Image-Based Pedestrian Classification for 79 GHz Automotive Radar

Prophet, Robert; Hoffmann, Marcel; Ossowska, Alicja; Malik, Waqas Ahmed; Sturm, Christian; Vossiek, Martin

doi:10.23919/eurad.2018.8546611

Cited by 13 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By design, these layers process each reflection in the input independently. This is equivalent to a multi layer perceptron consisting of 2 layers with output shapes (30,4) and (30,8), where the parameters of each layer are shared across the first dimension, i. e. the one which corresponds to the reflections. This sequence ends with a global maxpooling layer, which ensures that the reflection branch is invariant w. r. t. the order of reflections in the input.…”

Section: B Deephybridmentioning

confidence: 99%

See 1 more Smart Citation

DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification

Cozma,

Morgan,

Stolz

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated vehicles need to detect and classify objects and traffic participants accurately. Reliable object classification using automotive radar sensors has proved to be challenging. We propose a method that combines classical radar signal processing and Deep Learning algorithms. The range-azimuth information on the radar reflection level is used to extract a sparse region of interest from the range-Doppler spectrum. This is used as input to a neural network (NN) that classifies different types of stationary and moving objects. We present a hybrid model (DeepHybrid) that receives both radar spectra and reflection attributes as inputs, e. g. radar crosssection. Experiments show that this improves the classification performance compared to models using only spectra. Moreover, a neural architecture search (NAS) algorithm is applied to find a resource-efficient and high-performing NN. NAS yields an almost one order of magnitude smaller NN than the manually-designed one while preserving the accuracy. The proposed method can be used for example to improve automatic emergency braking or collision avoidance systems.

show abstract

Section: B Deephybridmentioning

confidence: 99%

“…Compared to radar reflections, using the radar spectra can be beneficial, as no information is lost in the processing steps. The authors of [6], [7] take the radar spectrum into account to compute additional features for the classification, and [8] uses feature extractors known from vision to apply them on the radar spectrum.…”

Section: Introductionmentioning

confidence: 99%

DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification

Cozma,

Morgan,

Stolz

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…[6] applies a CNN-LSTM network on Range-Doppler and Doppler-Time spectrograms of 0.5-2 seconds to classify pedestrian, group of pedestrians, car, and cyclist classes. [10] pointed out that a long multi-frame observation period is not viable for urban driving, and proposed a single-frame usage of low-level data. Their method still generates object proposals with DBSCAN similar to [1], [2], but extracts for each cluster the corresponding area in a 2D Range-Doppler image, which is then classified using conventional computer vision.…”

Section: Related Workmentioning

confidence: 99%

CNN Based Road User Detection Using the 3D Radar Cube

Palffy

Dong

Kooij

et al. 2020

IEEE Robot. Autom. Lett.

133

View full text Add to dashboard Cite

This paper presents a novel radar based, singleframe, multi-class detection method for moving road users (pedestrian, cyclist, car), which utilizes low-level radar cube data. The method provides class information both on the radar targetand object-level. Radar targets are classified individually after extending the target features with a cropped block of the 3D radar cube around their positions, thereby capturing the motion of moving parts in the local velocity distribution. A Convolutional Neural Network (CNN) is proposed for this classification step. Afterwards, object proposals are generated with a clustering step, which not only considers the radar targets' positions and velocities, but their calculated class scores as well. In experiments on a real-life dataset we demonstrate that our method outperforms the state-of-the-art methods both target-and objectwise by reaching an average of 0.70 (baseline: 0.68) target-wise and 0.56 (baseline: 0.48) object-wise F1 score. Furthermore, we examine the importance of the used features in an ablation study.

show abstract

“…In an attempt to leverage as much information as possible, without any loss owed to the detection stage, classification is also performed directly on the radar spectra. Manual features based on the spectra are determined and used for classification of different objects in [13]- [15]. Data-driven approaches are investigated in [16], where the range-Doppler spectrum over multiple cycles is computed.…”

Section: Related Workmentioning

confidence: 99%

Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra

Patel

Beluch

Rambach

et al. 2021

Preprint

View full text Add to dashboard Cite

Deep learning (DL) has recently attracted increasing interest to improve object type classification for automotive radar. In addition to high accuracy, it is crucial for decision making in autonomous vehicles to evaluate the reliability of the predictions; however, decisions of DL networks are non-transparent. Current DL research has investigated how uncertainties of predictions can be quantified, and in this article, we evaluate the potential of these methods for safe, automotive radar perception. In particular we evaluate how uncertainty quantification can support radar perception under (1) domain shift, (2) corruptions of input signals, and (3) in the presence of unknown objects. We find that in agreement with phenomena observed in the literature, deep radar classifiers are overly confident, even in their wrong predictions. This raises concerns about the use of the confidence values for decision making under uncertainty, as the model fails to notify when it cannot handle an unknown situation. Accurate confidence values would allow optimal integration of multiple information sources, e.g. via sensor fusion. We show that by applying state-of-the-art post-hoc uncertainty calibration, the quality of confidence measures can be significantly improved, thereby partially resolving the over-confidence problem. Our investigation shows that further research into training and calibrating DL networks is necessary and offers great potential for safe automotive object classification with radar sensors.

show abstract

Image-Based Pedestrian Classification for 79 GHz Automotive Radar

Cited by 13 publications

References 8 publications

DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification

DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification

CNN Based Road User Detection Using the 3D Radar Cube

Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra

Contact Info

Product

Resources

About