DeepHybrid: Deep Learning on Automotive Radar Spectra and Reflections for Object Classification
This work addresses the problem of reliable object classification for automated vehicles, specifically improving systems like automatic emergency braking or collision avoidance, but it is incremental as it builds on existing radar and deep learning techniques.
The paper tackles object classification for automated vehicles using automotive radar sensors by proposing DeepHybrid, a method that combines radar spectra and reflection attributes as inputs to a neural network, improving classification performance and achieving a resource-efficient design through neural architecture search, with NAS yielding an almost one order of magnitude smaller network while preserving accuracy.
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 cross-section. 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.