Histogram-based Deep Learning for Automotive Radar
This work addresses the problem of interpreting noisy radar point clouds for automotive applications, representing an incremental improvement over existing methods.
The researchers tackled automotive radar object classification by proposing a histogram-based deep learning approach that computes point cloud histograms and processes them with a multi-layer perceptron. The method matches and surpasses state-of-the-art approaches in classification performance while offering improved robustness to noise and missing features.
There are various automotive applications that rely on correctly interpreting point cloud data recorded with radar sensors. We present a deep learning approach for histogram-based processing of such point clouds. Compared to existing methods, the design of our approach is extremely simple: it boils down to computing a point cloud histogram and passing it through a multi-layer perceptron. Our approach matches and surpasses state-of-the-art approaches on the task of automotive radar object type classification. It is also robust to noise that often corrupts radar measurements, and can deal with missing features of single radar reflections. Finally, the design of our approach makes it more interpretable than existing methods, allowing insightful analysis of its decisions.