# Distant Vehicle Detection Using Radar and Vision

## TL;DR

This paper presents a method combining radar and vision data to improve the detection of distant vehicles for autonomous driving, addressing the limitations of image-based detectors on small, far-away objects.

## Contribution

It introduces a novel approach that integrates radar with vision to enhance distant vehicle detection and proposes an automated data generation method for training.

## Key findings

- Radar integration improves detection accuracy for distant vehicles.
- Automated data generation reduces manual labeling effort.
- Enhanced detection performance on challenging small-object scenarios.

## Abstract

For autonomous vehicles to be able to operate successfully they need to be aware of other vehicles with sufficient time to make safe, stable plans. Given the possible closing speeds between two vehicles, this necessitates the ability to accurately detect distant vehicles. Many current image-based object detectors using convolutional neural networks exhibit excellent performance on existing datasets such as KITTI. However, the performance of these networks falls when detecting small (distant) objects. We demonstrate that incorporating radar data can boost performance in these difficult situations. We also introduce an efficient automated method for training data generation using cameras of different focal lengths.