric neural network that works directly on time domain data.Publicationtype: Conference Paper54 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Integrated Classification and Localization of Targets Using Bayesian Framework In Automotive Radars(IEEE, 2021-06); ; ; ; Automatic radar based classification of automotive targets, such as pedestrians and cyclist, poses several challenges due to low inter-class variations among different classes and large intra-class variations. Further, different targets required to track in typical automotive scenario can have completely varying dynamics which gets challenging for tracker using conventional state vectors. Compared to state-of-the-art using independent classification and tracking, in this paper, we propose an integrated tracker and classifier leading to a novel Bayesian framework. The tracker’s state vector in the proposed framework not only includes the localization parameters of the targets but is also augmented with the targets’s feature embedding vector. In consequence, the tracker’s performance is optimized due to a better separability of the targets. Furthermore, the classifier’s performance is enhanced due to Bayesian formulation utilizing the temporal smoothing of classifier’s embedding vector.Publicationtype: Conference Paper113 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , A Bayesian framework for integrated deep metric learning and tracking of vulnerable road users using automotive radars(IEEE, 2021-05-05); ; ; ; With the recent advancements in radar systems, radar sensors offer a promising and effective perception of the surrounding. This includes target detection, classification and tracking. Compared to the state-of-the-art, where the state vector of classical tracker considers only localization parameters, this paper proposes an integrated Bayesian framework by augmenting state vector with feature embedding as appearance parameter together with localization parameter. In context of automotive vulnerable road users (VRUs) such as pedestrian and cyclist, the classical tracker poses multiple challenges to preserve the identity of the tracked target during partial or complete occlusion, due to low inter-class (pedestrian-cyclist) variations and strong similarity between intra-class (pedestrian-pedestrian). Subsequently, feature embedding corresponding to target's micro-Doppler signature are learned using novel Bayesian based deep metric learning approaches. The tracker's performance is optimized due to a better separability of the targets. At the same time, the classifiers' performance is enhanced due to Bayesian formulation utilizing the temporal smoothing of the classifier's embedding vector. In this work, we demonstrate the performance of the proposed Bayesian framework using several vulnerable user targets based on a 77 GHz automotive radar.Publicationtype: Journal ArticleScopus© Citations 16 145 247