# DeepReflecs: Deep Learning for Automotive Object Classification with Radar Reflections

arXiv: https://arxiv.org/abs/2010.09273 · HTML: https://mlsanity.com/paper/2010.09273/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Oct 2020.

## Built on by (most cited first, 9 of 9)

- [Improved Orientation Estimation and Detection with Hybrid Object Detection Networks for Automotive Radar](https://mlsanity.com/paper/2205.02111/) (2022)
- [DeepFusion: A Robust and Modular 3D Object Detector for Lidars, Cameras and Radars](https://mlsanity.com/paper/2209.12729/) (2022)
- [A recurrent CNN for online object detection on raw radar frames](https://mlsanity.com/paper/2212.11172/) (2022)
- [Improved Multi-Scale Grid Rendering of Point Clouds for Radar Object Detection Networks](https://mlsanity.com/paper/2305.15836/) (2023)
- [Self-Supervised Velocity Estimation for Automotive Radar Object Detection Networks](https://mlsanity.com/paper/2207.03146/) (2022)
- [Improving Uncertainty of Deep Learning-based Object Classification on Radar Spectra using Label Smoothing](https://mlsanity.com/paper/2109.12851/) (2021)
- [Exploiting Sparsity in Automotive Radar Object Detection Networks](https://mlsanity.com/paper/2308.07748/) (2023)
- [Leveraging Self-Supervised Instance Contrastive Learning for Radar Object Detection](https://mlsanity.com/paper/2402.08427/) (2024)
- [Histogram-based Deep Learning for Automotive Radar](https://mlsanity.com/paper/2303.02975/) (2023)

## Abstract (arXiv)

This paper presents an novel object type classification method for automotive applications which uses deep learning with radar reflections. The method provides object class information such as pedestrian, cyclist, car, or non-obstacle. The method is both powerful and efficient, by using a light-weight deep learning approach on reflection level radar data. It fills the gap between low-performant methods of handcrafted features and high-performant methods with convolutional neural networks. The proposed network exploits the specific characteristics of radar reflection data: It handles unordered lists of arbitrary length as input and it combines both extraction of local and global features. In experiments with real data the proposed network outperforms existing methods of handcrafted or learned features. An ablation study analyzes the impact of the proposed global context layer.