Clustering of high resolution automotive radar detections and subsequent feature extraction for classification of road users

Schubert, Eugen; Meinl, Frank; Kunert, Martin; Menzel, Wolfgang

doi:10.1109/irs.2015.7226315

Cited by 36 publications

(13 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…radar targets with bike/pedestrian/car predicted labels are clustered in separate steps. As metric, we used a spatial threshold γ xy on the Euclidean distance in the x, y space (2D Cartesian spatial position), and a separate speed threshold γ v in velocity dimension (Prophet [1], [18], [25]). The advantage of clustering each class separately is that no universal parameter set is needed for DBSCAN.…”

Section: Object Clusteringmentioning

confidence: 99%

CNN Based Road User Detection Using the 3D Radar Cube

Palffy

Dong

Kooij

et al. 2020

IEEE Robot. Autom. Lett.

141

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

Section: Object Clusteringmentioning

confidence: 99%

CNN Based Road User Detection Using the 3D Radar Cube

Palffy

Dong

Kooij

et al. 2020

IEEE Robot. Autom. Lett.

141

View full text Add to dashboard Cite

show abstract

“…Schubert et al [ 9 ] used DBSCAN with only minor modifications to cluster radar reflections of moving pedestrians. In a three-dimensional x - y - v space where x and y refer to Cartesian coordinates and v to Doppler velocity, they filtered out stationary reflections below a threshold of 0.1

and applied DBSCAN with

m and an additional velocity threshold of 1

.…”

Section: Related Workmentioning

confidence: 99%

Constraint-Based Hierarchical Cluster Selection in Automotive Radar Data

Malzer

Baum

2021

Sensors

View full text Add to dashboard Cite

High-resolution automotive radar sensors play an increasing role in detection, classification and tracking of moving objects in traffic scenes. Clustering is frequently used to group detection points in this context. However, this is a particularly challenging task due to variations in number and density of available data points across different scans. Modified versions of the density-based clustering method DBSCAN have mostly been used so far, while hierarchical approaches are rarely considered. In this article, we explore the applicability of HDBSCAN, a hierarchical DBSCAN variant, for clustering radar measurements. To improve results achieved by its unsupervised version, we propose the use of cluster-level constraints based on aggregated background information from cluster candidates. Further, we propose the application of a distance threshold to avoid selection of small clusters at low hierarchy levels. Based on exemplary traffic scenes from nuScenes, a publicly available autonomous driving data set, we test our constraint-based approach along with other methods, including label-based semi-supervised HDBSCAN. Our experiments demonstrate that cluster-level constraints help to adjust HDBSCAN to the given application context and can therefore achieve considerably better results than the unsupervised method. However, the approach requires carefully selected constraint criteria that can be difficult to choose in constantly changing environments.

show abstract

“…Schubert looked at using Range-Doppler images as the domain to perform classification. They coped with the clustering of all these reflections into appropriate groups to extract features that are classified in a support vector machine (SVM) classifier [ 6 ]. Further works focused on using different domains of information to achieve vehicle and pedestrian classification, such as the phase characteristic of object signature [ 7 ], and the defined parameter, root radar cross section (RRCS) [ 8 ].…”

Section: Introductionmentioning

confidence: 99%

Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar

Gao

Lai

et al. 2020

Sensors

View full text Add to dashboard Cite

Human–vehicle classification is an essential component to avoiding accidents in autonomous driving. The classification technique based on the automotive radar sensor has been paid more attention by related researchers, owing to its robustness to low-light conditions and severe weather. In the paper, we propose a hybrid support vector machine–convolutional neural network (SVM-CNN) approach to address the class-imbalance classification of vehicles and pedestrians with limited experimental radar data available. A two-stage scheme with the combination of feature-based SVM technique and deep learning-based CNN is employed. In the first stage, the modified SVM technique based on these distinct physical features is firstly used to recognize vehicles to effectively alleviate the imbalance ratio of vehicles to pedestrians in the data level. Then, the residual unclassified images will be used as inputs to the deep network for the subsequent classification, and we introduce a weighted false error function into deep network architectures to enhance the class-imbalance classification performance at the algorithm level. The proposed SVM-CNN approach takes full advantage of both the locations of underlying class in the entire Range-Doppler image and automatical local feature learning in the CNN with sliding filter bank to improve the classification performance. Experimental results demonstrate the superior performances of the proposed method with the F 1 score of 0.90 and area under the curve (AUC) of the receiver operating characteristic (ROC) of 0.99 over several state-of-the-art methods with limited experimental radar data available in a 77 GHz automotive radar.

show abstract

Clustering of high resolution automotive radar detections and subsequent feature extraction for classification of road users

Cited by 36 publications

References 2 publications

CNN Based Road User Detection Using the 3D Radar Cube

CNN Based Road User Detection Using the 3D Radar Cube

Constraint-Based Hierarchical Cluster Selection in Automotive Radar Data

Hybrid SVM-CNN Classification Technique for Human–Vehicle Targets in an Automotive LFMCW Radar

Contact Info

Product

Resources

About