Radar-based Feature Design and Multiclass Classification for Road User Recognition

Abstract

The classification of individual traffic participants is a complex task, especially for challenging scenarios with multiple road users or under bad weather conditions. Radar sensors provide an -with respect to well established camera systems -orthogonal way of measuring such scenes. In order to gain accurate classification results, 50 different features are extracted from the measurement data and tested on their performance. From these features a suitable subset is chosen and passed to random forest and long short-term memory (LSTM) classifiers to obtain class predictions for the radar input. Moreover, it is shown why data imbalance is an inherent problem in automotive radar classification when the dataset is not sufficiently large. To overcome this issue, classifier binarization is used among other techniques in order to better account for underrepresented classes. A new method to couple the resulting probabilities is proposed and compared to others with great success. Final results show substantial improvements when compared to ordinary multiclass classification.

Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles

“…Thus, in [5] and [6], five classes of dynamic road users are recognized and separated from a sixth class comprising measurement artifacts and other undesired data points. This article is based on the work presented in [6]. By applying different kinds of multiclass binarization techniques, the classification performance is improved, there.…”

Automated Ground Truth Estimation of Vulnerable Road Users in Automotive Radar Data Using GNSS

“…Scans from the two sensors are hereby treated as different measurements. These features were previously found to be well-suited characteristics for the classification of VRUs in [1]. The reflected power is compensated for free-space path loss using R 4 correction where R is the range between sensor and detection.…”

“…A human labeler is simply not as accustomed to radar measurements as to image data, for example. One solution to this problem is to find models that require less data to converge, i.e., using classification models with small amount of training coefficients as in [1]. Moreover, techniques such as active learning were found to be able to reduce the required amount of data for radar-based classification tasks [2].…”

CNN Based Road User Detection Using the 3D Radar Cube

“…[18] also aims to improve the clustering with a multi-stage approach. [3] follows the work of [2] for clustering and classification, but tests and ranks further cluster-wise features in a backward elimination study.…”

“…Since a single reflection does not convey enough information to segment and classify an entire object, many radar based road user detection methods (e.g. [1], [2], [3]) first cluster radar targets by their target-level features. Clusters are then classified as a whole based on derived statistical features (e.g.…”