Dataset for Robust and Accurate Leading Vehicle Velocity Recognition

TL;DR

This paper introduces a new dataset designed to improve the robustness and accuracy of leading vehicle velocity recognition in various challenging driving conditions, aiding development of advanced driver-assistance systems.

Contribution

The authors created a comprehensive dataset for benchmarking vehicle velocity recognition under diverse and difficult environmental conditions, including rain and nighttime.

Findings

Dataset enables benchmarking in challenging conditions

Supports development of robust velocity recognition models

Facilitates progress in autonomous driving technology

Abstract

Recognition of the surrounding environment using a camera is an important technology in Advanced Driver-Assistance Systems and Autonomous Driving, and recognition technology is often solved by machine learning approaches such as deep learning in recent years. Machine learning requires datasets for learning and evaluation. To develop robust recognition technology in the real world, in addition to normal driving environment, data in environments that are difficult for cameras such as rainy weather or nighttime are essential. We have constructed a dataset that one can benchmark the technology, targeting the velocity recognition of the leading vehicle. This task is an important one for the Advanced Driver-Assistance Systems and Autonomous Driving. The dataset is available at https://signate.jp/competitions/657