BoostRad: Enhancing Object Detection by Boosting Radar Reflections

TL;DR

BoostRad enhances automotive radar object detection by training a neural network to sharpen radar reflections, reducing clutter and improving resolution before applying object detection, outperforming existing methods.

Contribution

Introduces BoostRad, a novel two-stage neural network approach that explicitly narrows radar PSF and boosts reflections, improving detection accuracy over end-to-end methods.

Findings

BoostRad outperforms reference methods on RADDet and CARRADA datasets.

The boosting DNN effectively reduces clutter and sharpens radar images.

Domain knowledge integration improves training of the boosting network.

Abstract

Automotive radars have an important role in autonomous driving systems. The main challenge in automotive radar detection is the radar's wide point spread function (PSF) in the angular domain that causes blurriness and clutter in the radar image. Numerous studies suggest employing an 'end-to-end' learning strategy using a Deep Neural Network (DNN) to directly detect objects from radar images. This approach implicitly addresses the PSF's impact on objects of interest. In this paper, we propose an alternative approach, which we term "Boosting Radar Reflections" (BoostRad). In BoostRad, a first DNN is trained to narrow the PSF for all the reflection points in the scene. The output of the first DNN is a boosted reflection image with higher resolution and reduced clutter, resulting in a sharper and cleaner image. Subsequently, a second DNN is employed to detect objects within the boosted reflection image. We develop a novel method for training the boosting DNN that incorporates domain knowledge of radar's PSF characteristics. BoostRad's performance is evaluated using the RADDet and CARRADA datasets, revealing its superiority over reference methods.