Automotive Radar Data Acquisition using Object Detection

TL;DR

This paper presents an adaptive radar data acquisition algorithm that leverages object detection to optimize sampling, improving reconstruction quality and efficiency in autonomous vehicle sensing.

Contribution

It introduces a novel adaptive sampling algorithm using linear programming and analyzes hardware-efficient measurement matrices for radar data acquisition.

Findings

Significant time savings with reduced radar block size by a factor of 2

Effective object reconstruction at 10% sampling rate

Performance of Binary Permuted Diagonal matrix comparable to Gaussian matrices

Abstract

The growing urban complexity demands an efficient algorithm to acquire and process various sensor information from autonomous vehicles. In this paper, we introduce an algorithm to utilize object detection results from the image to adaptively sample and acquire radar data using Compressed Sensing (CS). This novel algorithm is motivated by the hypothesis that with a limited sampling budget, allocating more sampling budget to areas with the object as opposed to a uniform sampling ultimately improves relevant object detection performance. We improve detection performance by dynamically allocating a lower sampling rate to objects such as buses than pedestrians leading to better reconstruction than baseline across areas with objects of interest. We automate the sampling rate allocation using linear programming and show significant time savings while reducing the radar block size by a factor of 2. We also analyze a Binary Permuted Diagonal measurement matrix for radar acquisition which is hardware-efficient and show its performance is similar to Gaussian and Binary Permuted Block Diagonal matrix. Our experiments on the Oxford radar dataset show an effective reconstruction of objects of interest with 10% sampling rate. Finally, we develop a transformer-based 2D object detection network using the NuScenes radar and image data.