Published on Wed May 01 2019

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

Ramin Nabati, Hairong Qi

RRPN is a Radar-based real-time region proposal algorithm for object detection in autonomous driving vehicles. Compared to the Selective Search object proposal algorithm [3], our model operates more than 100x faster while at the same time achieving higher detection precision and recall.

0
0
0
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 .

Thu Sep 17 2020
Computer Vision
Radar-Camera Sensor Fusion for Joint Object Detection and Distance Estimation in Autonomous Vehicles
Radar object proposal network uses radar point clouds to generate 3D proposals from a set of 3D prior boxes. These proposals are mapped to the image and fed into a Radar Proposal Refinement(RPR) network for objectness score prediction.
0
0
0
Tue Nov 10 2020
Computer Vision
CenterFusion: Center-based Radar and Camera Fusion for 3D Object Detection
CenterFusion uses a center point detection network to identify objects by identifying their center points on the image. It then solves the key data association problem using a novel frustum-based method to associate the radar detections to their corresponding object's center point.
0
0
0
Wed Apr 17 2019
Machine Learning
2D Car Detection in Radar Data with PointNets
This work presents an approach to detect 2D objects solely depending on sparse radar data using PointNets. In literature, only methods are presented so far which perform either object classification or bounding box estimation for objects. The results show the great potential of object detection in high-resolution radar
0
0
0
Sun May 02 2021
Computer Vision
RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users
0
0
0
Tue Feb 09 2021
Computer Vision
RODNet: A Real-Time Radar Object Detection Network Cross-Supervised by Camera-Radar Fused Object 3D Localization
RODNet is a deep radar object detection network. It is cross-supervised by a camera-radar fused algorithm without laborious annotation efforts. The network is able to effectively detect objects from the radio frequency (RF) images in real-time.
0
0
0
Sat Apr 11 2020
Computer Vision
Probabilistic Oriented Object Detection in Automotive Radar
Autonomous radar has been an integral part of advanced driver assistance systems. Conventional automotive radars use digital signal processing (DSP) algorithms to process raw data into sparse radar pins. In this paper, we propose a deep-learning based algorithm for radar object detection.
0
0
0