RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles
This work addresses the need for real-time object detection in autonomous vehicles, offering a domain-specific improvement that is incremental by building on existing radar and detection methods.
The paper tackles the bottleneck of slow region proposal algorithms in two-stage object detection networks for autonomous driving by introducing RRPN, a radar-based real-time method that maps radar detections to image coordinates and scales anchor boxes based on object distance, achieving over 100x faster operation and higher precision and recall compared to Selective Search on the NuScenes dataset.
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 .