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

arXiv: https://arxiv.org/abs/1905.11703 · HTML: https://mlsanity.com/paper/1905.11703/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2019.

## Built on by (most cited first, 6 of 6)

- [RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applications](https://mlsanity.com/paper/2104.02493/) (2021)
- [RadSimReal: Bridging the Gap Between Synthetic and Real Data in Radar Object Detection With Simulation](https://mlsanity.com/paper/2404.18150/) (2024)
- [DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification](https://mlsanity.com/paper/2202.08519/) (2022)
- [Investigation of Uncertainty of Deep Learning-based Object Classification on Radar Spectra](https://mlsanity.com/paper/2106.05870/) (2021)
- [BoostRad: Enhancing Object Detection by Boosting Radar Reflections](https://mlsanity.com/paper/2404.17861/) (2024)
- [ROSS: Radar Off-road Semantic Segmentation](https://mlsanity.com/paper/2310.13551/) (2023)

## Abstract (arXiv)

Radar-based road user classification is an important yet still challenging task towards autonomous driving applications. The resolution of conventional automotive radar sensors results in a sparse data representation which is tough to recover by subsequent signal processing. In this article, classifier ensembles originating from a one-vs-one binarization paradigm are enriched by one-vs-all correction classifiers. They are utilized to efficiently classify individual traffic participants and also identify hidden object classes which have not been presented to the classifiers during training. For each classifier of the ensemble an individual feature set is determined from a total set of 98 features. Thereby, the overall classification performance can be improved when compared to previous methods and, additionally, novel classes can be identified much more accurately. Furthermore, the proposed structure allows to give new insights in the importance of features for the recognition of individual classes which is crucial for the development of new algorithms and sensor requirements.