Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles
This work addresses the challenging problem of classifying sparse radar data for autonomous driving, with incremental improvements in classification accuracy and novelty detection.
The paper tackles radar-based road user classification for autonomous driving by enriching classifier ensembles with correction classifiers to improve classification and novelty detection, achieving improved overall performance and more accurate identification of novel classes compared to previous methods.
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.