# RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles

## TL;DR

RRPN is a real-time radar-based region proposal network that significantly speeds up object detection in autonomous vehicles while improving accuracy, addressing the bottleneck in traditional two-stage detection systems.

## Contribution

Introduces RRPN, a novel radar-based region proposal method that enhances speed and accuracy for autonomous vehicle object detection.

## Key findings

- RRPN operates over 100x faster than Selective Search.
- RRPN achieves higher detection precision and recall.
- The method is validated on the NuScenes dataset with Fast R-CNN.

## Abstract

Region proposal algorithms play an important role in most state-of-the-art two-stage object detection networks by hypothesizing object locations in the image. Nonetheless, region proposal algorithms are known to be the bottleneck in most two-stage object detection networks, increasing the processing time for each image and resulting in slow networks not suitable for real-time applications such as autonomous driving vehicles. In this paper we introduce RRPN, a Radar-based real-time region proposal algorithm for object detection in autonomous driving vehicles. RRPN generates object proposals by mapping Radar detections to the image coordinate system and generating pre-defined anchor boxes for each mapped Radar detection point. These anchor boxes are then transformed and scaled based on the object's distance from the vehicle, to provide more accurate proposals for the detected objects. We evaluate our method on the newly released NuScenes dataset [1] using the Fast R-CNN object detection network [2]. Compared to the Selective Search object proposal algorithm [3], our model operates more than 100x faster while at the same time achieves higher detection precision and recall. Code has been made publicly available at https://github.com/mrnabati/RRPN .